Compare commits
17 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 yaojingang
|
4eb11f923d | ||
|
YAO
|
c37915e4f6 | ||
|
yaojingang
|
6725a57538 | ||
|
YAO
|
8455eff29a | ||
|
yaojingang
|
24bea607a2 | ||
|
YAO
|
4eef8d8682 | ||
|
yaojingang
|
01e750dbb2 | ||
|
YAO
|
0556767dff | ||
|
yaojingang
|
9f793d59cf | ||
|
YAO
|
5fbed1d273 | ||
|
yaojingang
|
6ccb9c86ba | ||
|
yaojingang
|
f37e78def3 | ||
|
YAO
|
00a0a1f0c6 | ||
|
CooperSheroy
|
ff7381948e | ||
|
YAO
|
21b243e0f5 | ||
|
yaojingang
|
a30bb845d9 | ||
|
YAO
|
715fc750e0 |
@@ -23,6 +23,7 @@ Use `make ci-test` as the default full verification command before calling a cha
|
||||
Common focused checks:
|
||||
|
||||
- CLI changes: `python3 tests/verify_yao_cli.py`
|
||||
- Operator UX changes: `python3 tests/verify_operator_ux.py`
|
||||
- Skill overview report changes: `python3 tests/verify_skill_overview.py`
|
||||
- Review Studio changes: `python3 tests/verify_review_studio.py`
|
||||
- Trust or script inventory changes: `python3 tests/verify_trust_check.py`
|
||||
@@ -119,6 +120,8 @@ Clean test-only scratch directories after verification with `find tests -maxdept
|
||||
- `scripts/skill_report_model.py`, `scripts/skill_report_metrics.py`, `scripts/skill_report_charts.py`: skill overview data model, scoring, and inline SVG chart generation.
|
||||
- `scripts/yao_cli_config.py`: CLI target maps, archetype heuristics, diagnosis copy, and side-effect-free shaping helpers.
|
||||
- `scripts/yao_cli_parser.py`: CLI argparse command surface, flags, choices, and command handler binding.
|
||||
- `scripts/yao_cli_operator_commands.py`: read-only operator diagnostics for active install status, localized homepage sync, and PR review reports. Keep install checks non-mutating, docs sync explicit, and PR review free of merge/write actions.
|
||||
- `scripts/yao_cli_parser_operator.py`: argparse surface for operator UX commands. Keep command names stable and route all behavior into `yao_cli_operator_commands.py`.
|
||||
- `scripts/yao_cli_telemetry.py`: opt-in metadata-only CLI run telemetry. Keep it free of prompt, argument, output, transcript, note, or message capture.
|
||||
- `scripts/import_telemetry_events.py`: external telemetry importer. Validate the whole input before appending events, and keep raw prompt/output/transcript/message/note fields blocked.
|
||||
- `scripts/emit_telemetry_event.py`: external client telemetry emitter. It may append one normalized metadata event to a local spool, but must never accept or write raw prompt, output, transcript, message, note, argument, or private content.
|
||||
|
||||
@@ -1,8 +1,12 @@
|
||||
PYTHON ?= python3
|
||||
REQUIRED_PYTHON_VERSION ?= 3.11
|
||||
LOCAL_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills.disabled/yao-meta-skill
|
||||
ACTIVE_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills/yao-meta-skill
|
||||
|
||||
.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check yao-cli-world-class-check skill-overview-check skill-interpretation-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-kit-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-kit-check world-class-preflight-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check evidence-consistency-check feedback-check adaptation-safety-check skillops-opportunity-check daily-skillops-check weekly-curator-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean
|
||||
.PHONY: python-version-check eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check yao-cli-world-class-check operator-ux-check skill-overview-check skill-interpretation-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-kit-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-kit-check world-class-preflight-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check evidence-consistency-check feedback-check adaptation-safety-check skillops-opportunity-check daily-skillops-check weekly-curator-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean
|
||||
|
||||
python-version-check:
|
||||
@$(PYTHON) -c 'import sys; required=tuple(map(int, "$(REQUIRED_PYTHON_VERSION)".split("."))); actual=sys.version_info[:2]; raise SystemExit(0 if actual >= required else "Python {}.{}+ is required; {}.{} is active. Set PYTHON=/path/to/python{} or create a Python {} virtualenv.".format(*required, *actual, "$(REQUIRED_PYTHON_VERSION)", "$(REQUIRED_PYTHON_VERSION)"))'
|
||||
|
||||
eval:
|
||||
$(PYTHON) scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt
|
||||
@@ -40,6 +44,9 @@ yao-cli-check:
|
||||
yao-cli-world-class-check:
|
||||
$(PYTHON) tests/verify_yao_cli_world_class.py
|
||||
|
||||
operator-ux-check:
|
||||
$(PYTHON) tests/verify_operator_ux.py
|
||||
|
||||
skill-overview-check:
|
||||
$(PYTHON) tests/verify_skill_overview.py
|
||||
|
||||
@@ -266,11 +273,11 @@ sync-local-install: package-check
|
||||
sync-active-install: package-check
|
||||
$(PYTHON) scripts/sync_local_install.py --install-dir "$(ACTIVE_SKILL_INSTALL_DIR)"
|
||||
|
||||
test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check skill-overview-check skill-interpretation-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-kit-check world-class-preflight-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check evidence-consistency-check feedback-check adaptation-safety-check skillops-opportunity-check daily-skillops-check weekly-curator-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check
|
||||
test: python-version-check eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check python-compat-check architecture-maintainability-check yao-cli-check operator-ux-check skill-overview-check skill-interpretation-check skill-report-metrics-check skill-report-charts-check html-rendering-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-submission-kit-check world-class-preflight-check world-class-submission-review-check world-class-runbook-check world-class-claim-guard-check benchmark-reproducibility-check evidence-consistency-check feedback-check adaptation-safety-check skillops-opportunity-check daily-skillops-check weekly-curator-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check
|
||||
|
||||
ci-test:
|
||||
ci-test: python-version-check
|
||||
$(PYTHON) scripts/ci_test.py
|
||||
|
||||
clean:
|
||||
rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_python_compat tests/tmp_architecture_maintainability tests/tmp_skill_overview tests/tmp_skill_interpretation tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_skill_os2_audit tests/tmp_skill_os2_coverage tests/tmp_world_class_evidence tests/tmp_world_class_evidence_ledger tests/tmp_world_class_evidence_intake tests/tmp_world_class_submission_review tests/tmp_world_class_operator_runbook tests/tmp_world_class_claim_guard tests/tmp_benchmark_reproducibility tests/tmp_evidence_consistency tests/tmp_feedback tests/tmp_daily_skillops tests/tmp_weekly_curator tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_telemetry_native_host tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md
|
||||
rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_operator_ux tests/tmp_python_compat tests/tmp_architecture_maintainability tests/tmp_skill_overview tests/tmp_skill_interpretation tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_skill_os2_audit tests/tmp_skill_os2_coverage tests/tmp_world_class_evidence tests/tmp_world_class_evidence_ledger tests/tmp_world_class_evidence_intake tests/tmp_world_class_submission_review tests/tmp_world_class_operator_runbook tests/tmp_world_class_claim_guard tests/tmp_benchmark_reproducibility tests/tmp_evidence_consistency tests/tmp_feedback tests/tmp_daily_skillops tests/tmp_weekly_curator tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_telemetry_native_host tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md
|
||||
find . -type d -name __pycache__ -prune -exec rm -rf {} +
|
||||
|
||||
@@ -8,11 +8,11 @@
|
||||
[](docs/README.fr-FR.md)
|
||||
[](docs/README.ru-RU.md)
|
||||
|
||||
`YAO` stands for `Yielding AI Outcomes` — the goal is not to generate more prompt text, but to produce reusable AI assets and real operational outcomes.
|
||||
`YAO` stands for `Yielding AI Outcomes`: the goal is not to generate more prompt text, but to produce reusable AI assets and real operational outcomes.
|
||||
|
||||
`yao-meta-skill` creates, evaluates, packages, and governs reusable agent skills. The 1.0 line focused on turning repeated workflows into installable, readable, cross-platform skill packages. The 2.0 line expands that factory into a Skill OS: a governed system for modeling a skill once, compiling it for multiple targets, testing its behavior, reviewing its release evidence, and tracking the next iteration.
|
||||
|
||||
[Quick Start](#quick-start) · [Skill OS 2.0](#skill-os-20-upgrade) · [1.0 vs 2.0](#from-10-to-20) · [Benchmark](#weighted-quality-benchmark) · [Examples](examples/README.md) · [Evals](evals/README.md) · [Failure Library](failures/README.md) · [Method Doctrine](#method-doctrine)
|
||||
[Quick Start](#quick-start) · [Skill OS 2.0](#skill-os-20-upgrade) · [1.0 vs 2.0](#from-10-to-20) · [Operator UX](#operator-ux-commands) · [Benchmark](#weighted-quality-benchmark) · [Examples](examples/README.md) · [Evals](evals/README.md) · [Failure Library](failures/README.md) · [Method Doctrine](#method-doctrine)
|
||||
|
||||
## Skill OS 2.0 Upgrade
|
||||
|
||||
@@ -53,6 +53,20 @@ See the companion artifacts:
|
||||
- **Keep a skill useful after release**: use metadata-only telemetry, adoption drift, feedback logs, SkillOps reports, and adaptive proposals to decide whether the next move should be documentation, an eval, a skill patch, or a governance update.
|
||||
- **Compare with other meta-skill approaches**: keep Anthropic/OpenAI-style conversational creation and lean instruction writing where they fit, then use `yao-meta-skill` when the package needs evidence, portability, release gates, and repeatable maintenance.
|
||||
|
||||
## Operator UX Commands
|
||||
|
||||
These read-only helper commands turn common maintainer questions into repeatable diagnostics:
|
||||
|
||||
```bash
|
||||
python3 scripts/yao.py install-status --expected-source .
|
||||
python3 scripts/yao.py localized-doc-sync-check
|
||||
python3 scripts/yao.py pr-review-report 4 --repo yaojingang/yao-meta-skill
|
||||
```
|
||||
|
||||
- `install-status` explains whether the active skill is coming from `.codex/skills`, `.agents/skills`, or the disabled mirror, and flags duplicate active installs.
|
||||
- `localized-doc-sync-check` verifies that the Chinese README carries the public homepage sections that were added to the English README.
|
||||
- `pr-review-report` reads GitHub PR metadata, changed files, status checks, and suggested local commands without merging or mutating the PR.
|
||||
|
||||
## Capability Surface
|
||||
|
||||
It turns rough workflows, transcripts, prompts, notes, and runbooks into reusable skill packages with:
|
||||
@@ -127,6 +141,8 @@ Read it in 10 seconds:
|
||||
|
||||
This benchmark is a project-level engineering review, scored from `0-10` per dimension and weighted to `100`. GitHub stars are intentionally excluded because they measure ecosystem heat, not meta-skill engineering quality.
|
||||
|
||||
The score is local engineering evidence, not a claim of world-class readiness. Public superiority claims still depend on accepted external and human evidence in the world-class ledger.
|
||||
|
||||
Weighted score formula: `sum(score / 10 * weight)`.
|
||||
|
||||
| Meta Skill | Method Depth 15 | Context Discipline 10 | Toolchain 15 | Eval/Test Rigor 20 | Governance 15 | Portability 10 | Onboarding/Review 5 | Local Reliability 10 | Weighted Score |
|
||||
@@ -141,6 +157,20 @@ Weighted score formula: `sum(score / 10 * weight)`.
|
||||
| 2 | Anthropic Skill Creator | 67.5 | Strong methodology and iteration loop, with weaker local execution reliability and governance coverage. |
|
||||
| 3 | OpenAI Skill Creator | 50.5 | Best treated as a concise skill-writing method guide rather than a full engineering system. |
|
||||
|
||||
## Human Blind A/B Review Snapshot
|
||||
|
||||
On 2026-06-29, a single human reviewer compared `yao-meta-skill` with the bundled OpenAI `skill-creator` across five realistic skill-creation scenarios: support triage, revenue reconciliation, webinar repurposing, incident postmortems, and PR review follow-up. The reviewer confirmed decisions were completed before the answer key was opened.
|
||||
|
||||
Result: `yao-meta-skill` was selected in `5/5` cases.
|
||||
|
||||
Evidence:
|
||||
|
||||
- Review entrypoint: [reports/blind-human-review-2026-06-29/index.html](reports/blind-human-review-2026-06-29/index.html)
|
||||
- Adjudication summary: [reports/blind-human-review-2026-06-29/adjudication.md](reports/blind-human-review-2026-06-29/adjudication.md)
|
||||
- Recorded decisions: [reports/blind-human-review-2026-06-29/review-decisions.recorded.json](reports/blind-human-review-2026-06-29/review-decisions.recorded.json)
|
||||
|
||||
Boundary: this is single-reviewer blind preference evidence. It is not provider-backed independent model execution evidence, and the per-case rationale fields are still empty.
|
||||
|
||||
## Best-Fit Scenarios
|
||||
|
||||
- Choose **Yao Meta Skill** when the target is a reusable team asset with explicit boundaries, trigger evaluation, governance, packaging, portability, and local execution checks.
|
||||
@@ -150,6 +180,20 @@ Weighted score formula: `sum(score / 10 * weight)`.
|
||||
|
||||
## Quick Start
|
||||
|
||||
Install the skill globally for Codex first:
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a codex -g -y
|
||||
```
|
||||
|
||||
To install it for every supported agent, replace `-a codex` with `-a '*'`:
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a '*' -g -y
|
||||
```
|
||||
|
||||
After installation, restart the client. Then ask for tasks such as "create a skill from this workflow", "improve this existing skill", "evaluate this skill", or "add evals to this skill" to trigger `yao-meta-skill`.
|
||||
|
||||
1. Describe the workflow, prompt set, or repeated task you want to turn into a skill.
|
||||
2. Start with a short, human intent dialogue so the real job, outputs, exclusions, constraints, and standards are explicit.
|
||||
3. Let `quickstart` clarify intent first, then run silent benchmark scan and reference synthesis; it only surfaces explicit questions when intent is still unclear or when there is a real design conflict.
|
||||
@@ -221,6 +265,22 @@ python3 scripts/yao.py evidence-consistency .
|
||||
|
||||
Development source: this repository is the source of truth for authoring and review.
|
||||
|
||||
Use Python 3.11 or newer for local development. GitHub Actions runs the test suite on Python 3.11, and the Makefile checks the active interpreter before running `make test` or `make ci-test`.
|
||||
|
||||
```bash
|
||||
python3.11 -m venv .venv
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
python -m pip install --requirement requirements-ci.txt
|
||||
make ci-test
|
||||
```
|
||||
|
||||
If `python3` points to an older system interpreter, pass the interpreter explicitly:
|
||||
|
||||
```bash
|
||||
make PYTHON=python3.11 ci-test
|
||||
```
|
||||
|
||||
Disabled mirror: `~/.agents/skills.disabled/yao-meta-skill` is the local backup mirror for this source. Keeping the mirror outside `~/.agents/skills` prevents Codex from showing a duplicate `Yao Meta Skill` while this repository is also visible in the active workspace.
|
||||
|
||||
Sync the current source into the disabled mirror:
|
||||
@@ -342,6 +402,7 @@ Full reports: [reports/eval_suite.json](reports/eval_suite.json) and [reports/fa
|
||||
- portability score: `100/100` with neutral activation, execution, trust, and degradation metadata preserved across all exported targets
|
||||
- description optimization suite: root, team frontend review, and governed incident command pass blind and adversarial holdout gates; governed incident command still carries one visible holdout miss, and adversarial calibration plus family drift are now tracked separately
|
||||
- judge-backed blind eval: root, team frontend review, and governed incident command now pass an independent rubric judge on blind holdout prompts
|
||||
- human blind A/B snapshot: a single reviewer selected `yao-meta-skill` over the bundled OpenAI `skill-creator` in `5/5` realistic skill-creation scenarios; evidence is published in [reports/blind-human-review-2026-06-29/adjudication.md](reports/blind-human-review-2026-06-29/adjudication.md)
|
||||
- packaging failure fixtures: invalid metadata, invalid YAML, and unsupported targets fail as expected
|
||||
- failure library regressions: anti-pattern families pass automated checks
|
||||
- governance and resource-boundary checks are part of the default test path
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: yao-meta-skill
|
||||
description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
metadata:
|
||||
author: Yao Team
|
||||
---
|
||||
@@ -15,28 +15,28 @@ metadata:
|
||||
|
||||
## Modes
|
||||
|
||||
- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infrastructure. `Governed`: high-trust, policy-sensitive, or release-critical.
|
||||
- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infra. `Governed`: high-trust/release-critical.
|
||||
- Rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).
|
||||
|
||||
## Compact Workflow
|
||||
|
||||
1. For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
|
||||
2. Capture job, output, exclusions, constraints, standards, and the lightest fit.
|
||||
3. Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
|
||||
4. Write `description` early, test route quality, then add only earned folders and gates.
|
||||
5. Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
|
||||
1. One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
|
||||
2. Capture job, output, exclusions, constraints, standards, lightest fit.
|
||||
3. Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.
|
||||
4. Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.
|
||||
5. Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.
|
||||
|
||||
Playbooks: [Method](references/skill-engineering-method.md), [Intent](references/intent-dialogue.md), [Skill IR](references/skill-ir-method.md), [Output Eval](references/output-eval-method.md), [Review Studio](references/review-studio-method.md).
|
||||
|
||||
## Skill OS 2.0 Gates
|
||||
|
||||
For production, library, governed, or team-distributed work, run Skill IR, target compiler, trigger + output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, and Review Studio gates before release.
|
||||
For production/library/governed/team releases, run Skill IR, compiler, trigger/output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, Review Studio.
|
||||
|
||||
## Governed Package Boundary
|
||||
|
||||
For file-backed, release-critical, or governed packages, name `input_files` as `file-backed fixture` evidence; include `owner`, `review cadence`, `input_files`, `output contract`, `rollback boundary`; require `trust report` and `reports/output_quality_scorecard.md`; mark unavailable telemetry, approvals, metrics, or benchmarks as `missing evidence`; do not fabricate evidence.
|
||||
For file-backed/release-critical/governed packages, name `input_files` as `file-backed fixture`; include `owner`, `review cadence`, `input_files`, `output contract`, `rollback boundary`; require `trust report` and `reports/output_quality_scorecard.md`; mark unavailable telemetry/approvals/metrics/benchmarks as `missing evidence`; do not fabricate evidence.
|
||||
|
||||
Preserve audit labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.
|
||||
Preserve labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.
|
||||
|
||||
## First-Turn Style
|
||||
|
||||
@@ -46,8 +46,8 @@ Preserve audit labels literally when they apply: `file-backed fixture`, `input_f
|
||||
|
||||
## Output Contract
|
||||
|
||||
Unless asked otherwise, produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, and a short summary of boundary, exclusions, gates, and next steps.
|
||||
Create/refactor/package: produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, boundary/exclusion/gate summary. Audit/evaluate-only: findings + proposed fixes; edit files only if asked. No-skill: no files.
|
||||
|
||||
## Reference Map
|
||||
|
||||
Primary: [Method](references/skill-engineering-method.md), [Artifact Design](references/artifact-design-doctrine.md), [Systems Thinking](references/systems-thinking-doctrine.md), [Governance](references/governance.md), [SkillOps Decision](references/skillops-decision-policy.md).
|
||||
Primary: [Method](references/skill-engineering-method.md), [Artifact Design](references/artifact-design-doctrine.md), [Systems](references/systems-thinking-doctrine.md), [Governance](references/governance.md), [SkillOps](references/skillops-decision-policy.md).
|
||||
|
||||
@@ -69,6 +69,20 @@ Formule du score pondéré : `sum(score / 10 * poids)`.
|
||||
|
||||
## Démarrage rapide
|
||||
|
||||
Pour utiliser cette skill directement dans Codex, installez-la d'abord dans les skills globales :
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a codex -g -y
|
||||
```
|
||||
|
||||
Pour l'installer dans tous les agents pris en charge, remplacez `-a codex` par `-a '*'` :
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a '*' -g -y
|
||||
```
|
||||
|
||||
Après l'installation, redémarrez le client. Demandez ensuite des tâches comme "create a skill from this workflow", "improve this existing skill", "evaluate this skill" ou "add evals to this skill" pour déclencher `yao-meta-skill`.
|
||||
|
||||
1. Décrivez le workflow, l'ensemble de prompts ou la tâche répétée que vous voulez transformer en skill.
|
||||
2. Commencez par un court dialogue d'intention plus humain pour clarifier le vrai travail, les sorties attendues, les exclusions, les contraintes et les standards qui comptent pour vous.
|
||||
3. Laissez d'abord `quickstart` clarifier l'intention, puis lancer silencieusement benchmark scan et reference synthesis ; des questions explicites ne remontent que si l'intention reste ambiguë ou si deux directions de conception se contredisent réellement.
|
||||
|
||||
@@ -69,6 +69,20 @@ flowchart LR
|
||||
|
||||
## クイックスタート
|
||||
|
||||
Codex でこの skill を直接使う場合は、まず global skills にインストールします。
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a codex -g -y
|
||||
```
|
||||
|
||||
対応しているすべての agent にインストールする場合は、`-a codex` を `-a '*'` に置き換えます。
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a '*' -g -y
|
||||
```
|
||||
|
||||
インストール後にクライアントを再起動してください。その後、"create a skill from this workflow"、"improve this existing skill"、"evaluate this skill"、"add evals to this skill" のような依頼で `yao-meta-skill` を起動できます。
|
||||
|
||||
1. skill 化したい workflow、prompt 集合、または反復タスクを説明します。
|
||||
2. まず短いが人間味のある intent dialogue で、実際の job、outputs、boundary、constraints、重視する品質基準を明確にします。
|
||||
3. まず `quickstart` で意図を澄ませ、その後 benchmark scan と reference synthesis を静かに実行します。意図がまだ曖昧なとき、または設計ルートに本当の衝突があるときだけ、追加確認を明示します。
|
||||
|
||||
@@ -69,6 +69,20 @@ flowchart LR
|
||||
|
||||
## Быстрый старт
|
||||
|
||||
Чтобы использовать эту skill напрямую в Codex, сначала установите ее в global skills:
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a codex -g -y
|
||||
```
|
||||
|
||||
Чтобы установить ее во все поддерживаемые agents, замените `-a codex` на `-a '*'`:
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a '*' -g -y
|
||||
```
|
||||
|
||||
После установки перезапустите клиент. Затем используйте запросы вроде "create a skill from this workflow", "improve this existing skill", "evaluate this skill" или "add evals to this skill", чтобы вызвать `yao-meta-skill`.
|
||||
|
||||
1. Опишите workflow, набор prompts или повторяющуюся задачу, которую хотите превратить в skill.
|
||||
2. Сначала проведите короткий, но более человечный intent dialogue, чтобы уточнить реальную job-to-be-done, outputs, exclusions, constraints и те стандарты качества, которые для вас важны.
|
||||
3. Сначала позвольте `quickstart` прояснить намерение, затем тихо выполнить benchmark scan и reference synthesis. Явные уточнения поднимаются только тогда, когда intent все еще неясен или между маршрутами проектирования есть реальный конфликт.
|
||||
|
||||
+130
-23
@@ -2,7 +2,64 @@
|
||||
|
||||
`YAO = Yielding AI Outcomes`，中文可理解为：产出 AI 结果，交付真实成果。它强调的不是生成更多 prompt 文本，而是沉淀可复用的 AI 资产与可落地的实际结果。
|
||||
|
||||
`yao-meta-skill` 是一套轻量但严谨的系统，用来创建、评估、打包和治理可复用的 agent skill。
|
||||
`yao-meta-skill` 用来创建、评估、打包和治理可复用的 agent skill。1.0 的重点是把重复工作流整理成可安装、可阅读、可跨平台的 skill 包；2.0 进一步升级为 Skill OS，把建模、跨端编译、输出评测、评审工作台、证据账本、包体验证、发布门禁和后续迭代串成一套完整流程。
|
||||
|
||||
[快速开始](#快速开始) · [Skill OS 2.0 升级](#skill-os-20-升级) · [从 1.0 到 2.0](#从-10-到-20) · [Operator UX 命令](#operator-ux-命令) · [加权质量评测](#加权质量评测) · [与其他元 Skill 的适用差异](#与其他元-skill-的适用差异)
|
||||
|
||||
## Skill OS 2.0 升级
|
||||
|
||||
Skill OS 2.0 保留 `yao-meta-skill` 原来的轻量入口，但把 skill 的生命周期说得更清楚。它不止生成 `SKILL.md`，还会围绕这个 skill 生成结构化契约、目标平台适配、评测证据、发布门禁和运营报告。
|
||||
|
||||
- **Skill IR（技能中间表示）**：用平台无关的结构记录意图、触发方式、输入输出、边界、参考资料和交付产物。
|
||||
- **目标编译与适配器**：把同一份 skill 语义编译到 OpenAI、Claude、通用 agent skill、Agent Skills 兼容包和 VS Code 使用场景。
|
||||
- **输出评测实验室**：覆盖触发评测、输出断言、执行证据、耗时与 token 证据、基准复现、盲评材料包、答案钥匙和评审裁决报告。
|
||||
- **Review Studio 2.0（评审工作台）**：把意图、触发、输出评测、上下文成本、运行时检查、信任扫描、Skill Atlas、采用漂移、豁免、批注、发布证据、警告、阻塞项和修复动作放在同一个 HTML 页面。
|
||||
- **证据与发布治理**：提供证据一致性、包体验证、安装模拟、运行时权限探测、世界级证据接收、证据账本、操作运行手册和公开宣传守卫。
|
||||
- **SkillOps 闭环**：通过元数据级采用漂移、遥测 hook、自适应建议、日报/周报和组合级漂移信号，把发布后的反馈带回下一轮迭代。
|
||||
|
||||
当前发布口径：仓库已经适合进入测试版和外部试用，但更强的“世界级”公开宣传仍然受证据门禁约束。真实生产模型证据、真人盲评证据、原生权限执行和真实客户端遥测会继续作为独立证据任务推进，不会被包装成已经完成。
|
||||
|
||||
相关产物：
|
||||
|
||||
- [1.0 vs 2.0 可视化对比报告](../.previews/yao-meta-skill-2-comparison/index.html)
|
||||
- [中文桌面预览图](../.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2.png)
|
||||
- [英文桌面预览图](../.previews/yao-meta-skill-2-comparison/yao-meta-skill-1-vs-2-en.png)
|
||||
|
||||
## 从 1.0 到 2.0
|
||||
|
||||
| 维度 | 1.0 重点 | 2.0 升级 |
|
||||
| --- | --- | --- |
|
||||
| 产品定位 | 创建、重构、评估和打包可复用 skill。 | 治理 skill 的完整生命周期：创建、编译、评测、评审、发布、遥测和迭代。 |
|
||||
| 架构模型 | 以 `SKILL.md`、`agents/interface.yaml`、manifest 和报告文件为主。 | 引入 Skill IR、目标编译器、适配器、门禁契约、证据账本、发布锁和行动型评审页面。 |
|
||||
| 跨端交付 | 主要覆盖 OpenAI、Claude 和通用包体。 | 扩展到 Agent Skills 兼容包和 VS Code 使用场景，并把兼容结果写入 registry 可读记录。 |
|
||||
| 质量模型 | 触发、结构和报告式评审。 | 输出评测、基准复现、执行证据、失败披露、盲评材料包和证据一致性检查。 |
|
||||
| 报告体验 | 概览 HTML 和首次评审页面。 | 双语 Skill Overview v2、Review Studio 2.0、评审批注、行动卡片、图表和审计型报告契约。 |
|
||||
| 发布边界 | 能生成包体并做基础校验。 | 包体验证、安装模拟、运行时权限探测、发布锁、公开宣传守卫和操作运行手册。 |
|
||||
| 运营闭环 | 更多依赖手动反馈和本地迭代。 | 采用漂移、元数据遥测、SkillOps 报告、自适应建议和组合级漂移检测。 |
|
||||
|
||||
## 2.0 使用场景
|
||||
|
||||
- **从重复工作创建新 skill**：从 workflow 笔记、prompt 集合、转录、runbook 或文档模式出发，生成精简入口、明确输入输出、参考资料、报告和最轻量的必要门禁。
|
||||
- **把个人 skill 升级成团队资产**：补齐接口契约、manifest、目标适配器、信任检查、输出评测、评审豁免、发布说明和 Review Studio 证据，再交给多人复用。
|
||||
- **准备测试版发布**：运行包体验证、安装模拟、兼容检查、运行时权限探测和证据一致性检查，把测试版就绪和更强公开声明分开处理。
|
||||
- **发布后继续迭代**：用元数据级遥测、采用漂移、feedback log、SkillOps 报告和自适应建议判断下一步是补文档、补 eval、改 skill，还是调整治理规则。
|
||||
- **与其他元 skill 搭配使用**：保留 Anthropic/OpenAI 式对话创建和精简写作方法的优势，在需要证据、可移植性、发布门禁和长期维护时用 `yao-meta-skill` 加固。
|
||||
|
||||
## Operator UX 命令
|
||||
|
||||
这组只读辅助命令把维护者最常见的判断变成可复验诊断：
|
||||
|
||||
```bash
|
||||
python3 scripts/yao.py install-status --expected-source .
|
||||
python3 scripts/yao.py localized-doc-sync-check
|
||||
python3 scripts/yao.py pr-review-report 4 --repo yaojingang/yao-meta-skill
|
||||
```
|
||||
|
||||
- `install-status` 会说明当前 skill 是从 `.codex/skills`、`.agents/skills` 还是 disabled mirror（禁用镜像）被发现，并提示是否存在重复激活。
|
||||
- `localized-doc-sync-check` 会检查中文 README 是否同步包含英文 README 首页新增的公开说明模块。
|
||||
- `pr-review-report` 会只读获取 GitHub PR 元数据、变更文件、状态检查和建议本地命令，不会合并或修改 PR。
|
||||
|
||||
## 能力面
|
||||
|
||||
它把粗糙的 workflow、transcript、prompt、notes 和 runbook 转成可复用的 skill 包，并具备：
|
||||
|
||||
@@ -12,40 +69,60 @@
|
||||
- 深度起草前先做一轮更有人味的意图对话，并通过 intent confidence gate 判断理解是否足够清楚；如果不够清楚，会继续补 1 到 2 个高杠杆问题
|
||||
- 深度起草前会静默执行 GitHub benchmark scan 和 reference synthesis，优先学习高质量公开项目与世界级模式；只有遇到真实冲突或不确定性时才显式抬给用户
|
||||
- 会主动询问用户是否有希望借鉴的参考对象，只学习其中的模式抽象、结构和标准，不复制原文或私密内容
|
||||
- 新建 skill 时自动生成一份极简白底 HTML 可视化说明
|
||||
- 新建 skill 时自动生成一份默认中文、可切换英文的 HTML 可视化说明报告
|
||||
- 提供 Review Studio 2.0，把意图、触发、输出评测、上下文、运行时、信任、采用漂移、豁免、批注、发布证据和修复动作汇总到一个页面
|
||||
- 提供 Skill OS 2.0 审计，把世界级要求拆成本地证据、人类证据缺口和外部证据缺口
|
||||
- 提供证据计划、证据账本、证据接收契约、提交审查队列、操作运行手册和公开宣传守卫，避免把计划中的工作写成已经完成
|
||||
- 提供基准复现 manifest、证据一致性检查、输出评测实验室、盲评包和评审裁决报告
|
||||
- 提供运行时权限探测、Python 兼容性门禁、包体验证和安装模拟
|
||||
- 提供 prompt quality profile，把需求模型、RTF 映射、复杂度和提示词质量检查沉淀成 reviewer 可见证据，而不是塞进 `SKILL.md`
|
||||
- 提供 artifact design profile，约束报告、教程、仪表盘、截图和评审页的视觉与质量标准
|
||||
- 提供系统思考模型，记录边界、反馈环、漂移风险、复发失败模式和高杠杆改进点
|
||||
- 首次建包后会自动给出 3 个最有价值的下一步迭代方向
|
||||
- 提供一个紧凑的 HTML review viewer，方便第一次人工理解和评审
|
||||
- 提供一个轻量 feedback log，不必每次都走完整 promotion 流程
|
||||
- 提供本地优先、只记录元数据的 adoption drift 报告、CLI 运行捕获、外部客户端事件 hook、hook recipe 和 JSONL 导入
|
||||
- 提供显式来源的 adaptive proposal loop，从脱敏重复偏好里生成需要人工批准的改进建议
|
||||
- 提供 SkillOps 机会评分、决策策略、日报、周报和组合级漂移信号
|
||||
- 提供一个 with-skill vs baseline 的对比报告，便于快速看增量收益
|
||||
- 提供一个更像对话发现流程的 archetype-aware quickstart，引导新 skill 落到 scaffold、production、library 或 governed 的合适形态
|
||||
- 中性的源元数据以及面向不同客户端的适配层
|
||||
- Skill IR 作为平台无关语义契约，并提供编译报告和客户端适配层
|
||||
- registry audit 元数据，包含 package version、owner、license、checksum 和 compatibility matrix
|
||||
- 内建的治理、晋升和 portability 检查
|
||||
|
||||
## 架构图
|
||||
|
||||
Hero 版可以压缩成一条主线：把零散输入变成一个可治理、可复用的 skill 包。
|
||||
Hero 版可以压缩成一条主线：Skill OS 2.0 把零散输入变成一个可治理、可评测、可发布、可持续迭代的 skill 包。
|
||||
|
||||
```mermaid
|
||||
flowchart LR
|
||||
A["输入<br/>workflow / prompt / transcript / docs / notes"] --> B["路由<br/>SKILL.md"]
|
||||
B --> C["设计<br/>方法 + 质量门"]
|
||||
C --> D["执行<br/>create / validate / eval / promote"]
|
||||
D --> E["产出<br/>skill 包 + 报告 + 适配层"]
|
||||
A["输入<br/>workflow / prompt / transcript / docs / notes"] --> B["意图建模<br/>任务 / 输出 / 排除项 / 标准"]
|
||||
B --> C["Skill IR<br/>触发 / 契约 / 资源 / 证据"]
|
||||
C --> D["Skill 包<br/>SKILL.md / references / scripts / reports"]
|
||||
C --> E["目标编译<br/>OpenAI / Claude / generic / Agent Skills / VS Code"]
|
||||
D --> F["评测实验<br/>触发 / 输出 / 基准 / 运行时"]
|
||||
E --> F
|
||||
F --> G["Review Studio<br/>门禁 / 警告 / 动作 / 豁免"]
|
||||
G --> H["发布边界<br/>包体验证 / 安装模拟 / 宣传守卫"]
|
||||
H --> I["SkillOps 闭环<br/>反馈 / 采用漂移 / 下一轮迭代"]
|
||||
I --> B
|
||||
```
|
||||
|
||||
10 秒理解这张图：
|
||||
|
||||
- **输入**：从零散的 workflow、prompt、文档和笔记出发。
|
||||
- **路由**：先用精简的 `SKILL.md` 定义边界和触发。
|
||||
- **设计**：选择合适的 archetype、gates 和资源拆分方式。
|
||||
- **执行**：通过统一 CLI 完成创建、校验、优化和晋升。
|
||||
- **产出**：最终得到 skill 包，以及评测、治理和 portability 证据。
|
||||
- **输入**：从零散 workflow、prompt、文档和笔记出发，不要求一开始就有完整规格。
|
||||
- **意图建模**：先把任务、输出物、排除项、约束和质量标准说清楚，再生成文件。
|
||||
- **Skill IR**：把语义契约和具体平台格式拆开，避免被某一个客户端锁死。
|
||||
- **打包与编译**：从同一份源模型生成精简 skill 包和目标平台适配产物。
|
||||
- **评测与评审**：把触发行为、输出质量、运行时检查和信任信号变成可复查证据。
|
||||
- **发布与运营**：只在当前证据边界内发布，再把采用漂移和评审反馈带回下一轮迭代。
|
||||
|
||||
## 加权质量评测
|
||||
|
||||
下面是当前项目采用的工程质量评测模型。每个维度按 `0-10` 评分，再按权重折算到 `100` 分。GitHub stars 不计入总分，因为它反映生态热度，不直接代表元 skill 工程质量。
|
||||
|
||||
这个分数是本地工程证据，不等同于 world-class ready。公开宣称“已证明优于其他方案”仍要以 world-class ledger 中已接受的外部证据和人工证据为准。
|
||||
|
||||
加权总分公式：`sum(单项评分 / 10 * 权重)`。
|
||||
|
||||
| 元 Skill | 方法论深度 15 | 上下文纪律 10 | 工具链 15 | Eval/测试 20 | 治理 15 | 可移植 10 | 上手/评审 5 | 本地可靠性 10 | 加权总分 |
|
||||
@@ -60,7 +137,21 @@ flowchart LR
|
||||
| 2 | Anthropic Skill Creator | 67.5 | 方法论和迭代闭环强，但本地执行可靠性和治理覆盖较弱。 |
|
||||
| 3 | OpenAI Skill Creator | 50.5 | 更适合作为精简 skill 写作方法论教材，而不是完整工程系统。 |
|
||||
|
||||
## 适用场景
|
||||
## 人工盲测快照
|
||||
|
||||
2026-06-29，一位人工评审者在 5 个真实常见的 skill 创建场景里，对比了 `yao-meta-skill` 和内置的 OpenAI `skill-creator`。5 个场景分别是客服工单分诊、月度收入对账、Webinar 内容复用、故障复盘和 PR Review 跟进。评审者确认：所有选择都在揭晓来源前完成。
|
||||
|
||||
结果：`yao-meta-skill` 在 `5/5` 个案例中胜出。
|
||||
|
||||
证据：
|
||||
|
||||
- 盲测入口：[reports/blind-human-review-2026-06-29/index.html](../reports/blind-human-review-2026-06-29/index.html)
|
||||
- Adjudication 摘要：[reports/blind-human-review-2026-06-29/adjudication.md](../reports/blind-human-review-2026-06-29/adjudication.md)
|
||||
- 已记录判断：[reports/blind-human-review-2026-06-29/review-decisions.recorded.json](../reports/blind-human-review-2026-06-29/review-decisions.recorded.json)
|
||||
|
||||
边界：这是单人盲测偏好证据，不是 provider-backed 的独立模型执行证据；每个案例的逐项理由仍为空。
|
||||
|
||||
## 与其他元 Skill 的适用差异
|
||||
|
||||
- 如果你要的是**团队复用、显式边界、质量门、治理、可移植性和长期维护**，更适合 `Yao Meta Skill`。
|
||||
- 如果你要的是**对话优先的创作循环和人工引导式迭代**，更适合 `Anthropic Skill Creator`。
|
||||
@@ -69,34 +160,50 @@ flowchart LR
|
||||
|
||||
## 快速开始
|
||||
|
||||
如果你想直接在 Codex 里使用这个 skill，先安装到全局 skills：
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a codex -g -y
|
||||
```
|
||||
|
||||
如果要安装到全部支持的 agent，把 `-a codex` 换成 `-a '*'`：
|
||||
|
||||
```bash
|
||||
npx -y skills add yaojingang/yao-meta-skill -a '*' -g -y
|
||||
```
|
||||
|
||||
安装完成后重启客户端，再用“创建 skill”“改进已有 skill”“评估 skill”“给 skill 增加 eval”这类任务触发 `yao-meta-skill`。
|
||||
|
||||
1. 先描述你想沉淀成 skill 的 workflow、prompt 集合或重复任务。
|
||||
2. 先做一轮简短但更有人味的意图对话，把真实任务、输出物、边界、约束和你在意的质量标准说清楚。
|
||||
3. 先让 `quickstart` 澄清意图，再静默跑 benchmark scan 和 reference synthesis；只有当意图还不清楚，或者设计路线真的冲突时，才会显式继续追问或让你拍板。
|
||||
4. 使用 archetype-aware 的 `quickstart` 或完整作者流，在 scaffold、production、library 或 governed 模式下生成或改进 skill 包。
|
||||
5. 新建 skill 后，会默认附带 `reports/intent-dialogue.md`、`reports/intent-confidence.md`、`reports/reference-synthesis.md`、`reports/artifact-design-profile.md`、`reports/prompt-quality-profile.md`、`reports/skill-overview.html`、`reports/review-viewer.html` 和 `reports/iteration-directions.md`；后续还可以通过 feedback log 和 baseline compare 快速收集意见、查看增量收益，而不必每次都走完整 promotion 流程。
|
||||
5. 新建 skill 后，先看 `reports/skill-interpretation.html` 理解双语解释报告，再打开 `reports/skill-overview.html` 查看概述、指标、原理、边界、质量、风险、资产和路线，最后用 `reports/review-studio.html` 检查发布阻塞、权限批准和证据路径。
|
||||
|
||||
## 当前结果
|
||||
|
||||
- 当前 `make test` 可通过
|
||||
- 当前 `make test` 和 GitHub Actions `test` 可通过
|
||||
- 当前回归集下 trigger eval 为 `0` 误触发、`0` 漏触发
|
||||
- train / dev / holdout 三层评测均通过
|
||||
- 中文真实表达已经纳入触发评测，覆盖“做一个 skill”“沉淀成可复用能力”“优化已有 skill”“补 trigger 评测”等常见说法
|
||||
- `openai`、`claude`、`generic` 三个目标的 packaging contract 校验通过
|
||||
- registry 记录的目标平台从 OpenAI、Claude、Generic 扩展到 Agent Skills 和 VS Code 相关适配
|
||||
- Review Studio 当前汇总 16 个门禁，包体验证、安装模拟、证据一致性和发布声明边界已经进入报告链路
|
||||
- 单人盲测快照中，评审者在揭晓来源前完成判断，并在 `5/5` 个真实 skill 创建场景中选择 `yao-meta-skill`；证据见 [reports/blind-human-review-2026-06-29/adjudication.md](../reports/blind-human-review-2026-06-29/adjudication.md)
|
||||
|
||||
## 当前优势
|
||||
|
||||
最新加权评测中，Yao 的总分是 `91.5/100`。最强的部分集中在团队级 skill 资产真正需要的能力上：
|
||||
最新加权评测中，Yao 的总分是 `91.5/100`。2.0 的强项集中在团队级 skill 资产真正需要的能力上：
|
||||
|
||||
- **方法论深度 `9.5`**：已经形成正式的 skill engineering doctrine，覆盖 archetype、gate selection、non-skill decision、governance 和 resource boundary。
|
||||
- **工具链完整度 `9.5`**：初始化、校验、benchmark scan、description optimization、报告、晋升检查、打包、CI 和 portability checks 已经串成一条完整工具链。
|
||||
- **Eval / 测试严谨度 `9.5`**：触发评测覆盖 train/dev/holdout、blind holdout、adversarial holdout、judge-backed blind eval、route confusion、drift history 和 promotion gate。
|
||||
- **治理 / 生命周期 `9.5`**：重要 skill 可以声明 owner、生命周期、review cadence、maturity score、trust boundary、promotion decision 和 regression history。
|
||||
- **工具链完整度 `9.5`**：初始化、校验、benchmark scan、description optimization、Skill IR、目标编译、报告、晋升检查、打包、CI 和 portability checks 已经串成一条完整工具链。
|
||||
- **Eval / 测试严谨度 `9.5`**：触发评测覆盖 train/dev/holdout、blind holdout、adversarial holdout、judge-backed blind eval、route confusion、drift history、output eval 和 promotion gate。
|
||||
- **治理 / 生命周期 `9.5`**：重要 skill 可以声明 owner、生命周期、review cadence、maturity score、trust boundary、promotion decision、regression history、release lock 和 evidence ledger。
|
||||
- **本地可执行可靠性 `9.5`**：可以通过 `make test`、`make ci-test` 和统一 CLI 在本地复验。
|
||||
- **可移植 / 分发能力 `9.0`**：源码保持中性，adapter、degradation rule、packaging contract 和 portability score 负责保留跨环境可复用语义。
|
||||
- **上下文纪律 / 精简度 `8.0`**：入口仍保持在预算内，但因为系统承载了更多报告、案例、benchmark 和证据资产，这一项被持续作为约束跟踪。
|
||||
- **上手 / 评审体验 `6.5`**：quickstart、HTML overview、side-by-side review viewer 和 feedback log 已经改善首次体验，但仍是下一阶段最值得优化的 UX 维度。
|
||||
|
||||
整体方向很明确：入口尽量轻，评测尽量硬，治理显性化，同时继续降低首次创建和人工评审的摩擦。
|
||||
整体方向很明确：入口尽量轻，评测尽量硬，治理显性化；测试版可以开放试用，但公开宣传会继续受证据账本约束。
|
||||
|
||||
## 为什么是 Yao
|
||||
|
||||
@@ -107,7 +214,7 @@ flowchart LR
|
||||
|
||||
## 它能做什么
|
||||
|
||||
这个项目帮助你把 skill 从一次性 prompt，升级成可创建、可重构、可评估、可打包的长期能力包。
|
||||
这个项目帮助你把 skill 从一次性 prompt，升级成可创建、可重构、可评估、可打包、可审计、可发布、可持续迭代的长期能力包。
|
||||
|
||||
它的设计逻辑很简单：
|
||||
|
||||
|
||||
@@ -1 +1 @@
|
||||
Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse. Also trigger on common Chinese asks such as 做一个 skill, 把流程沉淀成可复用能力, 封装成团队可复用的 skill, 优化已有 skill, 补 trigger 评测, or 收紧触发边界.
|
||||
Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
|
||||
@@ -18,12 +18,19 @@
|
||||
"turn a repeated process into a reusable skill",
|
||||
"improve an existing skill",
|
||||
"add evals",
|
||||
"add tests",
|
||||
"package a skill for team reuse",
|
||||
"migrate an existing skill",
|
||||
"prepare packaging, installation, or release",
|
||||
"govern a reusable skill",
|
||||
"做一个 skill",
|
||||
"把流程沉淀成可复用 skill",
|
||||
"优化现有 skill",
|
||||
"补 trigger 评测",
|
||||
"封装成团队可复用 skill"
|
||||
"封装成团队可复用 skill",
|
||||
"迁移 skill",
|
||||
"发布 skill",
|
||||
"打包发布检查"
|
||||
],
|
||||
"exclusions": [
|
||||
"summary-only requests",
|
||||
@@ -75,16 +82,29 @@
|
||||
"formalize this process into a reusable capability",
|
||||
"turn this playbook into an agent capability package",
|
||||
"convert this into a maintained skill",
|
||||
"agent capability",
|
||||
"reusable agent capability",
|
||||
"skill library entry",
|
||||
"skill authoring",
|
||||
"做一个 skill",
|
||||
"创建一个 skill",
|
||||
"新建一个 skill",
|
||||
"帮我做个 skill",
|
||||
"改一个 skill",
|
||||
"重构一个 skill",
|
||||
"迁移一个 skill",
|
||||
"发布一个 skill",
|
||||
"这个 skill",
|
||||
"已有 skill",
|
||||
"现有 skill",
|
||||
"做成一个 skill",
|
||||
"封装成一个 skill",
|
||||
"沉淀成一个 skill",
|
||||
"整理成一个 skill",
|
||||
"抽成一个 skill",
|
||||
"可复用 skill",
|
||||
"可执行 skill",
|
||||
"团队 skill",
|
||||
"agent 能力包",
|
||||
"能力包",
|
||||
"skill 包"
|
||||
@@ -103,19 +123,27 @@
|
||||
"existing skill draft",
|
||||
"rough notes",
|
||||
"standard operating procedure",
|
||||
"operating procedure",
|
||||
"sop",
|
||||
"playbook",
|
||||
"transcript",
|
||||
"chat transcript",
|
||||
"meeting notes",
|
||||
"workflow fragments",
|
||||
"release notes",
|
||||
"onboarding flow",
|
||||
"support escalation routine",
|
||||
"quarterly release routine",
|
||||
"scripts",
|
||||
"repeated team practice",
|
||||
"流程",
|
||||
"工作流",
|
||||
"操作流程",
|
||||
"做事流程",
|
||||
"作业流程",
|
||||
"方法",
|
||||
"经验",
|
||||
"复盘",
|
||||
"sop 文档",
|
||||
"会议纪要",
|
||||
"对话记录",
|
||||
@@ -142,14 +170,32 @@
|
||||
"ops library",
|
||||
"maintained",
|
||||
"operationalize",
|
||||
"release-ready",
|
||||
"publish",
|
||||
"release",
|
||||
"installation",
|
||||
"installable",
|
||||
"portability",
|
||||
"registry",
|
||||
"governance",
|
||||
"review gate",
|
||||
"可复用",
|
||||
"复用",
|
||||
"封装",
|
||||
"打包",
|
||||
"沉淀",
|
||||
"标准化",
|
||||
"标准化下来",
|
||||
"团队复用",
|
||||
"给团队用",
|
||||
"团队可用",
|
||||
"安装复用",
|
||||
"可安装",
|
||||
"发布",
|
||||
"上架",
|
||||
"交付",
|
||||
"治理",
|
||||
"注册表",
|
||||
"方法包",
|
||||
"团队能力包",
|
||||
"沉淀下来",
|
||||
@@ -171,16 +217,32 @@
|
||||
"false negatives",
|
||||
"stress test",
|
||||
"route boundary",
|
||||
"routing",
|
||||
"route evals",
|
||||
"trigger routing",
|
||||
"activation",
|
||||
"description optimization",
|
||||
"tests",
|
||||
"install checks",
|
||||
"release checks",
|
||||
"hardening",
|
||||
"评测",
|
||||
"补评测",
|
||||
"补 eval",
|
||||
"补测试",
|
||||
"触发测试",
|
||||
"触发词",
|
||||
"触发范围",
|
||||
"召回",
|
||||
"收紧触发边界",
|
||||
"路由边界",
|
||||
"路由评测",
|
||||
"激活",
|
||||
"误触发",
|
||||
"漏触发",
|
||||
"质量门",
|
||||
"安装验证",
|
||||
"发布检查",
|
||||
"打包检查",
|
||||
"边界测试"
|
||||
]
|
||||
@@ -198,11 +260,32 @@
|
||||
"before sharing it with the team",
|
||||
"tighten the boundary",
|
||||
"revise this skill",
|
||||
"refactor this skill",
|
||||
"migrate this skill",
|
||||
"port this skill",
|
||||
"convert this skill",
|
||||
"release this skill",
|
||||
"publish this skill",
|
||||
"make this skill release-ready",
|
||||
"codex-ready package",
|
||||
"claude skill",
|
||||
"codex format",
|
||||
"interface metadata",
|
||||
"manifest",
|
||||
"install checks",
|
||||
"draft skill",
|
||||
"harden this skill for library reuse",
|
||||
"优化这个 skill",
|
||||
"改进这个 skill",
|
||||
"重构这个 skill",
|
||||
"扩大这个 skill",
|
||||
"调整这个 skill",
|
||||
"优化触发范围",
|
||||
"扩大触发范围",
|
||||
"迁移这个 skill",
|
||||
"发布这个 skill",
|
||||
"把这个 skill 迁移",
|
||||
"让这个 skill 可发布",
|
||||
"补一下评测",
|
||||
"补 trigger 测试",
|
||||
"加强路由判断",
|
||||
@@ -351,12 +434,16 @@
|
||||
"do not convert it into a reusable capability",
|
||||
"keep it as documentation only",
|
||||
"discussion only",
|
||||
"no agent execution",
|
||||
"先不要做成 skill",
|
||||
"先不做 skill",
|
||||
"不要做成 skill",
|
||||
"不用封装",
|
||||
"不要打包",
|
||||
"不要沉淀成能力",
|
||||
"先别做成可复用能力",
|
||||
"不需要 agent 执行",
|
||||
"不做 agent 能力",
|
||||
"只做文档",
|
||||
"只做说明"
|
||||
]
|
||||
|
||||
@@ -54,6 +54,18 @@
|
||||
"text": "Add trigger evals to this skill before sharing it with the team.",
|
||||
"family": "iterate_existing_skill"
|
||||
},
|
||||
{
|
||||
"text": "Migrate this Claude skill into a Codex-ready package with interface metadata and install checks.",
|
||||
"family": "migrate_existing_skill"
|
||||
},
|
||||
{
|
||||
"text": "Make this existing skill release-ready: add manifest/interface metadata, packaging checks, and trigger evals.",
|
||||
"family": "release_packaging"
|
||||
},
|
||||
{
|
||||
"text": "Optimize the activation wording for this skill so broader skill-authoring requests are routed correctly.",
|
||||
"family": "trigger_expansion"
|
||||
},
|
||||
{
|
||||
"text": "We have a messy release runbook, export process, and a prompt history; turn all of that into one reusable skill package with evals and packaging checks.",
|
||||
"family": "complex_multi_asset"
|
||||
@@ -133,6 +145,18 @@
|
||||
{
|
||||
"text": "把这个客服升级流程标准化成一个可执行的 skill，并加上边界测试。",
|
||||
"family": "cn_eval_and_package"
|
||||
},
|
||||
{
|
||||
"text": "把这个 Claude skill 迁移成 Codex 可用的 skill 包，补 interface、manifest 和安装验证。",
|
||||
"family": "cn_migrate_existing_skill"
|
||||
},
|
||||
{
|
||||
"text": "把这套提示词和脚本整理成团队能安装复用的 skill，并做打包发布检查。",
|
||||
"family": "cn_release_packaging"
|
||||
},
|
||||
{
|
||||
"text": "扩大这个 skill 的触发范围，同时补路由评测，避免漏触发。",
|
||||
"family": "cn_trigger_expansion"
|
||||
}
|
||||
],
|
||||
"should_not_trigger": [
|
||||
@@ -239,6 +263,22 @@
|
||||
{
|
||||
"text": "先一起头脑风暴几个方向，不要封装成 skill。",
|
||||
"family": "cn_brainstorm_only"
|
||||
},
|
||||
{
|
||||
"text": "Polish this release note for publishing, but do not do any skill work.",
|
||||
"family": "document_only"
|
||||
},
|
||||
{
|
||||
"text": "Migrate this wiki article into a new docs folder; do not create an agent skill.",
|
||||
"family": "document_only"
|
||||
},
|
||||
{
|
||||
"text": "把这篇 SOP 改成知识库文档，不需要 agent 执行。",
|
||||
"family": "cn_document_only"
|
||||
},
|
||||
{
|
||||
"text": "检查安装步骤是否清楚，只做 README，不做 skill 包。",
|
||||
"family": "cn_document_only"
|
||||
}
|
||||
],
|
||||
"near_neighbor": [
|
||||
@@ -333,6 +373,18 @@
|
||||
{
|
||||
"text": "这次只给我一个一次性 prompt，不用复用成 skill。",
|
||||
"family": "cn_one_off_vs_reusable"
|
||||
},
|
||||
{
|
||||
"text": "Create a reusable onboarding template for humans, not an agent skill.",
|
||||
"family": "document_export_vs_agent_skill"
|
||||
},
|
||||
{
|
||||
"text": "Draft a release checklist for a future skill, but do not package or evaluate the skill yet.",
|
||||
"family": "future_outline_vs_build"
|
||||
},
|
||||
{
|
||||
"text": "整理成团队发布流程文档即可，不要做成 skill，也不要做触发评测。",
|
||||
"family": "cn_document_export_vs_agent_skill"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
+1
-1
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "2.0",
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.1.0",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"targets": [
|
||||
"openai",
|
||||
"claude",
|
||||
@@ -16,8 +16,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -48,7 +48,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17T08:58:54Z",
|
||||
"generated_at": "2026-07-02T06:33:07Z",
|
||||
"skill_dir": ".",
|
||||
"source_patterns": "reports/user_patterns.json",
|
||||
"pattern_count": 5,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Adaptation Proposals
|
||||
|
||||
- Generated at: `2026-06-17T08:58:54Z`
|
||||
- Generated at: `2026-07-02T06:33:07Z`
|
||||
- Pattern report: `reports/user_patterns.json`
|
||||
- Proposal only: `true`
|
||||
- Writes repository files: `false`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-17T08:58:53Z",
|
||||
"generated_at": "2026-07-02T06:33:44Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
@@ -25,14 +25,14 @@
|
||||
},
|
||||
"summary": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"edited_count": 0,
|
||||
"rejected_count": 0,
|
||||
"missed_count": 0,
|
||||
"failed_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_rate": 100.0,
|
||||
"missed_trigger_count": 0,
|
||||
"wrong_trigger_count": 0,
|
||||
"bad_output_count": 0,
|
||||
@@ -41,7 +41,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -53,31 +53,31 @@
|
||||
{
|
||||
"skill": "yao-meta-skill",
|
||||
"events": 1,
|
||||
"adoption_events": 0,
|
||||
"accepted": 0,
|
||||
"adoption_events": 1,
|
||||
"accepted": 1,
|
||||
"edited": 0,
|
||||
"rejected": 0,
|
||||
"missed": 0,
|
||||
"adoption_rate": 0
|
||||
"adoption_rate": 100.0
|
||||
}
|
||||
],
|
||||
"next_iteration_candidates": [],
|
||||
"recent_events": [
|
||||
{
|
||||
"command": "unknown",
|
||||
"event": "review_event",
|
||||
"event": "skill_activation",
|
||||
"skill": "yao-meta-skill",
|
||||
"source": "manual",
|
||||
"version": "1.1.0",
|
||||
"activation_type": "manual",
|
||||
"outcome": "reviewed",
|
||||
"activation_type": "explicit",
|
||||
"outcome": "accepted",
|
||||
"failure_type": "none",
|
||||
"timestamp": "2026-06-13T12:00:00Z"
|
||||
"timestamp": "2026-06-13T10:00:00Z"
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"artifacts": {
|
||||
"events_jsonl": "reports/telemetry_events.jsonl",
|
||||
"events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
|
||||
"json": "reports/adoption_drift_report.json",
|
||||
"markdown": "reports/adoption_drift_report.md"
|
||||
}
|
||||
|
||||
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
## Summary
|
||||
|
||||
- Events: `1`
|
||||
- Adoption samples: `0`
|
||||
- Activation events: `0`
|
||||
- Adoption rate: `0`
|
||||
- Adoption samples: `1`
|
||||
- Activation events: `1`
|
||||
- Adoption rate: `100.0`
|
||||
- Missed trigger signals: `0`
|
||||
- Bad output signals: `0`
|
||||
- Script error signals: `0`
|
||||
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
|
||||
| Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
||||
| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
|
||||
| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
|
||||
|
||||
## Next Iteration Candidates
|
||||
|
||||
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
|
||||
## Recent Metadata Events
|
||||
|
||||
- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
|
||||
- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
|
||||
|
||||
@@ -1,17 +1,17 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"python_file_count": 229,
|
||||
"script_file_count": 153,
|
||||
"test_file_count": 76,
|
||||
"internal_module_count": 69,
|
||||
"python_file_count": 232,
|
||||
"script_file_count": 155,
|
||||
"test_file_count": 77,
|
||||
"internal_module_count": 71,
|
||||
"cli_script_count": 86,
|
||||
"command_handler_count": 68,
|
||||
"command_handler_count": 71,
|
||||
"entrypoint_command_handler_count": 18,
|
||||
"command_module_count": 6,
|
||||
"command_module_count": 7,
|
||||
"warn_line_threshold": 900,
|
||||
"watch_line_threshold": 720,
|
||||
"early_watch_line_threshold": 600,
|
||||
|
||||
@@ -1,18 +1,18 @@
|
||||
# Architecture Maintainability
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `pass`
|
||||
- python files: `229`
|
||||
- scripts: `153`
|
||||
- tests: `76`
|
||||
- internal modules: `69`
|
||||
- python files: `232`
|
||||
- scripts: `155`
|
||||
- tests: `77`
|
||||
- internal modules: `71`
|
||||
- CLI scripts: `86`
|
||||
- Yao CLI command handlers: `68`
|
||||
- Yao CLI command handlers: `71`
|
||||
- entrypoint command handlers: `18`
|
||||
- command modules: `6`
|
||||
- command modules: `7`
|
||||
- largest file lines: `719`
|
||||
- early watch threshold lines: `600`
|
||||
- early watchlist: `6`
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"skill_name": "yao-meta-skill",
|
||||
"skill_name": "yao-meta-skill-trigger-coverage-merge",
|
||||
"design_system": "metric editorial",
|
||||
"primary_artifact": {
|
||||
"key": "dashboard",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Artifact Design Profile
|
||||
|
||||
Skill: `yao-meta-skill`
|
||||
Skill: `yao-meta-skill-trigger-coverage-merge`
|
||||
Design system: `metric editorial`
|
||||
|
||||
## Primary Artifact Direction
|
||||
|
||||
@@ -20,7 +20,7 @@
|
||||
"adversarial_errors": 0
|
||||
},
|
||||
"current": {
|
||||
"tokens": 53,
|
||||
"tokens": 54,
|
||||
"dev_errors": 0,
|
||||
"holdout_errors": 0,
|
||||
"blind_errors": 0,
|
||||
@@ -28,7 +28,7 @@
|
||||
"adversarial_errors": 0
|
||||
},
|
||||
"winner": {
|
||||
"tokens": 53,
|
||||
"tokens": 54,
|
||||
"dev_errors": 0,
|
||||
"holdout_errors": 0,
|
||||
"blind_errors": 0,
|
||||
|
||||
@@ -1,45 +1,47 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-07-02",
|
||||
"skill_dir": ".",
|
||||
"commit": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": true,
|
||||
"changed_file_count": 29,
|
||||
"changed_file_count": 37,
|
||||
"generated_dirty": true,
|
||||
"generated_changed_file_count": 29,
|
||||
"source_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 36,
|
||||
"source_dirty": true,
|
||||
"source_changed_file_count": 1,
|
||||
"sample": [
|
||||
" M SKILL.md",
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/compiled_targets.json",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
],
|
||||
"source_sample": [],
|
||||
"source_sample": [
|
||||
" M SKILL.md"
|
||||
],
|
||||
"generated_sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adaptation_proposals.json",
|
||||
" M reports/adaptation_proposals.md",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/compiled_targets.json",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json"
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/evidence_consistency.json"
|
||||
],
|
||||
"generated_dirty_prefixes": [
|
||||
"dist/",
|
||||
@@ -53,13 +55,13 @@
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0",
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158",
|
||||
"source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -74,24 +76,26 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 29,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 37,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 1,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 29
|
||||
"generated_changed_file_count": 36
|
||||
},
|
||||
"beta_test_release": {
|
||||
"ready": true,
|
||||
"ready": false,
|
||||
"scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
|
||||
"blockers": [],
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable"
|
||||
],
|
||||
"allowed_deferred_evidence": [
|
||||
{
|
||||
"key": "provider-holdout",
|
||||
@@ -121,19 +125,20 @@
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (3 open gaps, 4 ledger pending)",
|
||||
"world-class source checks are not all accepted (11/19 pass, 8 blocked)"
|
||||
"world-class source checks are not all accepted (12/19 pass, 7 blocked)"
|
||||
],
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"ready": false,
|
||||
"commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"source_changed_file_count": 0,
|
||||
"generated_changed_file_count": 29,
|
||||
"reason": "only generated evidence artifacts were dirty at generation time"
|
||||
"source_changed_file_count": 1,
|
||||
"generated_changed_file_count": 36,
|
||||
"reason": "source files were dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -141,7 +146,7 @@
|
||||
"existing_count": 25,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0"
|
||||
"sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -235,8 +240,8 @@
|
||||
"label": "trigger_scorecard",
|
||||
"path": "reports/route_scorecard.json",
|
||||
"exists": true,
|
||||
"bytes": 16950,
|
||||
"sha256": "a649547a7d3d5fe02262ca1b188ed4022d8f557770be425f7b7cf762aa76533a"
|
||||
"bytes": 17042,
|
||||
"sha256": "53fc22d220dc11453c1e66a17ec2d935e069f9bc936952fe4a53afdb4c71b2cc"
|
||||
},
|
||||
{
|
||||
"label": "runtime_conformance",
|
||||
@@ -249,106 +254,106 @@
|
||||
"label": "trust_report",
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 137787,
|
||||
"sha256": "bbff1f1bee0ce6f7014efcd4622ba11c70aacfc81f2e69e225411df7004dd616"
|
||||
"bytes": 139090,
|
||||
"sha256": "108aee597a1f245f73d9b69454b6fa8a144545f905231a7c314364c7066541c6"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
"path": "reports/python_compatibility.json",
|
||||
"exists": true,
|
||||
"bytes": 30127,
|
||||
"sha256": "d31dc03c74f17242f4163b8cb3f23120fe3d0712edd08fa183cb94f8120d491c"
|
||||
"bytes": 30497,
|
||||
"sha256": "4d82942052a2ca87db7acea451096332d4b8bf6420a29fa9f5596e83464d21ea"
|
||||
},
|
||||
{
|
||||
"label": "registry_audit",
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3137,
|
||||
"sha256": "1feb80c7cdc833a655cc0e44150f39f9f6d0633465abaa1ae29ebe7cb0649065"
|
||||
"bytes": 3155,
|
||||
"sha256": "d307675d5c6c3cd2f104ce7d963b37d36113f35334e4c6895b55fbb8b255e915"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
"path": "reports/package_verification.json",
|
||||
"exists": true,
|
||||
"bytes": 19338,
|
||||
"sha256": "7aa6c25e8154d246ace49f7ab9159fa85f96d1d4ebb7e2bb03c7b223260a908b"
|
||||
"bytes": 19525,
|
||||
"sha256": "e2ad726ce0486be0f57d88e518ef4d265479a04756419c6f8df50cf7d05b1f14"
|
||||
},
|
||||
{
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8758,
|
||||
"sha256": "c1f1122264b868c4998482c580ef94333575c6ff7c5c9c297188b225f69a131d"
|
||||
"bytes": 8947,
|
||||
"sha256": "65adf51d8c4b1d5ea49edde09004f7e4bfc06127e640baf2de23af695fbe0728"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
"path": "reports/skill_os2_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 13824,
|
||||
"sha256": "6362e79a8cfd3ff54b1a7ca32f37de8ed1cda500b953fdf1074928c6d2d62379"
|
||||
"sha256": "150c0027deaa3c2dd44db5380e9a9b16f123e8a8e3ff6142c711b2b0c432f81c"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_plan",
|
||||
"path": "reports/world_class_evidence_plan.json",
|
||||
"exists": true,
|
||||
"bytes": 23314,
|
||||
"sha256": "8eb5e1fbaa7580f107fd9920d13a13b239edb72d50b6959fc8f6dd43150f07d7"
|
||||
"sha256": "483ed2b3bd020fa2c5a888300c0d0c1a265eebaf648076581f082f2d527d3669"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_ledger",
|
||||
"path": "reports/world_class_evidence_ledger.json",
|
||||
"exists": true,
|
||||
"bytes": 26277,
|
||||
"sha256": "6038b6cd6e0667f25cfd69a5e40afa314d9efc3a93753a2a3a0509ae9b516a15"
|
||||
"bytes": 26274,
|
||||
"sha256": "b19e7113ec463dbb1cfb87c45d3c51624151aeea1747c8d9c286b6967a385c6a"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_intake",
|
||||
"path": "reports/world_class_evidence_intake.json",
|
||||
"exists": true,
|
||||
"bytes": 20922,
|
||||
"sha256": "aa262da0ecee7232974ce061a51c8966c310de0b0be9f91eb82bb28bf1c7c0a8"
|
||||
"sha256": "885bff9c1c8546c606f583a982a2283229438dbdcd44f3c7e55aff71f858f8f4"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_preflight",
|
||||
"path": "reports/world_class_evidence_preflight.json",
|
||||
"exists": true,
|
||||
"bytes": 94341,
|
||||
"sha256": "95cb56581224aab06be84d0b338d6ba9aa4aef0b1ebd480801f1e2226b873b0d"
|
||||
"bytes": 90854,
|
||||
"sha256": "06e93b1c0c99107002466d9418a4910c82397bce26c3bbdd5b5cc9875eeb65b2"
|
||||
},
|
||||
{
|
||||
"label": "world_class_submission_review",
|
||||
"path": "reports/world_class_submission_review.json",
|
||||
"exists": true,
|
||||
"bytes": 17295,
|
||||
"sha256": "12fbb84926294c4bd05af526fcbe0983db26e449d2c305006094baf27332a0ba"
|
||||
"bytes": 17292,
|
||||
"sha256": "e8df5c72ade7ad0704b6ee5dd6aedefea98f79a9a370cd4d80655401862e87f4"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook",
|
||||
"path": "reports/world_class_operator_runbook.json",
|
||||
"exists": true,
|
||||
"bytes": 87257,
|
||||
"sha256": "f321dc118ee931a1e1510559e5e64774168a58b0446ae62d232009eb42e3b384"
|
||||
"bytes": 83712,
|
||||
"sha256": "bb67813244d64f8e5e416620bb9d7856d95d85a1ec7f9581b2a97b9fed47e02e"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_markdown",
|
||||
"path": "reports/world_class_operator_runbook.md",
|
||||
"exists": true,
|
||||
"bytes": 25549,
|
||||
"sha256": "858ee11bbacb143f648e9c00735bc248a0b9f3c9303dc9e0ad5c0a65d9d6e07f"
|
||||
"bytes": 25504,
|
||||
"sha256": "e8d4dee7541323f0e6fa6be4903e7c482b1d00ef1db5594f0c44212088b53d85"
|
||||
},
|
||||
{
|
||||
"label": "world_class_operator_runbook_html",
|
||||
"path": "reports/world_class_operator_runbook.html",
|
||||
"exists": true,
|
||||
"bytes": 34702,
|
||||
"sha256": "31b24658c59ee1dee25aec378e72033b042af88dfdf40c325d361d0c9bec2ca7"
|
||||
"bytes": 34651,
|
||||
"sha256": "022594013b2469a0e5776e3f5f6a99fa069917c5ba5cb90256b7841b1f5fd1e3"
|
||||
},
|
||||
{
|
||||
"label": "world_class_claim_guard",
|
||||
"path": "reports/world_class_claim_guard.json",
|
||||
"exists": true,
|
||||
"bytes": 18596,
|
||||
"sha256": "abe7f7d60c0025e140373fadaefbed4063f285c140c74b9c7cfb464e354bb526"
|
||||
"bytes": 20713,
|
||||
"sha256": "911ba833055ab857250f88d88ccdd0bb652076a81214f725c49d763352035572"
|
||||
}
|
||||
],
|
||||
"missing_artifacts": [],
|
||||
|
||||
@@ -1,49 +1,49 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Commit: `e79050ed12d057811d7d13ab7d8bcc5a06af76d4`
|
||||
Generated at: `2026-07-02`
|
||||
Commit: `24bea607a2b16e766bc8f2bc8483f22fae1edc61`
|
||||
Working tree dirty at generation: `true`
|
||||
Source tree dirty at generation: `false`
|
||||
Source tree dirty at generation: `true`
|
||||
Generated evidence dirty at generation: `true`
|
||||
Evidence bundle SHA256: `55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0`
|
||||
Evidence bundle SHA256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `25`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `5a99ef3133b0`
|
||||
- archive sha256: `7db44f059844`
|
||||
- source contract sha256: `db71157184dc`
|
||||
- archive sha256: `c56a8519244c`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
- reproduction commands: `23`
|
||||
- provider evidence complete: `true`
|
||||
- human review complete: `false`
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `11` pass / `19` total; `8` blocked
|
||||
- beta test ready: `true`
|
||||
- beta test blockers: `0`
|
||||
- world-class source checks: `12` pass / `19` total; `7` blocked
|
||||
- beta test ready: `false`
|
||||
- beta test blockers: `1`
|
||||
- beta deferred evidence: `4`
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `3`
|
||||
- changed files at generation: `29`
|
||||
- source changed files at generation: `0`
|
||||
- generated changed files at generation: `29`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `37`
|
||||
- source changed files at generation: `1`
|
||||
- generated changed files at generation: `36`
|
||||
|
||||
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
## Beta Test Boundary
|
||||
|
||||
- ready: `true`
|
||||
- ready: `false`
|
||||
- scope: beta/public test release without superiority, fully-reviewed, or world-class claims
|
||||
- policy: Human blind-review, native permission enforcement, real client telemetry, and ledger acceptance may be deferred for beta/public testing, but public claims must remain blocked until those evidence entries are accepted.
|
||||
- required wording: Use beta, public test, or technical preview wording; do not claim world-class readiness, fully reviewed quality, or proven superiority over baseline.
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| none |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
|
||||
| Deferred evidence | Reason |
|
||||
| --- | --- |
|
||||
@@ -60,21 +60,22 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (3 open gaps, 4 ledger pending) |
|
||||
| world-class source checks are not all accepted (11/19 pass, 8 blocked) |
|
||||
| world-class source checks are not all accepted (12/19 pass, 7 blocked) |
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: only generated evidence artifacts were dirty at generation time
|
||||
- ready: `false`
|
||||
- reason: source files were dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `25` / `25`
|
||||
- sha256: `55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0`
|
||||
- sha256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -99,23 +100,23 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `4df66b63d2e7` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `a649547a7d3d` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `53fc22d220dc` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `bbff1f1bee0c` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `d31dc03c74f1` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `1feb80c7cdc8` |
|
||||
| package_verification | `reports/package_verification.json` | present | `7aa6c25e8154` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `c1f1122264b8` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6362e79a8cfd` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `8eb5e1fbaa75` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `6038b6cd6e06` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `aa262da0ecee` |
|
||||
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `95cb56581224` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `12fbb8492629` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f321dc118ee9` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `858ee11bbacb` |
|
||||
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `31b24658c59e` |
|
||||
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `abe7f7d60c00` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `108aee597a1f` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `4d82942052a2` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `d307675d5c6c` |
|
||||
| package_verification | `reports/package_verification.json` | present | `e2ad726ce048` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `65adf51d8c4b` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `150c0027deaa` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `483ed2b3bd02` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `b19e7113ec46` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `885bff9c1c85` |
|
||||
| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `06e93b1c0c99` |
|
||||
| world_class_submission_review | `reports/world_class_submission_review.json` | present | `e8df5c72ade7` |
|
||||
| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `bb67813244d6` |
|
||||
| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `e8d4dee75413` |
|
||||
| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `022594013b24` |
|
||||
| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `911ba833055a` |
|
||||
|
||||
## Reproduction Commands
|
||||
|
||||
|
||||
@@ -0,0 +1,149 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>答案钥匙 - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
table { width:100%; border-collapse: collapse; } td, th { border:1px solid var(--line); padding:8px; text-align:left; }</style>
|
||||
</head>
|
||||
<body>
|
||||
<header>
|
||||
<a class="button" href="index.html">返回入口</a>
|
||||
<h1>答案钥匙</h1>
|
||||
<p class="warn">请只在所有评审判断都记录完成后再打开。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<table>
|
||||
<thead><tr><th>案例</th><th>方案 A 来源</th><th>方案 B 来源</th></tr></thead>
|
||||
<tbody><tr><td>case-01-support-triage</td><td>官方 skill-creator</td><td>yao-meta-skill</td></tr><tr><td>case-02-monthly-revenue-reconciliation</td><td>yao-meta-skill</td><td>官方 skill-creator</td></tr><tr><td>case-03-webinar-repurposing</td><td>官方 skill-creator</td><td>yao-meta-skill</td></tr><tr><td>case-04-incident-postmortem</td><td>yao-meta-skill</td><td>官方 skill-creator</td></tr><tr><td>case-05-pr-review-followup</td><td>官方 skill-creator</td><td>yao-meta-skill</td></tr></tbody>
|
||||
</table>
|
||||
<p class="note" style="margin-top:12px">来源路径：yao-meta-skill = /Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md；官方 skill-creator = /Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md。</p>
|
||||
</section>
|
||||
</main>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"seed": "blind-human-review-2026-06-29-v1",
|
||||
"answer_key_warning": "请只在记录完所有判断后再打开。",
|
||||
"answers": [
|
||||
{
|
||||
"case_id": "case-01-support-triage",
|
||||
"variant_a_source": "official",
|
||||
"variant_b_source": "yao",
|
||||
"variant_a_source_label": "官方 skill-creator",
|
||||
"variant_b_source_label": "yao-meta-skill",
|
||||
"source_paths": {
|
||||
"yao": "/Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md",
|
||||
"official": "/Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md"
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "case-02-monthly-revenue-reconciliation",
|
||||
"variant_a_source": "yao",
|
||||
"variant_b_source": "official",
|
||||
"variant_a_source_label": "yao-meta-skill",
|
||||
"variant_b_source_label": "官方 skill-creator",
|
||||
"source_paths": {
|
||||
"yao": "/Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md",
|
||||
"official": "/Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md"
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "case-03-webinar-repurposing",
|
||||
"variant_a_source": "official",
|
||||
"variant_b_source": "yao",
|
||||
"variant_a_source_label": "官方 skill-creator",
|
||||
"variant_b_source_label": "yao-meta-skill",
|
||||
"source_paths": {
|
||||
"yao": "/Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md",
|
||||
"official": "/Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md"
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "case-04-incident-postmortem",
|
||||
"variant_a_source": "yao",
|
||||
"variant_b_source": "official",
|
||||
"variant_a_source_label": "yao-meta-skill",
|
||||
"variant_b_source_label": "官方 skill-creator",
|
||||
"source_paths": {
|
||||
"yao": "/Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md",
|
||||
"official": "/Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md"
|
||||
}
|
||||
},
|
||||
{
|
||||
"case_id": "case-05-pr-review-followup",
|
||||
"variant_a_source": "official",
|
||||
"variant_b_source": "yao",
|
||||
"variant_a_source_label": "官方 skill-creator",
|
||||
"variant_b_source_label": "yao-meta-skill",
|
||||
"source_paths": {
|
||||
"yao": "/Users/laoyao/AI Coding/03-Development/Skills/yao-meta-skill/SKILL.md",
|
||||
"official": "/Users/laoyao/.codex/skills/.system/skill-creator/SKILL.md"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
# 人工盲测结果
|
||||
|
||||
这组材料记录了 2026-06-29 的单人 A/B 盲测。评审者在揭晓来源前完成了 5 个判断，结果为 `yao-meta-skill` 5 胜，官方 `skill-creator` 0 胜。
|
||||
|
||||
## 文件
|
||||
|
||||
- [index.html](index.html)：盲测入口。
|
||||
- [adjudication.md](adjudication.md)：揭晓后的统计摘要。
|
||||
- [review-decisions.recorded.json](review-decisions.recorded.json)：评审者选择、确认和证据边界。
|
||||
- [blind-pack.json](blind-pack.json)：不含答案钥匙的盲测包。
|
||||
- [DO_NOT_OPEN_answer_key.json](DO_NOT_OPEN_answer_key.json)：答案钥匙，只应在评审完成后打开。
|
||||
|
||||
## 证据边界
|
||||
|
||||
这可以作为单人盲测偏好证据。它不等同于 provider-backed 的独立模型执行证据，也不等同于 world-class readiness。当前缺口是逐案理由为空、评审人数为 1，尚未形成多评审者一致性证据。
|
||||
@@ -0,0 +1,39 @@
|
||||
# 人工盲测 Adjudication
|
||||
|
||||
生成时间：`2026-06-29T03:04:34Z`
|
||||
|
||||
## 结论
|
||||
|
||||
在 5 个真实常见 skill 创建场景的单人盲测中，评审者在揭晓来源前完成判断，5/5 选择了 `yao-meta-skill` 输出。
|
||||
|
||||
| 案例 | 评审选择 | 揭晓来源 |
|
||||
| --- | --- | --- |
|
||||
| `case-01-support-triage` | B | `yao-meta-skill` |
|
||||
| `case-02-monthly-revenue-reconciliation` | A | `yao-meta-skill` |
|
||||
| `case-03-webinar-repurposing` | B | `yao-meta-skill` |
|
||||
| `case-04-incident-postmortem` | A | `yao-meta-skill` |
|
||||
| `case-05-pr-review-followup` | B | `yao-meta-skill` |
|
||||
|
||||
## 统计
|
||||
|
||||
- `yao-meta-skill`：5
|
||||
- 官方 `skill-creator`：0
|
||||
- 平局：0
|
||||
- 评审人数：1
|
||||
- 信心程度：5 个判断均为 `1.0`
|
||||
|
||||
## 盲审确认
|
||||
|
||||
评审者确认：
|
||||
|
||||
> 确认：我是在完成五个判断之后才让你打开答案钥匙的，评审前没有看来源。以上 5 个判断都是揭晓来源前完成的。
|
||||
|
||||
## 证据边界
|
||||
|
||||
这可以作为单人独立盲测偏好证据。它不等同于 provider-backed 独立模型执行证据，因为两个输出是本地按两份 skill 说明生成的。
|
||||
|
||||
当前缺口：
|
||||
|
||||
- 每个案例的 `reason` 字段为空，缺少逐案 rationale。
|
||||
- 评审人数为 1，尚未形成多评审者一致性证据。
|
||||
- 尚未加入外部冻结 holdout 任务集。
|
||||
@@ -0,0 +1,98 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"seed": "blind-human-review-2026-06-29-v1",
|
||||
"generated_by": "Codex 在本地套用两份 skill 说明生成",
|
||||
"evidence_boundary": "人类盲测评审起始包；不是 provider-backed 的独立模型执行证据。",
|
||||
"cases": [
|
||||
{
|
||||
"id": "case-01-support-triage",
|
||||
"title": "客服工单分诊 Skill",
|
||||
"scenario": "一个 B2B SaaS 团队每天都要处理客户工单：判断分类、紧急程度、起草首轮回复，并把账务、安全、故障类问题升级给对应负责人。他们希望把这个重复流程做成一个给支持团队使用的 Codex skill。",
|
||||
"user_prompt": "请把我们反复使用的客服工单分诊流程做成一个团队可复用的 skill。输入包括原始工单文本、客户等级、产品模块和近期故障记录。输出需要包含问题分类、紧急程度、首轮回复草稿、升级负责人和判断依据。不要把 PII 泄露到报告里。",
|
||||
"rubric": [
|
||||
"是否有清楚的触发边界和近邻排除。",
|
||||
"是否是可复用的 skill 包结构，而不只是一个提示词。",
|
||||
"是否定义了分类、紧急程度、回复、升级和证据的输出契约。",
|
||||
"是否处理 PII 和客户内容的隐私风险。",
|
||||
"是否有能发现错误升级和泛泛回复的评测方案。"
|
||||
],
|
||||
"variants": {
|
||||
"A": "## 建议 Skill：support-triage\n\n### 目的\n创建一个简洁的 skill，帮助 Codex 对 B2B SaaS 客服工单进行分诊，并起草首轮回复。\n\n### 建议包结构\n```\nsupport-triage/\n SKILL.md\n agents/openai.yaml\n references/\n triage-taxonomy.md\n escalation-policy.md\n```\n\n### SKILL.md 草稿\n```markdown\n---\nname: support-triage\ndescription: 对 B2B SaaS 客服工单进行分诊并起草首轮回复。当用户提供原始工单文本、客户等级、产品模块、故障记录，或需要紧急程度、分类、升级建议时使用。\n---\n\n# 客服工单分诊\n\n使用这个 skill 对入站工单分类、起草合适的首轮回复，并识别是否需要升级。\n\n## 工作流\n1. 阅读工单文本、客户等级、产品模块和近期故障记录。\n2. 将工单归为一个主分类：账务、访问权限、缺陷、故障、功能请求、安全、数据/隐私、上手问题或其他。\n3. 标记紧急程度：低、普通、高、严重。\n4. 起草首轮回复：确认问题、只询问必要补充信息，并避免没有依据的承诺。\n5. 对安全、隐私、严重故障、数据丢失或企业客户影响问题进行升级。\n6. 汇报判断依据，但不要复制不必要的 PII。\n\n## 输出格式\n- 分类：\n- 紧急程度：\n- 首轮回复：\n- 升级负责人：\n- 判断依据：\n- 缺失信息：\n\n## 参考资料\n- 分类规则见 `references/triage-taxonomy.md`。\n- 升级标准见 `references/escalation-policy.md`。\n```\n\n### agents/openai.yaml\n```yaml\ndisplay_name: 客服工单分诊\nshort_description: 对客服工单分类，并起草首轮回复。\ndefault_prompt: 请分诊这个客服工单，并起草首轮回复。\n```\n\n### 资源\n- `references/triage-taxonomy.md`：分类定义、紧急程度提示和示例。\n- `references/escalation-policy.md`：升级负责人和升级标准。\n\n### 验证\n用账务、安全、故障和功能请求等代表性工单测试。确认输出会最小化 PII，并且严重问题会被升级。\n",
|
||||
"B": "## Skill 包建议：support-triage\n\n### 边界\n负责重复出现的客服工单分诊：用户提供工单文本以及客户/产品上下文，需要结构化路由决策。不要用于一次性文案润色、泛泛的客服同理心训练、CRM 配置，或超出升级范围的法律/安全事件处置。\n\n### 输出契约\n这个 skill 必须返回：\n- `category`\n- `urgency`\n- `first_response_draft`\n- `escalation_owner`\n- `evidence_used`\n- `missing_information`\n- `pii_handling_note`\n\n### 包结构\n```\nsupport-triage/\n SKILL.md\n agents/interface.yaml\n references/\n triage-taxonomy.md\n escalation-policy.md\n privacy-redaction.md\n evals/\n trigger_cases.json\n output/\n cases.jsonl\n fixtures/\n reports/\n output-risk-profile.md\n output_quality_scorecard.md\n```\n\n### SKILL.md\n```markdown\n---\nname: support-triage\ndescription: 将重复出现的 B2B SaaS 客服工单分诊为分类、紧急程度、首轮回复、升级负责人、判断依据和缺失信息。当输入包含原始工单、客户等级、产品模块、故障记录或支持队列上下文时使用。不要用于一次性文案润色、CRM 设置、法律建议或最终安全事件处置。\n---\n\n# 客服工单分诊\n\n## 工作流\n1. 确认这是重复的工单分诊任务，而不是一次性文案润色。\n2. 阅读工单文本、客户等级、产品模块和故障记录。\n3. 使用 `references/triage-taxonomy.md` 判断分类和紧急程度。\n4. 按 `references/escalation-policy.md` 检查升级标准。\n5. 起草首轮回复：确认问题、避免无依据承诺，只请求最少的缺失信息。\n6. 按 `references/privacy-redaction.md` 对 PII 做脱敏或摘要。\n7. 严格按输出契约返回。\n\n## 必填输出\n使用这些字段：\n- category\n- urgency\n- first_response_draft\n- escalation_owner\n- evidence_used\n- missing_information\n- pii_handling_note\n```\n\n### agents/interface.yaml\n```yaml\ndisplay_name: 客服工单分诊\nshort_description: 对工单分类、起草首轮回复，并给出升级依据。\ndefault_prompt: 请用分类、紧急程度、回复、升级负责人和依据来分诊这个客服工单。\n```\n\n### 评测用例\n1. 企业客户在已知故障期间提交工单：必须标为 `critical`，并升级给 incident commander。\n2. SMB 客户的账务困惑：不应过度升级。\n3. 带客户邮箱和 token 片段的安全披露：必须脱敏 token，并升级安全团队。\n4. 伪装成投诉的功能请求：应归类为功能请求，紧急程度为普通。\n5. 近邻请求：“把这段回复改得更温和”不应触发包级分诊。\n\n### 发布门禁\n- 触发评测：正例、反例、近邻文案润色。\n- 输出评测：首轮回复不能编造 SLA，升级必须匹配策略。\n- 隐私检查：报告不能保存原始工单 PII。\n- 审查备注：如果分类规则或升级负责人未提供，标记为 `missing evidence`，不要编造。\n\n### 下一步\n加入 3 个匿名工单 fixture，运行输出评测，并记录错误升级、泛泛回复和 PII 泄露的失败分类。\n"
|
||||
},
|
||||
"html_report": "case-01-support-triage.html"
|
||||
},
|
||||
{
|
||||
"id": "case-02-monthly-revenue-reconciliation",
|
||||
"title": "月度收入对账 Skill",
|
||||
"scenario": "一个财务运营团队每个月结账前都要比对 Stripe 导出、数据仓库发票 CSV 和人工调整表，找出金额、币种、发票和调整项的不一致。",
|
||||
"user_prompt": "请创建一个用于月度收入对账的可复用 skill。输入是 Stripe balance export CSV、warehouse invoice CSV 和 adjustments sheet。输出需要标出不一致项、解释可能原因，并生成可用于月结的摘要。准确性比速度更重要。",
|
||||
"rubric": [
|
||||
"是否识别出这是 file-backed 且准确性敏感的任务。",
|
||||
"是否定义了确定性脚本和资源边界。",
|
||||
"是否说明输入/输出 schema 与对账容差。",
|
||||
"是否包含 fixture 和失败用例验证。",
|
||||
"是否避免编造财务事实或隐藏未解决差异。"
|
||||
],
|
||||
"variants": {
|
||||
"A": "## Skill 包建议：revenue-reconciliation\n\n### 边界\n负责围绕 Stripe balance export、warehouse invoice CSV 和调整表的重复月结对账。排除税务建议、收入确认政策决策、支付渠道配置和一次性表格美化。\n\n### 风险等级\nGoverned，file-backed，准确性敏感。任何可用于月结的结论前，都必须有确定性解析和可见的未解决项目。\n\n### 包结构\n```\nrevenue-reconciliation/\n SKILL.md\n agents/interface.yaml\n scripts/\n reconcile_revenue.py\n validate_reconciliation_fixture.py\n references/\n input-schema.md\n tolerance-policy.md\n close-summary-contract.md\n evals/\n output/\n cases.jsonl\n fixtures/\n stripe_sample.csv\n warehouse_sample.csv\n adjustments_sample.csv\n reports/\n output-risk-profile.md\n output_quality_scorecard.md\n trust_report.md\n```\n\n### SKILL.md\n```markdown\n---\nname: revenue-reconciliation\ndescription: 对来自 Stripe 导出、warehouse invoice CSV 和调整表的重复月结收入文件进行对账。用于 file-backed 差异检测、可能原因分析、未解决项目报告和月结摘要。不要用于收入确认建议、税务指导、支付渠道配置或一次性表格格式整理。\n---\n\n# 收入对账\n\n## 工作流\n1. 要求提供所有输入文件；缺失文件必须标记为 `missing evidence`。\n2. 阅读 `references/input-schema.md`，先校验列再分析。\n3. 运行 `scripts/reconcile_revenue.py`，规范化 ID、币种、金额精度、日期和调整项关联。\n4. 审查 JSON 输出，并按缺失发票、金额差异、币种差异、重复项、时间差异或仅调整项分类。\n5. 只基于脚本证据生成月结摘要。\n6. 保持未解决差异可见。不要编造原因、审批或政策判断。\n\n## 输出契约\n- input_files\n- validation_status\n- totals_by_source\n- matched_count\n- mismatch_table\n- likely_causes\n- unresolved_items\n- close_ready_summary\n- missing_evidence\n```\n\n### 确定性脚本契约\n`scripts/reconcile_revenue.py` 应接受：\n```bash\npython3 scripts/reconcile_revenue.py --stripe stripe.csv --warehouse warehouse.csv --adjustments adjustments.csv --output reconciliation.json\n```\n\n它应返回包含源行 ID 的结构化 JSON，让摘要里的每个结论都能追溯到 file-backed fixture。\n\n### 评测\n- Fixture 1：所有记录匹配。\n- Fixture 2：Stripe 有付款，但 warehouse 缺发票。\n- Fixture 3：warehouse 金额超过容差。\n- Fixture 4：人工调整解释了差异。\n- 近邻请求：“把这个表格弄好看一点”不应路由到这里。\n\n### 门禁\n- 汇总前必须通过输入 schema 校验。\n- 如果遗漏未解决差异，输出评测必须失败。\n- Trust check 应标记网络访问为不必要。\n- Review Studio 应在晋级前显示 file-backed fixture 覆盖和未解决差异处理。\n",
|
||||
"B": "## 建议 Skill：revenue-reconciliation\n\n### 目的\n帮助 Codex 对 Stripe、数据仓库发票和人工调整表中的月度收入记录进行对账。\n\n### 建议包结构\n```\nrevenue-reconciliation/\n SKILL.md\n agents/openai.yaml\n scripts/\n reconcile_revenue.py\n references/\n csv-schema.md\n```\n\n### SKILL.md 草稿\n```markdown\n---\nname: revenue-reconciliation\ndescription: 对 Stripe balance export、warehouse invoice CSV 和调整表中的月度收入数据进行对账。当用户要求比较收入文件、找出不一致项或准备月结摘要时使用。\n---\n\n# 收入对账\n\n## 工作流\n1. 确认用户提供了 Stripe 导出、warehouse invoice CSV 和调整表。\n2. 阅读 `references/csv-schema.md`，了解预期列。\n3. 使用用户提供的文件运行 `scripts/reconcile_revenue.py`。\n4. 审查不一致项，并总结可能原因。\n5. 不要编造缺失值。清楚标记未解决记录。\n\n## 输出\n- 已检查文件\n- 匹配总额\n- 不一致项\n- 可能原因\n- 未解决项目\n- 月结摘要\n```\n\n### 脚本\n`scripts/reconcile_revenue.py` 应解析 CSV 输入，规范化 invoice ID 和币种，比较金额，并输出 JSON 供 Codex 总结。\n\n### agents/openai.yaml\n```yaml\ndisplay_name: 收入对账\nshort_description: 比对收入 CSV，并总结月结差异。\ndefault_prompt: 请对这些收入文件进行对账，并生成月结摘要。\n```\n\n### 验证\n使用包含匹配发票、缺失发票、重复发票和仅调整项记录的样例 CSV。确认未解决差异不会被隐藏。\n"
|
||||
},
|
||||
"html_report": "case-02-monthly-revenue-reconciliation.html"
|
||||
},
|
||||
{
|
||||
"id": "case-03-webinar-repurposing",
|
||||
"title": "Webinar 内容复用 Skill",
|
||||
"scenario": "一个市场团队经常把 webinar 逐字稿改写成 LinkedIn 帖子、邮件 teaser 和 newsletter 段落，同时必须保证所有说法都有来源，并避开禁止宣传的 claim。",
|
||||
"user_prompt": "请做一个可复用 skill，把 webinar 逐字稿复用成市场内容。输入包括逐字稿、讲者姓名、产品定位说明和禁止使用的 claim。输出包括 LinkedIn 帖子、邮件 teaser、newsletter 段落、可引用金句和来源依据说明。",
|
||||
"rubric": [
|
||||
"是否保留来源约束，并处理 banned claims。",
|
||||
"是否定义可重复的多渠道输出格式。",
|
||||
"是否把语气和定位资料放到 references，避免入口膨胀。",
|
||||
"是否有针对幻觉 claim 和泛泛市场文案的评测。",
|
||||
"是否在中等治理风险下保持 skill 足够轻量。"
|
||||
],
|
||||
"variants": {
|
||||
"A": "## 建议 Skill：webinar-repurposer\n\n### 目的\n创建一个 skill，把 webinar 逐字稿转成可复用的市场内容。\n\n### 包结构\n```\nwebinar-repurposer/\n SKILL.md\n agents/openai.yaml\n references/\n brand-voice.md\n banned-claims.md\n```\n\n### SKILL.md 草稿\n```markdown\n---\nname: webinar-repurposer\ndescription: 将 webinar 逐字稿复用成 LinkedIn 帖子、邮件 teaser、newsletter 段落、可引用金句和来源依据说明。当用户提供逐字稿、讲者、定位说明或禁止 claim 时使用。\n---\n\n# Webinar 内容复用\n\n## 工作流\n1. 阅读逐字稿、讲者姓名、产品定位说明和禁止 claim。\n2. 提取核心主题、最强的来源支持观点和可用引语。\n3. 起草一条 LinkedIn 帖子、一段邮件 teaser、一段 newsletter 和若干金句。\n4. 对照逐字稿和禁止 claim 检查每个说法。\n5. 为重要 claim 添加来源依据说明。\n\n## 输出\n- LinkedIn 帖子\n- 邮件 teaser\n- Newsletter 段落\n- 可引用金句\n- 来源依据说明\n- 已避免的 claim\n\n## 参考资料\n语气见 `references/brand-voice.md`，禁止 claim 见 `references/banned-claims.md`。\n```\n\n### agents/openai.yaml\n```yaml\ndisplay_name: Webinar 内容复用\nshort_description: 将 webinar 逐字稿转成有来源依据的市场内容。\ndefault_prompt: 请把这份 webinar 逐字稿复用成可发布的多渠道市场内容。\n```\n\n### 验证\n用包含强金句、证据较弱、以及容易误用禁止 claim 的逐字稿测试。确认输出会避免没有依据的 claim。\n",
|
||||
"B": "## Skill 包建议：webinar-repurposer\n\n### 边界\n负责在提供来源逐字稿和定位约束时，把逐字稿复用为市场内容。排除全新 campaign strategy、没有依据的产品 claim、法律审核和一次性文案润色。\n\n### 类型\nProduction-light。它需要输出质量检查和 banned-claim 防护，但除非涉及受监管 claim 或上市公司披露规则，否则不需要做成很重的 governed 包。\n\n### 包结构\n```\nwebinar-repurposer/\n SKILL.md\n agents/interface.yaml\n references/\n brand-voice.md\n positioning-notes.md\n banned-claims.md\n evals/\n output/\n cases.jsonl\n reports/\n output-risk-profile.md\n prompt-quality-profile.md\n```\n\n### SKILL.md\n```markdown\n---\nname: webinar-repurposer\ndescription: 将重复出现的 webinar 逐字稿复用为有来源依据的 LinkedIn 帖子、邮件 teaser、newsletter 段落、金句和 claim 依据说明。当提供逐字稿、讲者、定位说明或禁止 claim 时使用。不要用于无依据的发布 claim、法律审批、全新 campaign strategy 或一次性文案润色。\n---\n\n# Webinar 内容复用\n\n## 工作流\n1. 确认逐字稿是事实来源。\n2. 提取有来源支持的主题、讲者背书的引语和可安全复用的 claim。\n3. 起草前先检查 `references/banned-claims.md`。\n4. 生成各渠道输出，但不要添加逐字稿中没有的性能数字、客户结果或产品承诺。\n5. 添加来源依据说明，把每个主要 claim 绑定到逐字稿证据。\n\n## 必填输出\n- linkedin_post\n- email_teaser\n- newsletter_section\n- pull_quotes\n- source_grounding_notes\n- claims_avoided\n- missing_evidence\n```\n\n### 输出风险画像\n常见失败：\n- 生成任何产品都能用的泛泛市场话术。\n- 编造指标或客户结果。\n- 过度改写金句，导致意思偏离。\n- 因为某个 claim 很有吸引力而忽略 banned claims。\n\n### 输出评测用例\n1. 逐字稿包含诱人的“guaranteed ROI”禁止 claim：输出必须避开。\n2. 逐字稿没有量化证明：输出不能编造数字。\n3. 讲者原话不够顺：可以轻微修语法，但必须保留原意。\n4. 近邻请求：“从零写一个新 campaign idea”不应路由到这里。\n\n### 审查门禁\n- 必填 section 必须全部出现。\n- Banned claim 检查必须显式出现。\n- 来源依据说明必须引用逐字稿位置或原话片段。\n- 缺失证据必须被标出，而不是用通用卖点填补。\n"
|
||||
},
|
||||
"html_report": "case-03-webinar-repurposing.html"
|
||||
},
|
||||
{
|
||||
"id": "case-04-incident-postmortem",
|
||||
"title": "故障复盘 Skill",
|
||||
"scenario": "一个基础设施团队经常把 Slack 故障时间线、告警数据和部署记录整理成故障复盘和后续行动项。",
|
||||
"user_prompt": "请创建一个可复用的 governed skill，用于故障复盘。输入包括告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表。输出应包含时间线、影响、根因假设、行动项、未解决证据和后续负责人矩阵。",
|
||||
"rubric": [
|
||||
"是否处理 governed/运营风险和未解决证据。",
|
||||
"是否区分假设和已确认根因。",
|
||||
"是否定义行动项负责人矩阵和回滚/跟进边界。",
|
||||
"是否要求 file-backed 或 source-backed 证据。",
|
||||
"是否有针对 blame language 和编造因果的审查门禁。"
|
||||
],
|
||||
"variants": {
|
||||
"A": "## Skill 包建议：incident-postmortem\n\n### 边界\n负责根据 source-backed 时间线、Slack 摘要、部署记录、客户影响说明和负责人列表起草 governed 故障复盘。不要用于实时 incident command、最终 RCA 签核、HR/归责分析或面向客户的法律声明。\n\n### 类型\nGoverned。这个包会影响运营责任归属，如果证据不足，容易制造虚假因果。\n\n### 包结构\n```\nincident-postmortem/\n SKILL.md\n agents/interface.yaml\n references/\n postmortem-contract.md\n severity-policy.md\n blame-free-language.md\n action-owner-matrix.md\n evals/\n output/\n cases.jsonl\n fixtures/\n alert_timeline.json\n slack_summary.md\n deploy_notes.md\n reports/\n output-risk-profile.md\n output_quality_scorecard.md\n trust_report.md\n review-studio.html\n```\n\n### SKILL.md\n```markdown\n---\nname: incident-postmortem\ndescription: 根据告警时间线、Slack 摘要、部署记录、影响说明和负责人列表起草 governed 故障复盘。用于 source-backed 时间线重建、影响总结、根因假设、行动项、未解决证据和后续负责人矩阵。不要用于实时故障指挥、最终 RCA 审批、归责或法律/客户承诺。\n---\n\n# 故障复盘\n\n## 工作流\n1. 要求提供 source-backed 故障输入，并把缺失输入列为 `missing evidence`。\n2. 只根据已提供时间戳建立时间线；如需推断顺序，必须明确标注。\n3. 分开列出 `confirmed_facts`、`root_cause_hypotheses` 和 `unresolved_evidence`。\n4. 总结客户影响，但不要编造受影响账户、持续时间或 SLA 违约。\n5. 创建行动项：包含 owner、due date、验证信号和回滚/跟进边界。\n6. 使用 `references/blame-free-language.md` 的无责语言。\n7. 除非 reviewer 明确提供，否则最终 RCA 审批不属于本 skill。\n\n## 输出契约\n- incident_summary\n- source_inputs\n- timeline\n- customer_impact\n- confirmed_facts\n- root_cause_hypotheses\n- unresolved_evidence\n- action_items\n- owner_matrix\n- approval_status\n```\n\n### 输出评测用例\n1. Slack 和部署记录冲突：必须保留为未解决证据。\n2. 告警时间线缺恢复时间：不能编造持续时长。\n3. 用户要求实时故障决策：应路由出去，或说明本 skill 只做复盘。\n4. 来源材料带有归责语言：输出必须改写为系统/流程语言。\n5. 缺负责人列表：行动项 owner 字段应为 `missing evidence`。\n\n### 门禁\n- 时间线和部署记录需要 file-backed fixture 覆盖。\n- 输出评测禁止编造因果和隐藏未解决证据。\n- Review Studio 在人工 reviewer 审批行动负责人矩阵前保持 warning。\n- Trust report 应显示无网络和无破坏性操作。\n",
|
||||
"B": "## 建议 Skill：incident-postmortem\n\n### 目的\n帮助 Codex 根据时间线、Slack 摘要、部署记录、影响说明和负责人列表创建结构化故障复盘。\n\n### 包结构\n```\nincident-postmortem/\n SKILL.md\n agents/openai.yaml\n references/\n postmortem-template.md\n severity-policy.md\n```\n\n### SKILL.md 草稿\n```markdown\n---\nname: incident-postmortem\ndescription: 根据告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表创建故障复盘。当用户需要时间线、影响、根因假设、行动项、未解决证据或负责人矩阵时使用。\n---\n\n# 故障复盘\n\n## 工作流\n1. 收集告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表。\n2. 建立按时间排序的时间线。\n3. 总结客户和系统影响。\n4. 识别已确认事实和根因假设。\n5. 在提供负责人和截止时间时，起草行动项。\n6. 清楚标记未解决证据。\n7. 避免归责式语言。\n\n## 输出\n- 故障摘要\n- 时间线\n- 影响\n- 根因假设\n- 已确认事实\n- 未解决证据\n- 行动项\n- 负责人矩阵\n```\n\n### agents/openai.yaml\n```yaml\ndisplay_name: 故障复盘\nshort_description: 根据故障证据生成结构化复盘。\ndefault_prompt: 请把这些故障证据整理成复盘和负责人矩阵。\n```\n\n### 验证\n用证据完整、缺部署记录、Slack 说法冲突和暂时没有根因的 case 测试。确认 skill 会区分事实和假设。\n"
|
||||
},
|
||||
"html_report": "case-04-incident-postmortem.html"
|
||||
},
|
||||
{
|
||||
"id": "case-05-pr-review-followup",
|
||||
"title": "PR Review 跟进 Skill",
|
||||
"scenario": "一个小工程团队经常收到 GitHub PR review comments，希望 Codex 能把评论转成补丁、回复摘要和验证记录。",
|
||||
"user_prompt": "请设计一个用于处理 PR review comments 的可复用 skill。输入包括 review comments、变更文件、失败 CI 说明和 maintainer preferences。输出需要分组评论、只修改相关文件、写回复说明并运行验证。必须避免回滚无关的用户改动。",
|
||||
"rubric": [
|
||||
"是否理解 code-review 跟进和 dirty worktree 安全。",
|
||||
"是否定义评论分组、补丁、回复和验证工作流。",
|
||||
"是否避免过度重构和无关 revert。",
|
||||
"是否说明变更后需要的命令和证据。",
|
||||
"是否定义一般 code review 与评论跟进的触发排除。"
|
||||
],
|
||||
"variants": {
|
||||
"A": "## 建议 Skill：pr-review-followup\n\n### 目的\n创建一个 skill，帮助 Codex 安全处理 PR review comments，并总结回复。\n\n### 包结构\n```\npr-review-followup/\n SKILL.md\n agents/openai.yaml\n references/\n response-style.md\n```\n\n### SKILL.md 草稿\n```markdown\n---\nname: pr-review-followup\ndescription: 通过分组反馈、修改相关文件、编写回复说明和运行验证来处理 GitHub PR review comments。当用户提供 review comments、变更文件、CI 说明或 maintainer preferences 时使用。\n---\n\n# PR Review 跟进\n\n## 工作流\n1. 阅读所有 review comments，并按文件、主题和严重程度分组。\n2. 编辑前检查受影响文件。\n3. 只修改处理 comments 所需的文件。\n4. 不要回滚无关用户改动。\n5. 运行相关测试或 CI 复现命令。\n6. 总结变更，并为 reviewer 起草回复说明。\n\n## 输出\n- 评论分组\n- 修改文件\n- 验证命令\n- Reviewer 回复说明\n- 剩余问题\n```\n\n### agents/openai.yaml\n```yaml\ndisplay_name: PR Review 跟进\nshort_description: 处理 PR comments 并准备 reviewer 回复。\ndefault_prompt: 请处理这些 PR review comments，并总结验证结果。\n```\n\n### 验证\n用需要代码修改、文档修改、无需修改只需解释、以及 reviewer 要求冲突的 comments 测试。\n",
|
||||
"B": "## Skill 包建议：pr-review-followup\n\n### 边界\n负责 PR 已经有明确 reviewer comments、变更文件或 CI 说明之后的评论跟进。排除首次 code review、大范围重构、issue triage，以及没有绑定评论的推测性清理。\n\n### 包结构\n```\npr-review-followup/\n SKILL.md\n agents/interface.yaml\n references/\n response-style.md\n dirty-worktree-safety.md\n verification-policy.md\n evals/\n trigger_cases.json\n output/\n cases.jsonl\n reports/\n output-risk-profile.md\n output_quality_scorecard.md\n```\n\n### SKILL.md\n```markdown\n---\nname: pr-review-followup\ndescription: 处理具体 PR review comments：分组反馈、只修改相关文件、保留无关用户改动、起草 reviewer 回复并运行验证。当提供 review comments、变更文件、失败 CI 说明或 maintainer preferences 时使用。不要用于首次 code review、大范围重构、issue triage 或无关清理。\n---\n\n# PR Review 跟进\n\n## 工作流\n1. 编辑前记录 git status，并识别用户已经改动的文件。\n2. 按文件、行为、严重程度，以及是否需要代码、测试、文档或仅解释来分组 review comments。\n3. 修改前阅读受影响代码和附近测试。\n4. 只修改与评论绑定的文件。不要回滚无关改动，也不要格式化未触碰文件。\n5. 运行有针对性的验证，并记录命令和结果。\n6. 起草 reviewer 回复说明，把每组评论映射到变更、无需修改的理由或剩余问题。\n7. 如果评论冲突，停止并询问哪个 reviewer 指令优先。\n\n## 输出契约\n- comment_groups\n- patch_summary\n- files_changed\n- verification\n- reviewer_response_notes\n- unresolved_questions\n- unrelated_changes_preserved\n```\n\n### 输出评测用例\n1. 评论要求添加特定 null check：输出必须只修改受影响函数，并提到测试。\n2. Reviewer 要求与 PR 范围无关的大重构：输出应标出范围风险。\n3. Dirty worktree 中有无关用户文件：输出必须保留它。\n4. 两个 reviewer comments 冲突：输出必须询问优先级，而不是猜。\n5. 近邻请求：“从零 review 这个 PR”不应触发 follow-up mode。\n\n### 门禁\n- 触发评测必须区分首次 review 和评论跟进。\n- 如果回滚或隐藏无关改动，输出评测必须失败。\n- 验证策略必须记录跳过测试的原因。\n- 回复说明必须能追溯到评论分组。\n"
|
||||
},
|
||||
"html_report": "case-05-pr-review-followup.html"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,380 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>客服工单分诊 Skill - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body data-case-id="case-01-support-triage">
|
||||
<header>
|
||||
<div class="split"><a class="button" href="index.html">返回入口</a><a class="button" href="case-02-monthly-revenue-reconciliation.html">下一个</a></div>
|
||||
<h1>客服工单分诊 Skill</h1>
|
||||
<p class="meta">A/B 盲测评审。记录完判断前，不要打开答案钥匙。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>场景</h2>
|
||||
<p>一个 B2B SaaS 团队每天都要处理客户工单：判断分类、紧急程度、起草首轮回复，并把账务、安全、故障类问题升级给对应负责人。他们希望把这个重复流程做成一个给支持团队使用的 Codex skill。</p>
|
||||
<h3>用户请求</h3>
|
||||
<p>请把我们反复使用的客服工单分诊流程做成一个团队可复用的 skill。输入包括原始工单文本、客户等级、产品模块和近期故障记录。输出需要包含问题分类、紧急程度、首轮回复草稿、升级负责人和判断依据。不要把 PII 泄露到报告里。</p>
|
||||
<h3>评审标准</h3>
|
||||
<ol class="rubric"><li>是否有清楚的触发边界和近邻排除。</li>
|
||||
<li>是否是可复用的 skill 包结构，而不只是一个提示词。</li>
|
||||
<li>是否定义了分类、紧急程度、回复、升级和证据的输出契约。</li>
|
||||
<li>是否处理 PII 和客户内容的隐私风险。</li>
|
||||
<li>是否有能发现错误升级和泛泛回复的评测方案。</li></ol>
|
||||
</section>
|
||||
|
||||
<div class="grid" style="margin-top:18px">
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 A</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>建议 Skill：support-triage</h2>
|
||||
|
||||
<h3>目的</h3>
|
||||
<p>创建一个简洁的 skill，帮助 Codex 对 B2B SaaS 客服工单进行分诊，并起草首轮回复。</p>
|
||||
|
||||
<h3>建议包结构</h3>
|
||||
<pre><code>support-triage/
|
||||
SKILL.md
|
||||
agents/openai.yaml
|
||||
references/
|
||||
triage-taxonomy.md
|
||||
escalation-policy.md</code></pre>
|
||||
|
||||
<h3>SKILL.md 草稿</h3>
|
||||
<pre><code>---
|
||||
name: support-triage
|
||||
description: 对 B2B SaaS 客服工单进行分诊并起草首轮回复。当用户提供原始工单文本、客户等级、产品模块、故障记录，或需要紧急程度、分类、升级建议时使用。
|
||||
---
|
||||
|
||||
# 客服工单分诊
|
||||
|
||||
使用这个 skill 对入站工单分类、起草合适的首轮回复，并识别是否需要升级。
|
||||
|
||||
## 工作流
|
||||
1. 阅读工单文本、客户等级、产品模块和近期故障记录。
|
||||
2. 将工单归为一个主分类：账务、访问权限、缺陷、故障、功能请求、安全、数据/隐私、上手问题或其他。
|
||||
3. 标记紧急程度：低、普通、高、严重。
|
||||
4. 起草首轮回复：确认问题、只询问必要补充信息，并避免没有依据的承诺。
|
||||
5. 对安全、隐私、严重故障、数据丢失或企业客户影响问题进行升级。
|
||||
6. 汇报判断依据，但不要复制不必要的 PII。
|
||||
|
||||
## 输出格式
|
||||
- 分类：
|
||||
- 紧急程度：
|
||||
- 首轮回复：
|
||||
- 升级负责人：
|
||||
- 判断依据：
|
||||
- 缺失信息：
|
||||
|
||||
## 参考资料
|
||||
- 分类规则见 `references/triage-taxonomy.md`。
|
||||
- 升级标准见 `references/escalation-policy.md`。</code></pre>
|
||||
|
||||
<h3>agents/openai.yaml</h3>
|
||||
<pre><code>display_name: 客服工单分诊
|
||||
short_description: 对客服工单分类，并起草首轮回复。
|
||||
default_prompt: 请分诊这个客服工单，并起草首轮回复。</code></pre>
|
||||
|
||||
<h3>资源</h3>
|
||||
<ul>
|
||||
<li>`references/triage-taxonomy.md`：分类定义、紧急程度提示和示例。</li>
|
||||
<li>`references/escalation-policy.md`：升级负责人和升级标准。</li>
|
||||
</ul>
|
||||
|
||||
<h3>验证</h3>
|
||||
<p>用账务、安全、故障和功能请求等代表性工单测试。确认输出会最小化 PII，并且严重问题会被升级。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 B</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>Skill 包建议：support-triage</h2>
|
||||
|
||||
<h3>边界</h3>
|
||||
<p>负责重复出现的客服工单分诊：用户提供工单文本以及客户/产品上下文，需要结构化路由决策。不要用于一次性文案润色、泛泛的客服同理心训练、CRM 配置，或超出升级范围的法律/安全事件处置。</p>
|
||||
|
||||
<h3>输出契约</h3>
|
||||
<p>这个 skill 必须返回：</p>
|
||||
<ul>
|
||||
<li>`category`</li>
|
||||
<li>`urgency`</li>
|
||||
<li>`first_response_draft`</li>
|
||||
<li>`escalation_owner`</li>
|
||||
<li>`evidence_used`</li>
|
||||
<li>`missing_information`</li>
|
||||
<li>`pii_handling_note`</li>
|
||||
</ul>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>support-triage/
|
||||
SKILL.md
|
||||
agents/interface.yaml
|
||||
references/
|
||||
triage-taxonomy.md
|
||||
escalation-policy.md
|
||||
privacy-redaction.md
|
||||
evals/
|
||||
trigger_cases.json
|
||||
output/
|
||||
cases.jsonl
|
||||
fixtures/
|
||||
reports/
|
||||
output-risk-profile.md
|
||||
output_quality_scorecard.md</code></pre>
|
||||
|
||||
<h3>SKILL.md</h3>
|
||||
<pre><code>---
|
||||
name: support-triage
|
||||
description: 将重复出现的 B2B SaaS 客服工单分诊为分类、紧急程度、首轮回复、升级负责人、判断依据和缺失信息。当输入包含原始工单、客户等级、产品模块、故障记录或支持队列上下文时使用。不要用于一次性文案润色、CRM 设置、法律建议或最终安全事件处置。
|
||||
---
|
||||
|
||||
# 客服工单分诊
|
||||
|
||||
## 工作流
|
||||
1. 确认这是重复的工单分诊任务，而不是一次性文案润色。
|
||||
2. 阅读工单文本、客户等级、产品模块和故障记录。
|
||||
3. 使用 `references/triage-taxonomy.md` 判断分类和紧急程度。
|
||||
4. 按 `references/escalation-policy.md` 检查升级标准。
|
||||
5. 起草首轮回复：确认问题、避免无依据承诺，只请求最少的缺失信息。
|
||||
6. 按 `references/privacy-redaction.md` 对 PII 做脱敏或摘要。
|
||||
7. 严格按输出契约返回。
|
||||
|
||||
## 必填输出
|
||||
使用这些字段：
|
||||
- category
|
||||
- urgency
|
||||
- first_response_draft
|
||||
- escalation_owner
|
||||
- evidence_used
|
||||
- missing_information
|
||||
- pii_handling_note</code></pre>
|
||||
|
||||
<h3>agents/interface.yaml</h3>
|
||||
<pre><code>display_name: 客服工单分诊
|
||||
short_description: 对工单分类、起草首轮回复，并给出升级依据。
|
||||
default_prompt: 请用分类、紧急程度、回复、升级负责人和依据来分诊这个客服工单。</code></pre>
|
||||
|
||||
<h3>评测用例</h3>
|
||||
<p>1. 企业客户在已知故障期间提交工单：必须标为 `critical`，并升级给 incident commander。</p>
|
||||
<p>2. SMB 客户的账务困惑：不应过度升级。</p>
|
||||
<p>3. 带客户邮箱和 token 片段的安全披露：必须脱敏 token，并升级安全团队。</p>
|
||||
<p>4. 伪装成投诉的功能请求：应归类为功能请求，紧急程度为普通。</p>
|
||||
<p>5. 近邻请求：“把这段回复改得更温和”不应触发包级分诊。</p>
|
||||
|
||||
<h3>发布门禁</h3>
|
||||
<ul>
|
||||
<li>触发评测：正例、反例、近邻文案润色。</li>
|
||||
<li>输出评测：首轮回复不能编造 SLA，升级必须匹配策略。</li>
|
||||
<li>隐私检查：报告不能保存原始工单 PII。</li>
|
||||
<li>审查备注：如果分类规则或升级负责人未提供，标记为 `missing evidence`，不要编造。</li>
|
||||
</ul>
|
||||
|
||||
<h3>下一步</h3>
|
||||
<p>加入 3 个匿名工单 fixture，运行输出评测，并记录错误升级、泛泛回复和 PII 泄露的失败分类。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<section class="review-box">
|
||||
<h2>你的判断</h2>
|
||||
<p class="note">只根据评审标准和页面里可见的两个输出做判断。选择会保存到当前浏览器的本地存储里，也可以回到入口页导出。</p>
|
||||
<div class="controls" role="radiogroup" aria-label="胜出方案">
|
||||
<label><input type="radio" name="winner" value="A"> 方案 A 更好</label>
|
||||
<label><input type="radio" name="winner" value="B"> 方案 B 更好</label>
|
||||
<label><input type="radio" name="winner" value="tie"> 平局 / 没有明显胜出</label>
|
||||
</div>
|
||||
<label for="confidence">信心程度</label>
|
||||
<div class="controls">
|
||||
<select id="confidence">
|
||||
<option value="">请选择</option>
|
||||
<option value="0.4">0.4，较弱</option>
|
||||
<option value="0.6">0.6，中等</option>
|
||||
<option value="0.8">0.8，较强</option>
|
||||
<option value="1.0">1.0，非常确定</option>
|
||||
</select>
|
||||
</div>
|
||||
<label for="reason">理由</label>
|
||||
<textarea id="reason" placeholder="为什么这个方案更好？请写出具体的评审标准差异。"></textarea>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="saveDecision()">保存判断</button>
|
||||
<button type="button" onclick="clearDecision()">清空</button>
|
||||
</div>
|
||||
<p id="save-status" class="small note"></p>
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseId = document.body.dataset.caseId;
|
||||
const key = "blindSkillReview:" + caseId;
|
||||
function currentDecision() {
|
||||
const selected = document.querySelector('input[name="winner"]:checked');
|
||||
return {
|
||||
case_id: caseId,
|
||||
winner_variant: selected ? selected.value : "",
|
||||
confidence: document.getElementById("confidence").value,
|
||||
reason: document.getElementById("reason").value.trim(),
|
||||
reviewed_at: new Date().toISOString()
|
||||
};
|
||||
}
|
||||
function saveDecision() {
|
||||
const decision = currentDecision();
|
||||
localStorage.setItem(key, JSON.stringify(decision));
|
||||
document.getElementById("save-status").textContent = "已保存：" + decision.reviewed_at;
|
||||
}
|
||||
function clearDecision() {
|
||||
localStorage.removeItem(key);
|
||||
document.querySelectorAll('input[name="winner"]').forEach(el => el.checked = false);
|
||||
document.getElementById("confidence").value = "";
|
||||
document.getElementById("reason").value = "";
|
||||
document.getElementById("save-status").textContent = "已清空。";
|
||||
}
|
||||
function loadDecision() {
|
||||
const raw = localStorage.getItem(key);
|
||||
if (!raw) return;
|
||||
const decision = JSON.parse(raw);
|
||||
const selected = document.querySelector('input[name="winner"][value="' + decision.winner_variant + '"]');
|
||||
if (selected) selected.checked = true;
|
||||
document.getElementById("confidence").value = decision.confidence || "";
|
||||
document.getElementById("reason").value = decision.reason || "";
|
||||
document.getElementById("save-status").textContent = "已加载保存过的判断。";
|
||||
}
|
||||
loadDecision();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,368 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>月度收入对账 Skill - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body data-case-id="case-02-monthly-revenue-reconciliation">
|
||||
<header>
|
||||
<div class="split"><a class="button" href="index.html">返回入口</a><a class="button" href="case-01-support-triage.html">上一个</a><a class="button" href="case-03-webinar-repurposing.html">下一个</a></div>
|
||||
<h1>月度收入对账 Skill</h1>
|
||||
<p class="meta">A/B 盲测评审。记录完判断前，不要打开答案钥匙。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>场景</h2>
|
||||
<p>一个财务运营团队每个月结账前都要比对 Stripe 导出、数据仓库发票 CSV 和人工调整表，找出金额、币种、发票和调整项的不一致。</p>
|
||||
<h3>用户请求</h3>
|
||||
<p>请创建一个用于月度收入对账的可复用 skill。输入是 Stripe balance export CSV、warehouse invoice CSV 和 adjustments sheet。输出需要标出不一致项、解释可能原因，并生成可用于月结的摘要。准确性比速度更重要。</p>
|
||||
<h3>评审标准</h3>
|
||||
<ol class="rubric"><li>是否识别出这是 file-backed 且准确性敏感的任务。</li>
|
||||
<li>是否定义了确定性脚本和资源边界。</li>
|
||||
<li>是否说明输入/输出 schema 与对账容差。</li>
|
||||
<li>是否包含 fixture 和失败用例验证。</li>
|
||||
<li>是否避免编造财务事实或隐藏未解决差异。</li></ol>
|
||||
</section>
|
||||
|
||||
<div class="grid" style="margin-top:18px">
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 A</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>Skill 包建议：revenue-reconciliation</h2>
|
||||
|
||||
<h3>边界</h3>
|
||||
<p>负责围绕 Stripe balance export、warehouse invoice CSV 和调整表的重复月结对账。排除税务建议、收入确认政策决策、支付渠道配置和一次性表格美化。</p>
|
||||
|
||||
<h3>风险等级</h3>
|
||||
<p>Governed，file-backed，准确性敏感。任何可用于月结的结论前，都必须有确定性解析和可见的未解决项目。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>revenue-reconciliation/
|
||||
SKILL.md
|
||||
agents/interface.yaml
|
||||
scripts/
|
||||
reconcile_revenue.py
|
||||
validate_reconciliation_fixture.py
|
||||
references/
|
||||
input-schema.md
|
||||
tolerance-policy.md
|
||||
close-summary-contract.md
|
||||
evals/
|
||||
output/
|
||||
cases.jsonl
|
||||
fixtures/
|
||||
stripe_sample.csv
|
||||
warehouse_sample.csv
|
||||
adjustments_sample.csv
|
||||
reports/
|
||||
output-risk-profile.md
|
||||
output_quality_scorecard.md
|
||||
trust_report.md</code></pre>
|
||||
|
||||
<h3>SKILL.md</h3>
|
||||
<pre><code>---
|
||||
name: revenue-reconciliation
|
||||
description: 对来自 Stripe 导出、warehouse invoice CSV 和调整表的重复月结收入文件进行对账。用于 file-backed 差异检测、可能原因分析、未解决项目报告和月结摘要。不要用于收入确认建议、税务指导、支付渠道配置或一次性表格格式整理。
|
||||
---
|
||||
|
||||
# 收入对账
|
||||
|
||||
## 工作流
|
||||
1. 要求提供所有输入文件；缺失文件必须标记为 `missing evidence`。
|
||||
2. 阅读 `references/input-schema.md`，先校验列再分析。
|
||||
3. 运行 `scripts/reconcile_revenue.py`，规范化 ID、币种、金额精度、日期和调整项关联。
|
||||
4. 审查 JSON 输出，并按缺失发票、金额差异、币种差异、重复项、时间差异或仅调整项分类。
|
||||
5. 只基于脚本证据生成月结摘要。
|
||||
6. 保持未解决差异可见。不要编造原因、审批或政策判断。
|
||||
|
||||
## 输出契约
|
||||
- input_files
|
||||
- validation_status
|
||||
- totals_by_source
|
||||
- matched_count
|
||||
- mismatch_table
|
||||
- likely_causes
|
||||
- unresolved_items
|
||||
- close_ready_summary
|
||||
- missing_evidence</code></pre>
|
||||
|
||||
<h3>确定性脚本契约</h3>
|
||||
<p>`scripts/reconcile_revenue.py` 应接受：</p>
|
||||
<pre><code>python3 scripts/reconcile_revenue.py --stripe stripe.csv --warehouse warehouse.csv --adjustments adjustments.csv --output reconciliation.json</code></pre>
|
||||
|
||||
<p>它应返回包含源行 ID 的结构化 JSON，让摘要里的每个结论都能追溯到 file-backed fixture。</p>
|
||||
|
||||
<h3>评测</h3>
|
||||
<ul>
|
||||
<li>Fixture 1：所有记录匹配。</li>
|
||||
<li>Fixture 2：Stripe 有付款，但 warehouse 缺发票。</li>
|
||||
<li>Fixture 3：warehouse 金额超过容差。</li>
|
||||
<li>Fixture 4：人工调整解释了差异。</li>
|
||||
<li>近邻请求：“把这个表格弄好看一点”不应路由到这里。</li>
|
||||
</ul>
|
||||
|
||||
<h3>门禁</h3>
|
||||
<ul>
|
||||
<li>汇总前必须通过输入 schema 校验。</li>
|
||||
<li>如果遗漏未解决差异，输出评测必须失败。</li>
|
||||
<li>Trust check 应标记网络访问为不必要。</li>
|
||||
<li>Review Studio 应在晋级前显示 file-backed fixture 覆盖和未解决差异处理。</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 B</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>建议 Skill：revenue-reconciliation</h2>
|
||||
|
||||
<h3>目的</h3>
|
||||
<p>帮助 Codex 对 Stripe、数据仓库发票和人工调整表中的月度收入记录进行对账。</p>
|
||||
|
||||
<h3>建议包结构</h3>
|
||||
<pre><code>revenue-reconciliation/
|
||||
SKILL.md
|
||||
agents/openai.yaml
|
||||
scripts/
|
||||
reconcile_revenue.py
|
||||
references/
|
||||
csv-schema.md</code></pre>
|
||||
|
||||
<h3>SKILL.md 草稿</h3>
|
||||
<pre><code>---
|
||||
name: revenue-reconciliation
|
||||
description: 对 Stripe balance export、warehouse invoice CSV 和调整表中的月度收入数据进行对账。当用户要求比较收入文件、找出不一致项或准备月结摘要时使用。
|
||||
---
|
||||
|
||||
# 收入对账
|
||||
|
||||
## 工作流
|
||||
1. 确认用户提供了 Stripe 导出、warehouse invoice CSV 和调整表。
|
||||
2. 阅读 `references/csv-schema.md`，了解预期列。
|
||||
3. 使用用户提供的文件运行 `scripts/reconcile_revenue.py`。
|
||||
4. 审查不一致项，并总结可能原因。
|
||||
5. 不要编造缺失值。清楚标记未解决记录。
|
||||
|
||||
## 输出
|
||||
- 已检查文件
|
||||
- 匹配总额
|
||||
- 不一致项
|
||||
- 可能原因
|
||||
- 未解决项目
|
||||
- 月结摘要</code></pre>
|
||||
|
||||
<h3>脚本</h3>
|
||||
<p>`scripts/reconcile_revenue.py` 应解析 CSV 输入，规范化 invoice ID 和币种，比较金额，并输出 JSON 供 Codex 总结。</p>
|
||||
|
||||
<h3>agents/openai.yaml</h3>
|
||||
<pre><code>display_name: 收入对账
|
||||
short_description: 比对收入 CSV，并总结月结差异。
|
||||
default_prompt: 请对这些收入文件进行对账，并生成月结摘要。</code></pre>
|
||||
|
||||
<h3>验证</h3>
|
||||
<p>使用包含匹配发票、缺失发票、重复发票和仅调整项记录的样例 CSV。确认未解决差异不会被隐藏。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<section class="review-box">
|
||||
<h2>你的判断</h2>
|
||||
<p class="note">只根据评审标准和页面里可见的两个输出做判断。选择会保存到当前浏览器的本地存储里，也可以回到入口页导出。</p>
|
||||
<div class="controls" role="radiogroup" aria-label="胜出方案">
|
||||
<label><input type="radio" name="winner" value="A"> 方案 A 更好</label>
|
||||
<label><input type="radio" name="winner" value="B"> 方案 B 更好</label>
|
||||
<label><input type="radio" name="winner" value="tie"> 平局 / 没有明显胜出</label>
|
||||
</div>
|
||||
<label for="confidence">信心程度</label>
|
||||
<div class="controls">
|
||||
<select id="confidence">
|
||||
<option value="">请选择</option>
|
||||
<option value="0.4">0.4，较弱</option>
|
||||
<option value="0.6">0.6，中等</option>
|
||||
<option value="0.8">0.8，较强</option>
|
||||
<option value="1.0">1.0，非常确定</option>
|
||||
</select>
|
||||
</div>
|
||||
<label for="reason">理由</label>
|
||||
<textarea id="reason" placeholder="为什么这个方案更好？请写出具体的评审标准差异。"></textarea>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="saveDecision()">保存判断</button>
|
||||
<button type="button" onclick="clearDecision()">清空</button>
|
||||
</div>
|
||||
<p id="save-status" class="small note"></p>
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseId = document.body.dataset.caseId;
|
||||
const key = "blindSkillReview:" + caseId;
|
||||
function currentDecision() {
|
||||
const selected = document.querySelector('input[name="winner"]:checked');
|
||||
return {
|
||||
case_id: caseId,
|
||||
winner_variant: selected ? selected.value : "",
|
||||
confidence: document.getElementById("confidence").value,
|
||||
reason: document.getElementById("reason").value.trim(),
|
||||
reviewed_at: new Date().toISOString()
|
||||
};
|
||||
}
|
||||
function saveDecision() {
|
||||
const decision = currentDecision();
|
||||
localStorage.setItem(key, JSON.stringify(decision));
|
||||
document.getElementById("save-status").textContent = "已保存：" + decision.reviewed_at;
|
||||
}
|
||||
function clearDecision() {
|
||||
localStorage.removeItem(key);
|
||||
document.querySelectorAll('input[name="winner"]').forEach(el => el.checked = false);
|
||||
document.getElementById("confidence").value = "";
|
||||
document.getElementById("reason").value = "";
|
||||
document.getElementById("save-status").textContent = "已清空。";
|
||||
}
|
||||
function loadDecision() {
|
||||
const raw = localStorage.getItem(key);
|
||||
if (!raw) return;
|
||||
const decision = JSON.parse(raw);
|
||||
const selected = document.querySelector('input[name="winner"][value="' + decision.winner_variant + '"]');
|
||||
if (selected) selected.checked = true;
|
||||
document.getElementById("confidence").value = decision.confidence || "";
|
||||
document.getElementById("reason").value = decision.reason || "";
|
||||
document.getElementById("save-status").textContent = "已加载保存过的判断。";
|
||||
}
|
||||
loadDecision();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,356 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>Webinar 内容复用 Skill - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body data-case-id="case-03-webinar-repurposing">
|
||||
<header>
|
||||
<div class="split"><a class="button" href="index.html">返回入口</a><a class="button" href="case-02-monthly-revenue-reconciliation.html">上一个</a><a class="button" href="case-04-incident-postmortem.html">下一个</a></div>
|
||||
<h1>Webinar 内容复用 Skill</h1>
|
||||
<p class="meta">A/B 盲测评审。记录完判断前，不要打开答案钥匙。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>场景</h2>
|
||||
<p>一个市场团队经常把 webinar 逐字稿改写成 LinkedIn 帖子、邮件 teaser 和 newsletter 段落，同时必须保证所有说法都有来源，并避开禁止宣传的 claim。</p>
|
||||
<h3>用户请求</h3>
|
||||
<p>请做一个可复用 skill，把 webinar 逐字稿复用成市场内容。输入包括逐字稿、讲者姓名、产品定位说明和禁止使用的 claim。输出包括 LinkedIn 帖子、邮件 teaser、newsletter 段落、可引用金句和来源依据说明。</p>
|
||||
<h3>评审标准</h3>
|
||||
<ol class="rubric"><li>是否保留来源约束，并处理 banned claims。</li>
|
||||
<li>是否定义可重复的多渠道输出格式。</li>
|
||||
<li>是否把语气和定位资料放到 references，避免入口膨胀。</li>
|
||||
<li>是否有针对幻觉 claim 和泛泛市场文案的评测。</li>
|
||||
<li>是否在中等治理风险下保持 skill 足够轻量。</li></ol>
|
||||
</section>
|
||||
|
||||
<div class="grid" style="margin-top:18px">
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 A</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>建议 Skill：webinar-repurposer</h2>
|
||||
|
||||
<h3>目的</h3>
|
||||
<p>创建一个 skill，把 webinar 逐字稿转成可复用的市场内容。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>webinar-repurposer/
|
||||
SKILL.md
|
||||
agents/openai.yaml
|
||||
references/
|
||||
brand-voice.md
|
||||
banned-claims.md</code></pre>
|
||||
|
||||
<h3>SKILL.md 草稿</h3>
|
||||
<pre><code>---
|
||||
name: webinar-repurposer
|
||||
description: 将 webinar 逐字稿复用成 LinkedIn 帖子、邮件 teaser、newsletter 段落、可引用金句和来源依据说明。当用户提供逐字稿、讲者、定位说明或禁止 claim 时使用。
|
||||
---
|
||||
|
||||
# Webinar 内容复用
|
||||
|
||||
## 工作流
|
||||
1. 阅读逐字稿、讲者姓名、产品定位说明和禁止 claim。
|
||||
2. 提取核心主题、最强的来源支持观点和可用引语。
|
||||
3. 起草一条 LinkedIn 帖子、一段邮件 teaser、一段 newsletter 和若干金句。
|
||||
4. 对照逐字稿和禁止 claim 检查每个说法。
|
||||
5. 为重要 claim 添加来源依据说明。
|
||||
|
||||
## 输出
|
||||
- LinkedIn 帖子
|
||||
- 邮件 teaser
|
||||
- Newsletter 段落
|
||||
- 可引用金句
|
||||
- 来源依据说明
|
||||
- 已避免的 claim
|
||||
|
||||
## 参考资料
|
||||
语气见 `references/brand-voice.md`，禁止 claim 见 `references/banned-claims.md`。</code></pre>
|
||||
|
||||
<h3>agents/openai.yaml</h3>
|
||||
<pre><code>display_name: Webinar 内容复用
|
||||
short_description: 将 webinar 逐字稿转成有来源依据的市场内容。
|
||||
default_prompt: 请把这份 webinar 逐字稿复用成可发布的多渠道市场内容。</code></pre>
|
||||
|
||||
<h3>验证</h3>
|
||||
<p>用包含强金句、证据较弱、以及容易误用禁止 claim 的逐字稿测试。确认输出会避免没有依据的 claim。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 B</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>Skill 包建议：webinar-repurposer</h2>
|
||||
|
||||
<h3>边界</h3>
|
||||
<p>负责在提供来源逐字稿和定位约束时，把逐字稿复用为市场内容。排除全新 campaign strategy、没有依据的产品 claim、法律审核和一次性文案润色。</p>
|
||||
|
||||
<h3>类型</h3>
|
||||
<p>Production-light。它需要输出质量检查和 banned-claim 防护，但除非涉及受监管 claim 或上市公司披露规则，否则不需要做成很重的 governed 包。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>webinar-repurposer/
|
||||
SKILL.md
|
||||
agents/interface.yaml
|
||||
references/
|
||||
brand-voice.md
|
||||
positioning-notes.md
|
||||
banned-claims.md
|
||||
evals/
|
||||
output/
|
||||
cases.jsonl
|
||||
reports/
|
||||
output-risk-profile.md
|
||||
prompt-quality-profile.md</code></pre>
|
||||
|
||||
<h3>SKILL.md</h3>
|
||||
<pre><code>---
|
||||
name: webinar-repurposer
|
||||
description: 将重复出现的 webinar 逐字稿复用为有来源依据的 LinkedIn 帖子、邮件 teaser、newsletter 段落、金句和 claim 依据说明。当提供逐字稿、讲者、定位说明或禁止 claim 时使用。不要用于无依据的发布 claim、法律审批、全新 campaign strategy 或一次性文案润色。
|
||||
---
|
||||
|
||||
# Webinar 内容复用
|
||||
|
||||
## 工作流
|
||||
1. 确认逐字稿是事实来源。
|
||||
2. 提取有来源支持的主题、讲者背书的引语和可安全复用的 claim。
|
||||
3. 起草前先检查 `references/banned-claims.md`。
|
||||
4. 生成各渠道输出，但不要添加逐字稿中没有的性能数字、客户结果或产品承诺。
|
||||
5. 添加来源依据说明，把每个主要 claim 绑定到逐字稿证据。
|
||||
|
||||
## 必填输出
|
||||
- linkedin_post
|
||||
- email_teaser
|
||||
- newsletter_section
|
||||
- pull_quotes
|
||||
- source_grounding_notes
|
||||
- claims_avoided
|
||||
- missing_evidence</code></pre>
|
||||
|
||||
<h3>输出风险画像</h3>
|
||||
<p>常见失败：</p>
|
||||
<ul>
|
||||
<li>生成任何产品都能用的泛泛市场话术。</li>
|
||||
<li>编造指标或客户结果。</li>
|
||||
<li>过度改写金句，导致意思偏离。</li>
|
||||
<li>因为某个 claim 很有吸引力而忽略 banned claims。</li>
|
||||
</ul>
|
||||
|
||||
<h3>输出评测用例</h3>
|
||||
<p>1. 逐字稿包含诱人的“guaranteed ROI”禁止 claim：输出必须避开。</p>
|
||||
<p>2. 逐字稿没有量化证明：输出不能编造数字。</p>
|
||||
<p>3. 讲者原话不够顺：可以轻微修语法，但必须保留原意。</p>
|
||||
<p>4. 近邻请求：“从零写一个新 campaign idea”不应路由到这里。</p>
|
||||
|
||||
<h3>审查门禁</h3>
|
||||
<ul>
|
||||
<li>必填 section 必须全部出现。</li>
|
||||
<li>Banned claim 检查必须显式出现。</li>
|
||||
<li>来源依据说明必须引用逐字稿位置或原话片段。</li>
|
||||
<li>缺失证据必须被标出，而不是用通用卖点填补。</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<section class="review-box">
|
||||
<h2>你的判断</h2>
|
||||
<p class="note">只根据评审标准和页面里可见的两个输出做判断。选择会保存到当前浏览器的本地存储里，也可以回到入口页导出。</p>
|
||||
<div class="controls" role="radiogroup" aria-label="胜出方案">
|
||||
<label><input type="radio" name="winner" value="A"> 方案 A 更好</label>
|
||||
<label><input type="radio" name="winner" value="B"> 方案 B 更好</label>
|
||||
<label><input type="radio" name="winner" value="tie"> 平局 / 没有明显胜出</label>
|
||||
</div>
|
||||
<label for="confidence">信心程度</label>
|
||||
<div class="controls">
|
||||
<select id="confidence">
|
||||
<option value="">请选择</option>
|
||||
<option value="0.4">0.4，较弱</option>
|
||||
<option value="0.6">0.6，中等</option>
|
||||
<option value="0.8">0.8，较强</option>
|
||||
<option value="1.0">1.0，非常确定</option>
|
||||
</select>
|
||||
</div>
|
||||
<label for="reason">理由</label>
|
||||
<textarea id="reason" placeholder="为什么这个方案更好？请写出具体的评审标准差异。"></textarea>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="saveDecision()">保存判断</button>
|
||||
<button type="button" onclick="clearDecision()">清空</button>
|
||||
</div>
|
||||
<p id="save-status" class="small note"></p>
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseId = document.body.dataset.caseId;
|
||||
const key = "blindSkillReview:" + caseId;
|
||||
function currentDecision() {
|
||||
const selected = document.querySelector('input[name="winner"]:checked');
|
||||
return {
|
||||
case_id: caseId,
|
||||
winner_variant: selected ? selected.value : "",
|
||||
confidence: document.getElementById("confidence").value,
|
||||
reason: document.getElementById("reason").value.trim(),
|
||||
reviewed_at: new Date().toISOString()
|
||||
};
|
||||
}
|
||||
function saveDecision() {
|
||||
const decision = currentDecision();
|
||||
localStorage.setItem(key, JSON.stringify(decision));
|
||||
document.getElementById("save-status").textContent = "已保存：" + decision.reviewed_at;
|
||||
}
|
||||
function clearDecision() {
|
||||
localStorage.removeItem(key);
|
||||
document.querySelectorAll('input[name="winner"]').forEach(el => el.checked = false);
|
||||
document.getElementById("confidence").value = "";
|
||||
document.getElementById("reason").value = "";
|
||||
document.getElementById("save-status").textContent = "已清空。";
|
||||
}
|
||||
function loadDecision() {
|
||||
const raw = localStorage.getItem(key);
|
||||
if (!raw) return;
|
||||
const decision = JSON.parse(raw);
|
||||
const selected = document.querySelector('input[name="winner"][value="' + decision.winner_variant + '"]');
|
||||
if (selected) selected.checked = true;
|
||||
document.getElementById("confidence").value = decision.confidence || "";
|
||||
document.getElementById("reason").value = decision.reason || "";
|
||||
document.getElementById("save-status").textContent = "已加载保存过的判断。";
|
||||
}
|
||||
loadDecision();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,361 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>故障复盘 Skill - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body data-case-id="case-04-incident-postmortem">
|
||||
<header>
|
||||
<div class="split"><a class="button" href="index.html">返回入口</a><a class="button" href="case-03-webinar-repurposing.html">上一个</a><a class="button" href="case-05-pr-review-followup.html">下一个</a></div>
|
||||
<h1>故障复盘 Skill</h1>
|
||||
<p class="meta">A/B 盲测评审。记录完判断前，不要打开答案钥匙。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>场景</h2>
|
||||
<p>一个基础设施团队经常把 Slack 故障时间线、告警数据和部署记录整理成故障复盘和后续行动项。</p>
|
||||
<h3>用户请求</h3>
|
||||
<p>请创建一个可复用的 governed skill，用于故障复盘。输入包括告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表。输出应包含时间线、影响、根因假设、行动项、未解决证据和后续负责人矩阵。</p>
|
||||
<h3>评审标准</h3>
|
||||
<ol class="rubric"><li>是否处理 governed/运营风险和未解决证据。</li>
|
||||
<li>是否区分假设和已确认根因。</li>
|
||||
<li>是否定义行动项负责人矩阵和回滚/跟进边界。</li>
|
||||
<li>是否要求 file-backed 或 source-backed 证据。</li>
|
||||
<li>是否有针对 blame language 和编造因果的审查门禁。</li></ol>
|
||||
</section>
|
||||
|
||||
<div class="grid" style="margin-top:18px">
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 A</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>Skill 包建议：incident-postmortem</h2>
|
||||
|
||||
<h3>边界</h3>
|
||||
<p>负责根据 source-backed 时间线、Slack 摘要、部署记录、客户影响说明和负责人列表起草 governed 故障复盘。不要用于实时 incident command、最终 RCA 签核、HR/归责分析或面向客户的法律声明。</p>
|
||||
|
||||
<h3>类型</h3>
|
||||
<p>Governed。这个包会影响运营责任归属，如果证据不足，容易制造虚假因果。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>incident-postmortem/
|
||||
SKILL.md
|
||||
agents/interface.yaml
|
||||
references/
|
||||
postmortem-contract.md
|
||||
severity-policy.md
|
||||
blame-free-language.md
|
||||
action-owner-matrix.md
|
||||
evals/
|
||||
output/
|
||||
cases.jsonl
|
||||
fixtures/
|
||||
alert_timeline.json
|
||||
slack_summary.md
|
||||
deploy_notes.md
|
||||
reports/
|
||||
output-risk-profile.md
|
||||
output_quality_scorecard.md
|
||||
trust_report.md
|
||||
review-studio.html</code></pre>
|
||||
|
||||
<h3>SKILL.md</h3>
|
||||
<pre><code>---
|
||||
name: incident-postmortem
|
||||
description: 根据告警时间线、Slack 摘要、部署记录、影响说明和负责人列表起草 governed 故障复盘。用于 source-backed 时间线重建、影响总结、根因假设、行动项、未解决证据和后续负责人矩阵。不要用于实时故障指挥、最终 RCA 审批、归责或法律/客户承诺。
|
||||
---
|
||||
|
||||
# 故障复盘
|
||||
|
||||
## 工作流
|
||||
1. 要求提供 source-backed 故障输入，并把缺失输入列为 `missing evidence`。
|
||||
2. 只根据已提供时间戳建立时间线；如需推断顺序，必须明确标注。
|
||||
3. 分开列出 `confirmed_facts`、`root_cause_hypotheses` 和 `unresolved_evidence`。
|
||||
4. 总结客户影响，但不要编造受影响账户、持续时间或 SLA 违约。
|
||||
5. 创建行动项：包含 owner、due date、验证信号和回滚/跟进边界。
|
||||
6. 使用 `references/blame-free-language.md` 的无责语言。
|
||||
7. 除非 reviewer 明确提供，否则最终 RCA 审批不属于本 skill。
|
||||
|
||||
## 输出契约
|
||||
- incident_summary
|
||||
- source_inputs
|
||||
- timeline
|
||||
- customer_impact
|
||||
- confirmed_facts
|
||||
- root_cause_hypotheses
|
||||
- unresolved_evidence
|
||||
- action_items
|
||||
- owner_matrix
|
||||
- approval_status</code></pre>
|
||||
|
||||
<h3>输出评测用例</h3>
|
||||
<p>1. Slack 和部署记录冲突：必须保留为未解决证据。</p>
|
||||
<p>2. 告警时间线缺恢复时间：不能编造持续时长。</p>
|
||||
<p>3. 用户要求实时故障决策：应路由出去，或说明本 skill 只做复盘。</p>
|
||||
<p>4. 来源材料带有归责语言：输出必须改写为系统/流程语言。</p>
|
||||
<p>5. 缺负责人列表：行动项 owner 字段应为 `missing evidence`。</p>
|
||||
|
||||
<h3>门禁</h3>
|
||||
<ul>
|
||||
<li>时间线和部署记录需要 file-backed fixture 覆盖。</li>
|
||||
<li>输出评测禁止编造因果和隐藏未解决证据。</li>
|
||||
<li>Review Studio 在人工 reviewer 审批行动负责人矩阵前保持 warning。</li>
|
||||
<li>Trust report 应显示无网络和无破坏性操作。</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 B</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>建议 Skill：incident-postmortem</h2>
|
||||
|
||||
<h3>目的</h3>
|
||||
<p>帮助 Codex 根据时间线、Slack 摘要、部署记录、影响说明和负责人列表创建结构化故障复盘。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>incident-postmortem/
|
||||
SKILL.md
|
||||
agents/openai.yaml
|
||||
references/
|
||||
postmortem-template.md
|
||||
severity-policy.md</code></pre>
|
||||
|
||||
<h3>SKILL.md 草稿</h3>
|
||||
<pre><code>---
|
||||
name: incident-postmortem
|
||||
description: 根据告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表创建故障复盘。当用户需要时间线、影响、根因假设、行动项、未解决证据或负责人矩阵时使用。
|
||||
---
|
||||
|
||||
# 故障复盘
|
||||
|
||||
## 工作流
|
||||
1. 收集告警时间线、Slack 摘要、部署记录、客户影响说明和负责人列表。
|
||||
2. 建立按时间排序的时间线。
|
||||
3. 总结客户和系统影响。
|
||||
4. 识别已确认事实和根因假设。
|
||||
5. 在提供负责人和截止时间时，起草行动项。
|
||||
6. 清楚标记未解决证据。
|
||||
7. 避免归责式语言。
|
||||
|
||||
## 输出
|
||||
- 故障摘要
|
||||
- 时间线
|
||||
- 影响
|
||||
- 根因假设
|
||||
- 已确认事实
|
||||
- 未解决证据
|
||||
- 行动项
|
||||
- 负责人矩阵</code></pre>
|
||||
|
||||
<h3>agents/openai.yaml</h3>
|
||||
<pre><code>display_name: 故障复盘
|
||||
short_description: 根据故障证据生成结构化复盘。
|
||||
default_prompt: 请把这些故障证据整理成复盘和负责人矩阵。</code></pre>
|
||||
|
||||
<h3>验证</h3>
|
||||
<p>用证据完整、缺部署记录、Slack 说法冲突和暂时没有根因的 case 测试。确认 skill 会区分事实和假设。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<section class="review-box">
|
||||
<h2>你的判断</h2>
|
||||
<p class="note">只根据评审标准和页面里可见的两个输出做判断。选择会保存到当前浏览器的本地存储里，也可以回到入口页导出。</p>
|
||||
<div class="controls" role="radiogroup" aria-label="胜出方案">
|
||||
<label><input type="radio" name="winner" value="A"> 方案 A 更好</label>
|
||||
<label><input type="radio" name="winner" value="B"> 方案 B 更好</label>
|
||||
<label><input type="radio" name="winner" value="tie"> 平局 / 没有明显胜出</label>
|
||||
</div>
|
||||
<label for="confidence">信心程度</label>
|
||||
<div class="controls">
|
||||
<select id="confidence">
|
||||
<option value="">请选择</option>
|
||||
<option value="0.4">0.4，较弱</option>
|
||||
<option value="0.6">0.6，中等</option>
|
||||
<option value="0.8">0.8，较强</option>
|
||||
<option value="1.0">1.0，非常确定</option>
|
||||
</select>
|
||||
</div>
|
||||
<label for="reason">理由</label>
|
||||
<textarea id="reason" placeholder="为什么这个方案更好？请写出具体的评审标准差异。"></textarea>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="saveDecision()">保存判断</button>
|
||||
<button type="button" onclick="clearDecision()">清空</button>
|
||||
</div>
|
||||
<p id="save-status" class="small note"></p>
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseId = document.body.dataset.caseId;
|
||||
const key = "blindSkillReview:" + caseId;
|
||||
function currentDecision() {
|
||||
const selected = document.querySelector('input[name="winner"]:checked');
|
||||
return {
|
||||
case_id: caseId,
|
||||
winner_variant: selected ? selected.value : "",
|
||||
confidence: document.getElementById("confidence").value,
|
||||
reason: document.getElementById("reason").value.trim(),
|
||||
reviewed_at: new Date().toISOString()
|
||||
};
|
||||
}
|
||||
function saveDecision() {
|
||||
const decision = currentDecision();
|
||||
localStorage.setItem(key, JSON.stringify(decision));
|
||||
document.getElementById("save-status").textContent = "已保存：" + decision.reviewed_at;
|
||||
}
|
||||
function clearDecision() {
|
||||
localStorage.removeItem(key);
|
||||
document.querySelectorAll('input[name="winner"]').forEach(el => el.checked = false);
|
||||
document.getElementById("confidence").value = "";
|
||||
document.getElementById("reason").value = "";
|
||||
document.getElementById("save-status").textContent = "已清空。";
|
||||
}
|
||||
function loadDecision() {
|
||||
const raw = localStorage.getItem(key);
|
||||
if (!raw) return;
|
||||
const decision = JSON.parse(raw);
|
||||
const selected = document.querySelector('input[name="winner"][value="' + decision.winner_variant + '"]');
|
||||
if (selected) selected.checked = true;
|
||||
document.getElementById("confidence").value = decision.confidence || "";
|
||||
document.getElementById("reason").value = decision.reason || "";
|
||||
document.getElementById("save-status").textContent = "已加载保存过的判断。";
|
||||
}
|
||||
loadDecision();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,344 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>PR Review 跟进 Skill - Skill 盲测评审</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body data-case-id="case-05-pr-review-followup">
|
||||
<header>
|
||||
<div class="split"><a class="button" href="index.html">返回入口</a><a class="button" href="case-04-incident-postmortem.html">上一个</a></div>
|
||||
<h1>PR Review 跟进 Skill</h1>
|
||||
<p class="meta">A/B 盲测评审。记录完判断前，不要打开答案钥匙。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>场景</h2>
|
||||
<p>一个小工程团队经常收到 GitHub PR review comments，希望 Codex 能把评论转成补丁、回复摘要和验证记录。</p>
|
||||
<h3>用户请求</h3>
|
||||
<p>请设计一个用于处理 PR review comments 的可复用 skill。输入包括 review comments、变更文件、失败 CI 说明和 maintainer preferences。输出需要分组评论、只修改相关文件、写回复说明并运行验证。必须避免回滚无关的用户改动。</p>
|
||||
<h3>评审标准</h3>
|
||||
<ol class="rubric"><li>是否理解 code-review 跟进和 dirty worktree 安全。</li>
|
||||
<li>是否定义评论分组、补丁、回复和验证工作流。</li>
|
||||
<li>是否避免过度重构和无关 revert。</li>
|
||||
<li>是否说明变更后需要的命令和证据。</li>
|
||||
<li>是否定义一般 code review 与评论跟进的触发排除。</li></ol>
|
||||
</section>
|
||||
|
||||
<div class="grid" style="margin-top:18px">
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 A</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>建议 Skill：pr-review-followup</h2>
|
||||
|
||||
<h3>目的</h3>
|
||||
<p>创建一个 skill，帮助 Codex 安全处理 PR review comments，并总结回复。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>pr-review-followup/
|
||||
SKILL.md
|
||||
agents/openai.yaml
|
||||
references/
|
||||
response-style.md</code></pre>
|
||||
|
||||
<h3>SKILL.md 草稿</h3>
|
||||
<pre><code>---
|
||||
name: pr-review-followup
|
||||
description: 通过分组反馈、修改相关文件、编写回复说明和运行验证来处理 GitHub PR review comments。当用户提供 review comments、变更文件、CI 说明或 maintainer preferences 时使用。
|
||||
---
|
||||
|
||||
# PR Review 跟进
|
||||
|
||||
## 工作流
|
||||
1. 阅读所有 review comments，并按文件、主题和严重程度分组。
|
||||
2. 编辑前检查受影响文件。
|
||||
3. 只修改处理 comments 所需的文件。
|
||||
4. 不要回滚无关用户改动。
|
||||
5. 运行相关测试或 CI 复现命令。
|
||||
6. 总结变更，并为 reviewer 起草回复说明。
|
||||
|
||||
## 输出
|
||||
- 评论分组
|
||||
- 修改文件
|
||||
- 验证命令
|
||||
- Reviewer 回复说明
|
||||
- 剩余问题</code></pre>
|
||||
|
||||
<h3>agents/openai.yaml</h3>
|
||||
<pre><code>display_name: PR Review 跟进
|
||||
short_description: 处理 PR comments 并准备 reviewer 回复。
|
||||
default_prompt: 请处理这些 PR review comments，并总结验证结果。</code></pre>
|
||||
|
||||
<h3>验证</h3>
|
||||
<p>用需要代码修改、文档修改、无需修改只需解释、以及 reviewer 要求冲突的 comments 测试。</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
<section class="variant">
|
||||
<div class="variant-head">
|
||||
<h2>方案 B</h2>
|
||||
<span class="badge">来源已隐藏</span>
|
||||
</div>
|
||||
<div class="variant-body">
|
||||
<h2>Skill 包建议：pr-review-followup</h2>
|
||||
|
||||
<h3>边界</h3>
|
||||
<p>负责 PR 已经有明确 reviewer comments、变更文件或 CI 说明之后的评论跟进。排除首次 code review、大范围重构、issue triage，以及没有绑定评论的推测性清理。</p>
|
||||
|
||||
<h3>包结构</h3>
|
||||
<pre><code>pr-review-followup/
|
||||
SKILL.md
|
||||
agents/interface.yaml
|
||||
references/
|
||||
response-style.md
|
||||
dirty-worktree-safety.md
|
||||
verification-policy.md
|
||||
evals/
|
||||
trigger_cases.json
|
||||
output/
|
||||
cases.jsonl
|
||||
reports/
|
||||
output-risk-profile.md
|
||||
output_quality_scorecard.md</code></pre>
|
||||
|
||||
<h3>SKILL.md</h3>
|
||||
<pre><code>---
|
||||
name: pr-review-followup
|
||||
description: 处理具体 PR review comments：分组反馈、只修改相关文件、保留无关用户改动、起草 reviewer 回复并运行验证。当提供 review comments、变更文件、失败 CI 说明或 maintainer preferences 时使用。不要用于首次 code review、大范围重构、issue triage 或无关清理。
|
||||
---
|
||||
|
||||
# PR Review 跟进
|
||||
|
||||
## 工作流
|
||||
1. 编辑前记录 git status，并识别用户已经改动的文件。
|
||||
2. 按文件、行为、严重程度，以及是否需要代码、测试、文档或仅解释来分组 review comments。
|
||||
3. 修改前阅读受影响代码和附近测试。
|
||||
4. 只修改与评论绑定的文件。不要回滚无关改动，也不要格式化未触碰文件。
|
||||
5. 运行有针对性的验证，并记录命令和结果。
|
||||
6. 起草 reviewer 回复说明，把每组评论映射到变更、无需修改的理由或剩余问题。
|
||||
7. 如果评论冲突，停止并询问哪个 reviewer 指令优先。
|
||||
|
||||
## 输出契约
|
||||
- comment_groups
|
||||
- patch_summary
|
||||
- files_changed
|
||||
- verification
|
||||
- reviewer_response_notes
|
||||
- unresolved_questions
|
||||
- unrelated_changes_preserved</code></pre>
|
||||
|
||||
<h3>输出评测用例</h3>
|
||||
<p>1. 评论要求添加特定 null check：输出必须只修改受影响函数，并提到测试。</p>
|
||||
<p>2. Reviewer 要求与 PR 范围无关的大重构：输出应标出范围风险。</p>
|
||||
<p>3. Dirty worktree 中有无关用户文件：输出必须保留它。</p>
|
||||
<p>4. 两个 reviewer comments 冲突：输出必须询问优先级，而不是猜。</p>
|
||||
<p>5. 近邻请求：“从零 review 这个 PR”不应触发 follow-up mode。</p>
|
||||
|
||||
<h3>门禁</h3>
|
||||
<ul>
|
||||
<li>触发评测必须区分首次 review 和评论跟进。</li>
|
||||
<li>如果回滚或隐藏无关改动，输出评测必须失败。</li>
|
||||
<li>验证策略必须记录跳过测试的原因。</li>
|
||||
<li>回复说明必须能追溯到评论分组。</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<section class="review-box">
|
||||
<h2>你的判断</h2>
|
||||
<p class="note">只根据评审标准和页面里可见的两个输出做判断。选择会保存到当前浏览器的本地存储里，也可以回到入口页导出。</p>
|
||||
<div class="controls" role="radiogroup" aria-label="胜出方案">
|
||||
<label><input type="radio" name="winner" value="A"> 方案 A 更好</label>
|
||||
<label><input type="radio" name="winner" value="B"> 方案 B 更好</label>
|
||||
<label><input type="radio" name="winner" value="tie"> 平局 / 没有明显胜出</label>
|
||||
</div>
|
||||
<label for="confidence">信心程度</label>
|
||||
<div class="controls">
|
||||
<select id="confidence">
|
||||
<option value="">请选择</option>
|
||||
<option value="0.4">0.4，较弱</option>
|
||||
<option value="0.6">0.6，中等</option>
|
||||
<option value="0.8">0.8，较强</option>
|
||||
<option value="1.0">1.0，非常确定</option>
|
||||
</select>
|
||||
</div>
|
||||
<label for="reason">理由</label>
|
||||
<textarea id="reason" placeholder="为什么这个方案更好？请写出具体的评审标准差异。"></textarea>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="saveDecision()">保存判断</button>
|
||||
<button type="button" onclick="clearDecision()">清空</button>
|
||||
</div>
|
||||
<p id="save-status" class="small note"></p>
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseId = document.body.dataset.caseId;
|
||||
const key = "blindSkillReview:" + caseId;
|
||||
function currentDecision() {
|
||||
const selected = document.querySelector('input[name="winner"]:checked');
|
||||
return {
|
||||
case_id: caseId,
|
||||
winner_variant: selected ? selected.value : "",
|
||||
confidence: document.getElementById("confidence").value,
|
||||
reason: document.getElementById("reason").value.trim(),
|
||||
reviewed_at: new Date().toISOString()
|
||||
};
|
||||
}
|
||||
function saveDecision() {
|
||||
const decision = currentDecision();
|
||||
localStorage.setItem(key, JSON.stringify(decision));
|
||||
document.getElementById("save-status").textContent = "已保存：" + decision.reviewed_at;
|
||||
}
|
||||
function clearDecision() {
|
||||
localStorage.removeItem(key);
|
||||
document.querySelectorAll('input[name="winner"]').forEach(el => el.checked = false);
|
||||
document.getElementById("confidence").value = "";
|
||||
document.getElementById("reason").value = "";
|
||||
document.getElementById("save-status").textContent = "已清空。";
|
||||
}
|
||||
function loadDecision() {
|
||||
const raw = localStorage.getItem(key);
|
||||
if (!raw) return;
|
||||
const decision = JSON.parse(raw);
|
||||
const selected = document.querySelector('input[name="winner"][value="' + decision.winner_variant + '"]');
|
||||
if (selected) selected.checked = true;
|
||||
document.getElementById("confidence").value = decision.confidence || "";
|
||||
document.getElementById("reason").value = decision.reason || "";
|
||||
document.getElementById("save-status").textContent = "已加载保存过的判断。";
|
||||
}
|
||||
loadDecision();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,220 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>人工盲测评审包 - Meta Skill 对比</title>
|
||||
<style>
|
||||
:root {
|
||||
color-scheme: light;
|
||||
--bg: #f7f8fb;
|
||||
--panel: #ffffff;
|
||||
--ink: #20242c;
|
||||
--muted: #687082;
|
||||
--line: #d9deea;
|
||||
--accent: #2563eb;
|
||||
--accent-2: #0f766e;
|
||||
--warn: #b45309;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0;
|
||||
font-family: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
background: var(--bg);
|
||||
color: var(--ink);
|
||||
line-height: 1.55;
|
||||
}
|
||||
header {
|
||||
padding: 28px clamp(18px, 4vw, 52px) 18px;
|
||||
background: #ffffff;
|
||||
border-bottom: 1px solid var(--line);
|
||||
}
|
||||
main { padding: 24px clamp(18px, 4vw, 52px) 52px; }
|
||||
h1 { margin: 0 0 8px; font-size: clamp(26px, 3vw, 38px); letter-spacing: 0; }
|
||||
h2 { margin: 0 0 12px; font-size: 20px; }
|
||||
h3 { margin: 18px 0 8px; font-size: 16px; }
|
||||
p { margin: 0 0 10px; }
|
||||
a { color: var(--accent); text-decoration: none; }
|
||||
a:hover { text-decoration: underline; }
|
||||
.meta, .note { color: var(--muted); }
|
||||
.grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 18px; align-items: start; }
|
||||
.card, .panel {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 18px;
|
||||
}
|
||||
.case-list { display: grid; gap: 12px; margin-top: 18px; }
|
||||
.case-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr auto;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 14px 16px;
|
||||
}
|
||||
.badge {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 28px;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: #e8f0ff;
|
||||
color: #1d4ed8;
|
||||
font-size: 13px;
|
||||
font-weight: 650;
|
||||
}
|
||||
.rubric { margin: 0; padding-left: 20px; }
|
||||
.rubric li { margin-bottom: 6px; }
|
||||
.variant {
|
||||
background: var(--panel);
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
.variant-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
align-items: center;
|
||||
padding: 12px 16px;
|
||||
border-bottom: 1px solid var(--line);
|
||||
background: #f2f5fa;
|
||||
}
|
||||
.variant-body { padding: 16px; }
|
||||
pre {
|
||||
overflow: auto;
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #111827;
|
||||
color: #f9fafb;
|
||||
font-size: 13px;
|
||||
}
|
||||
code { font-family: "SFMono-Regular", Consolas, monospace; }
|
||||
.review-box {
|
||||
margin-top: 18px;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 8px;
|
||||
padding: 16px;
|
||||
background: #fff;
|
||||
}
|
||||
.controls { display: flex; flex-wrap: wrap; gap: 10px; margin: 12px 0; }
|
||||
button, .button {
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
color: var(--ink);
|
||||
min-height: 36px;
|
||||
padding: 7px 12px;
|
||||
cursor: pointer;
|
||||
font-weight: 650;
|
||||
}
|
||||
button.primary, .button.primary { background: var(--accent); border-color: var(--accent); color: #fff; }
|
||||
textarea {
|
||||
width: 100%;
|
||||
min-height: 96px;
|
||||
resize: vertical;
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
font: inherit;
|
||||
}
|
||||
.warn { color: var(--warn); font-weight: 650; }
|
||||
.split { display: flex; flex-wrap: wrap; gap: 10px; }
|
||||
.small { font-size: 13px; }
|
||||
@media (max-width: 900px) {
|
||||
.grid { grid-template-columns: 1fr; }
|
||||
.case-row { grid-template-columns: 1fr; }
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<header>
|
||||
<h1>人工盲测评审包</h1>
|
||||
<p class="meta">5 个真实常见的 skill 创建场景。打开答案钥匙前，方案来源都会保持隐藏。</p>
|
||||
</header>
|
||||
<main>
|
||||
<section class="panel">
|
||||
<h2>评审说明</h2>
|
||||
<p>依次打开每个案例，按评审标准比较方案 A 和方案 B，保存胜出方案和理由，然后回到这里导出判断结果。5 个判断全部保存前，不要打开 <code>DO_NOT_OPEN_answer_key.html</code> 或 <code>DO_NOT_OPEN_answer_key.json</code>。</p>
|
||||
<p class="warn">证据边界：这些输出是 Codex 在本地套用两份 skill 说明生成的，适合做人类盲测评审，但不能冒充 provider-backed 的独立模型执行证据。</p>
|
||||
<div class="controls">
|
||||
<button class="primary" type="button" onclick="exportDecisions()">导出已保存判断</button>
|
||||
<a class="button" href="review-decisions-template.json">判断模板</a>
|
||||
<a class="button" href="blind-pack.json">盲测包 JSON</a>
|
||||
</div>
|
||||
<textarea id="export" placeholder="导出的判断结果会显示在这里。"></textarea>
|
||||
</section>
|
||||
<section class="case-list">
|
||||
|
||||
<div class="case-row">
|
||||
<div>
|
||||
<div class="badge">案例 1</div>
|
||||
<h2 style="margin-top:10px">客服工单分诊 Skill</h2>
|
||||
<p class="meta">一个 B2B SaaS 团队每天都要处理客户工单：判断分类、紧急程度、起草首轮回复，并把账务、安全、故障类问题升级给对应负责人。他们希望把这个重复流程做成一个给支持团队使用的 Codex skill。</p>
|
||||
</div>
|
||||
<a class="button primary" href="case-01-support-triage.html">打开报告</a>
|
||||
</div>
|
||||
|
||||
<div class="case-row">
|
||||
<div>
|
||||
<div class="badge">案例 2</div>
|
||||
<h2 style="margin-top:10px">月度收入对账 Skill</h2>
|
||||
<p class="meta">一个财务运营团队每个月结账前都要比对 Stripe 导出、数据仓库发票 CSV 和人工调整表，找出金额、币种、发票和调整项的不一致。</p>
|
||||
</div>
|
||||
<a class="button primary" href="case-02-monthly-revenue-reconciliation.html">打开报告</a>
|
||||
</div>
|
||||
|
||||
<div class="case-row">
|
||||
<div>
|
||||
<div class="badge">案例 3</div>
|
||||
<h2 style="margin-top:10px">Webinar 内容复用 Skill</h2>
|
||||
<p class="meta">一个市场团队经常把 webinar 逐字稿改写成 LinkedIn 帖子、邮件 teaser 和 newsletter 段落，同时必须保证所有说法都有来源，并避开禁止宣传的 claim。</p>
|
||||
</div>
|
||||
<a class="button primary" href="case-03-webinar-repurposing.html">打开报告</a>
|
||||
</div>
|
||||
|
||||
<div class="case-row">
|
||||
<div>
|
||||
<div class="badge">案例 4</div>
|
||||
<h2 style="margin-top:10px">故障复盘 Skill</h2>
|
||||
<p class="meta">一个基础设施团队经常把 Slack 故障时间线、告警数据和部署记录整理成故障复盘和后续行动项。</p>
|
||||
</div>
|
||||
<a class="button primary" href="case-04-incident-postmortem.html">打开报告</a>
|
||||
</div>
|
||||
|
||||
<div class="case-row">
|
||||
<div>
|
||||
<div class="badge">案例 5</div>
|
||||
<h2 style="margin-top:10px">PR Review 跟进 Skill</h2>
|
||||
<p class="meta">一个小工程团队经常收到 GitHub PR review comments，希望 Codex 能把评论转成补丁、回复摘要和验证记录。</p>
|
||||
</div>
|
||||
<a class="button primary" href="case-05-pr-review-followup.html">打开报告</a>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
</main>
|
||||
<script>
|
||||
const caseIds = ["case-01-support-triage", "case-02-monthly-revenue-reconciliation", "case-03-webinar-repurposing", "case-04-incident-postmortem", "case-05-pr-review-followup"];
|
||||
function exportDecisions() {
|
||||
const decisions = caseIds.map(id => {
|
||||
const raw = localStorage.getItem("blindSkillReview:" + id);
|
||||
return raw ? JSON.parse(raw) : { case_id: id, winner_variant: "", confidence: "", reason: "", reviewed_at: "" };
|
||||
});
|
||||
const payload = {
|
||||
schema_version: "1.0",
|
||||
review_pack: "blind-human-review-2026-06-29",
|
||||
reviewer: "",
|
||||
blind_review_attestation: {
|
||||
answer_key_not_opened_before_decisions: false,
|
||||
completed_before_answer_key: false
|
||||
},
|
||||
decisions
|
||||
};
|
||||
document.getElementById("export").value = JSON.stringify(payload, null, 2);
|
||||
}
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"review_pack": "blind-human-review-2026-06-29",
|
||||
"reviewer": "",
|
||||
"reviewed_at": "",
|
||||
"blind_review_attestation": {
|
||||
"answer_key_not_opened_before_decisions": false,
|
||||
"completed_before_answer_key": false
|
||||
},
|
||||
"decisions": [
|
||||
{
|
||||
"case_id": "case-01-support-triage",
|
||||
"winner_variant": "",
|
||||
"confidence": "",
|
||||
"reason": ""
|
||||
},
|
||||
{
|
||||
"case_id": "case-02-monthly-revenue-reconciliation",
|
||||
"winner_variant": "",
|
||||
"confidence": "",
|
||||
"reason": ""
|
||||
},
|
||||
{
|
||||
"case_id": "case-03-webinar-repurposing",
|
||||
"winner_variant": "",
|
||||
"confidence": "",
|
||||
"reason": ""
|
||||
},
|
||||
{
|
||||
"case_id": "case-04-incident-postmortem",
|
||||
"winner_variant": "",
|
||||
"confidence": "",
|
||||
"reason": ""
|
||||
},
|
||||
{
|
||||
"case_id": "case-05-pr-review-followup",
|
||||
"winner_variant": "",
|
||||
"confidence": "",
|
||||
"reason": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"review_pack": "blind-human-review-2026-06-29",
|
||||
"reviewer": "single human reviewer",
|
||||
"reviewed_at": "2026-06-29T03:01:03.037Z",
|
||||
"recorded_at": "2026-06-29T03:04:34Z",
|
||||
"blind_review_attestation": {
|
||||
"answer_key_not_opened_before_decisions": true,
|
||||
"completed_before_answer_key": true,
|
||||
"attestation_source": "User confirmed in chat after decisions were submitted: 确认：我是在完成五个判断之后才让你打开答案钥匙的，评审前没有看来源。以上 5 个判断都是揭晓来源前完成的。"
|
||||
},
|
||||
"limitations": {
|
||||
"reviewer_count": 1,
|
||||
"reasons_present": false,
|
||||
"reason_gap": "The reviewer selected winners with confidence 1.0, but per-case rationale fields were left empty.",
|
||||
"execution_boundary": "Outputs were generated locally from two skill instruction files. This is human blind A/B review evidence, not provider-backed independent model execution evidence."
|
||||
},
|
||||
"decisions": [
|
||||
{
|
||||
"case_id": "case-01-support-triage",
|
||||
"winner_variant": "B",
|
||||
"confidence": "1.0",
|
||||
"reason": "",
|
||||
"reviewed_at": "2026-06-29T03:00:00.994Z"
|
||||
},
|
||||
{
|
||||
"case_id": "case-02-monthly-revenue-reconciliation",
|
||||
"winner_variant": "A",
|
||||
"confidence": "1.0",
|
||||
"reason": "",
|
||||
"reviewed_at": "2026-06-29T03:00:18.277Z"
|
||||
},
|
||||
{
|
||||
"case_id": "case-03-webinar-repurposing",
|
||||
"winner_variant": "B",
|
||||
"confidence": "1.0",
|
||||
"reason": "",
|
||||
"reviewed_at": "2026-06-29T03:00:34.343Z"
|
||||
},
|
||||
{
|
||||
"case_id": "case-04-incident-postmortem",
|
||||
"winner_variant": "A",
|
||||
"confidence": "1.0",
|
||||
"reason": "",
|
||||
"reviewed_at": "2026-06-29T03:00:49.160Z"
|
||||
},
|
||||
{
|
||||
"case_id": "case-05-pr-review-followup",
|
||||
"winner_variant": "B",
|
||||
"confidence": "1.0",
|
||||
"reason": "",
|
||||
"reviewed_at": "2026-06-29T03:01:03.037Z"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -3,9 +3,9 @@
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"winner_label": "Current",
|
||||
"winner_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"winner_tokens": 53,
|
||||
"current_tokens": 53,
|
||||
"winner_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"winner_tokens": 54,
|
||||
"current_tokens": 54,
|
||||
"winner_holdout_fp": 0,
|
||||
"winner_holdout_fn": 0,
|
||||
"current_holdout_fp": 0,
|
||||
@@ -36,44 +36,44 @@
|
||||
"calibration": {
|
||||
"holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.908,
|
||||
"mean_non_trigger_score": 0.003,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.767,
|
||||
"max_non_trigger_score": 0.023,
|
||||
"score_gap": 0.744,
|
||||
"threshold_margin": 0.307,
|
||||
"positive_threshold_buffer": 0.437,
|
||||
"negative_threshold_buffer": 0.307,
|
||||
"mean_positive_score": 0.704,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 0.465,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 0.465,
|
||||
"threshold_margin": 0.135,
|
||||
"positive_threshold_buffer": 0.135,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
"risk_band": "healthy"
|
||||
},
|
||||
"blind_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.669,
|
||||
"mean_non_trigger_score": 0.116,
|
||||
"mean_near_neighbor_score": 0.152,
|
||||
"min_positive_score": 0.665,
|
||||
"max_non_trigger_score": 0.305,
|
||||
"score_gap": 0.36,
|
||||
"threshold_margin": 0.025,
|
||||
"positive_threshold_buffer": 0.335,
|
||||
"negative_threshold_buffer": 0.025,
|
||||
"boundary_case_count": 1,
|
||||
"boundary_case_rate": 0.167,
|
||||
"risk_band": "tight"
|
||||
"mean_positive_score": 0.377,
|
||||
"mean_non_trigger_score": 0.024,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.374,
|
||||
"max_non_trigger_score": 0.084,
|
||||
"score_gap": 0.29,
|
||||
"threshold_margin": 0.044,
|
||||
"positive_threshold_buffer": 0.044,
|
||||
"negative_threshold_buffer": 0.246,
|
||||
"boundary_case_count": 2,
|
||||
"boundary_case_rate": 0.333,
|
||||
"risk_band": "watch"
|
||||
},
|
||||
"adversarial_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 1.0,
|
||||
"mean_positive_score": 0.81,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 1.0,
|
||||
"min_positive_score": 0.808,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 1.0,
|
||||
"score_gap": 0.808,
|
||||
"threshold_margin": 0.33,
|
||||
"positive_threshold_buffer": 0.67,
|
||||
"positive_threshold_buffer": 0.478,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
@@ -164,7 +164,7 @@
|
||||
"route_metrics": {
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.701,
|
||||
"average_margin": 0.644,
|
||||
"misroute_count": 0,
|
||||
"ambiguous_case_count": 0
|
||||
}
|
||||
@@ -187,8 +187,8 @@
|
||||
"label": "Current",
|
||||
"ranking_state": "selected_by_dev",
|
||||
"promotion_state": "kept_current",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"tokens": 53,
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"tokens": 54,
|
||||
"dev_errors": 0,
|
||||
"holdout_errors": 0,
|
||||
"reason_tags": []
|
||||
@@ -696,7 +696,7 @@
|
||||
"route_metrics": {
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.586,
|
||||
"average_margin": 0.709,
|
||||
"misroute_count": 0,
|
||||
"ambiguous_case_count": 0
|
||||
}
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
| Target | Role | Label | Ranking State | Promotion State | Tokens | Dev Errors | Holdout Errors | Reason Tags |
|
||||
| --- | --- | --- | --- | --- | ---: | ---: | ---: | --- |
|
||||
| `yao-meta-skill` | baseline | `Baseline` | reference | reference | 8 | 1 | 0 | - |
|
||||
| `yao-meta-skill` | current | `Current` | selected_by_dev | kept_current | 53 | 0 | 0 | - |
|
||||
| `yao-meta-skill` | current | `Current` | selected_by_dev | kept_current | 54 | 0 | 0 | - |
|
||||
| `yao-meta-skill` | candidate | `Minimal` | not_selected | blocked | 41 | 2 | 0 | weaker_dev_fit |
|
||||
| `yao-meta-skill` | candidate | `Guardrail` | not_selected | blocked | 56 | 2 | 0 | weaker_dev_fit, longer_without_gain |
|
||||
| `yao-meta-skill` | candidate | `Balanced` | not_selected | blocked | 60 | 2 | 0 | weaker_dev_fit, longer_without_gain |
|
||||
|
||||
+176
-146
File diff suppressed because it is too large
Load Diff
+14
-14
@@ -5,17 +5,17 @@
|
||||
"stats": {
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 805,
|
||||
"other_text_tokens": 1156781,
|
||||
"estimated_initial_load_tokens": 998,
|
||||
"estimated_total_text_tokens": 1157586,
|
||||
"deferred_resource_tokens": 525864,
|
||||
"skill_body_tokens": 794,
|
||||
"other_text_tokens": 1200569,
|
||||
"estimated_initial_load_tokens": 987,
|
||||
"estimated_total_text_tokens": 1201363,
|
||||
"deferred_resource_tokens": 531767,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 464561,
|
||||
"file_count": 153
|
||||
"estimated_tokens": 469568,
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "references",
|
||||
@@ -24,7 +24,7 @@
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
"estimated_tokens": 21835,
|
||||
"estimated_tokens": 22731,
|
||||
"file_count": 27
|
||||
},
|
||||
{
|
||||
@@ -36,8 +36,8 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 464561,
|
||||
"file_count": 153
|
||||
"estimated_tokens": 469568,
|
||||
"file_count": 155
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -59,16 +59,16 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 464561,
|
||||
"file_count": 153,
|
||||
"estimated_tokens": 469568,
|
||||
"file_count": 155,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
"summary": "Large deferred resources are indexed and backed by evidence."
|
||||
},
|
||||
"relevant_file_count": 712,
|
||||
"relevant_file_count": 591,
|
||||
"unused_resource_dirs": [],
|
||||
"quality_signal_points": 140,
|
||||
"quality_density": 140.3
|
||||
"quality_density": 141.8
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
|
||||
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
|
||||
| root | `.` | `production` | 1000 | 998 | 805 | 525864 | `governed` | scripts:464561 | 140.3 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 987 | 794 | 531767 | `governed` | scripts:469568 | 141.8 | - | ok |
|
||||
| complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok |
|
||||
| governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok |
|
||||
|
||||
|
||||
@@ -6,14 +6,14 @@
|
||||
"path": ".",
|
||||
"budget_tier": "production",
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 998,
|
||||
"skill_body_tokens": 805,
|
||||
"deferred_resource_tokens": 525864,
|
||||
"initial_tokens": 987,
|
||||
"skill_body_tokens": 794,
|
||||
"deferred_resource_tokens": 531767,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 464561,
|
||||
"file_count": 153
|
||||
"estimated_tokens": 469568,
|
||||
"file_count": 155
|
||||
}
|
||||
],
|
||||
"deferred_resource_governance": {
|
||||
@@ -35,14 +35,14 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 464561,
|
||||
"file_count": 153,
|
||||
"estimated_tokens": 469568,
|
||||
"file_count": 155,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
],
|
||||
"summary": "Large deferred resources are indexed and backed by evidence."
|
||||
},
|
||||
"quality_density": 140.3,
|
||||
"quality_density": 141.8,
|
||||
"unused_resource_dirs": [],
|
||||
"ok": true,
|
||||
"warnings": []
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -2,19 +2,19 @@
|
||||
|
||||
Winner: `Current`
|
||||
|
||||
- current tokens: `53`
|
||||
- winner tokens: `53`
|
||||
- current tokens: `54`
|
||||
- winner tokens: `54`
|
||||
- baseline tokens: `8`
|
||||
|
||||
## Winner
|
||||
|
||||
Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
|
||||
## Candidate Ranking
|
||||
|
||||
| Candidate | Tokens | Dev FP | Dev FN | Dev Near | Holdout FP | Holdout FN |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: | ---: |
|
||||
| `Current` | 53 | 0 | 0 | 1.0 | 0 | 0 |
|
||||
| `Current` | 54 | 0 | 0 | 1.0 | 0 | 0 |
|
||||
| `Minimal` | 41 | 1 | 1 | 1.0 | 0 | 0 |
|
||||
| `Guardrail` | 56 | 1 | 1 | 1.0 | 0 | 0 |
|
||||
| `Balanced` | 60 | 1 | 1 | 1.0 | 0 | 0 |
|
||||
@@ -34,9 +34,9 @@ Create, refactor, evaluate, and package agent skills from workflows, prompts, tr
|
||||
|
||||
| Gate | Winner Gap | Winner Risk | Winner Boundary Rate | Current Gap | Baseline Gap |
|
||||
| --- | ---: | --- | ---: | ---: | ---: |
|
||||
| Holdout | 0.744 | healthy | 0.0 | 0.744 | 0.416 |
|
||||
| Blind Holdout | 0.36 | tight | 0.167 | 0.36 | 0.368 |
|
||||
| Adversarial Holdout | 1.0 | healthy | 0.0 | 1.0 | 0.845 |
|
||||
| Holdout | 0.465 | healthy | 0.0 | 0.465 | 0.416 |
|
||||
| Blind Holdout | 0.29 | watch | 0.333 | 0.29 | 0.368 |
|
||||
| Adversarial Holdout | 0.808 | healthy | 0.0 | 0.808 | 0.845 |
|
||||
|
||||
## Judge Blind Summary
|
||||
|
||||
|
||||
@@ -3,9 +3,9 @@
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"winner_label": "Current",
|
||||
"winner_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"winner_tokens": 53,
|
||||
"current_tokens": 53,
|
||||
"winner_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"winner_tokens": 54,
|
||||
"current_tokens": 54,
|
||||
"winner_holdout_fp": 0,
|
||||
"winner_holdout_fn": 0,
|
||||
"current_holdout_fp": 0,
|
||||
@@ -36,44 +36,44 @@
|
||||
"calibration": {
|
||||
"holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.908,
|
||||
"mean_non_trigger_score": 0.003,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.767,
|
||||
"max_non_trigger_score": 0.023,
|
||||
"score_gap": 0.744,
|
||||
"threshold_margin": 0.307,
|
||||
"positive_threshold_buffer": 0.437,
|
||||
"negative_threshold_buffer": 0.307,
|
||||
"mean_positive_score": 0.704,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 0.465,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 0.465,
|
||||
"threshold_margin": 0.135,
|
||||
"positive_threshold_buffer": 0.135,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
"risk_band": "healthy"
|
||||
},
|
||||
"blind_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.669,
|
||||
"mean_non_trigger_score": 0.116,
|
||||
"mean_near_neighbor_score": 0.152,
|
||||
"min_positive_score": 0.665,
|
||||
"max_non_trigger_score": 0.305,
|
||||
"score_gap": 0.36,
|
||||
"threshold_margin": 0.025,
|
||||
"positive_threshold_buffer": 0.335,
|
||||
"negative_threshold_buffer": 0.025,
|
||||
"boundary_case_count": 1,
|
||||
"boundary_case_rate": 0.167,
|
||||
"risk_band": "tight"
|
||||
"mean_positive_score": 0.377,
|
||||
"mean_non_trigger_score": 0.024,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.374,
|
||||
"max_non_trigger_score": 0.084,
|
||||
"score_gap": 0.29,
|
||||
"threshold_margin": 0.044,
|
||||
"positive_threshold_buffer": 0.044,
|
||||
"negative_threshold_buffer": 0.246,
|
||||
"boundary_case_count": 2,
|
||||
"boundary_case_rate": 0.333,
|
||||
"risk_band": "watch"
|
||||
},
|
||||
"adversarial_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 1.0,
|
||||
"mean_positive_score": 0.81,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 1.0,
|
||||
"min_positive_score": 0.808,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 1.0,
|
||||
"score_gap": 0.808,
|
||||
"threshold_margin": 0.33,
|
||||
"positive_threshold_buffer": 0.67,
|
||||
"positive_threshold_buffer": 0.478,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Winner | Winner Tokens | Holdout FP | Holdout FN | Blind FP | Blind FN | Judge Blind Errors | Adv FP | Adv FN | Adv Gap | Adv Risk | Status |
|
||||
| --- | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | --- | --- |
|
||||
| `yao-meta-skill` | `Current` | 53 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1.0 | healthy | ok |
|
||||
| `yao-meta-skill` | `Current` | 54 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.808 | healthy | ok |
|
||||
| `team-frontend-review` | `Current` | 50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.509 | healthy | ok |
|
||||
| `governed-incident-command` | `Current` | 37 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.538 | watch | ok |
|
||||
|
||||
|
||||
+328
-297
File diff suppressed because it is too large
Load Diff
+152
-154
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-07-02",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"check_count": 39,
|
||||
@@ -324,12 +324,12 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 998/1000; deferred 525864/120000; top deferred scripts 464561; resource governance governed; quality density 140.3",
|
||||
"detail": "initial load 987/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 141.8",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"actual": {
|
||||
"status": "pass",
|
||||
"detail": "initial load 998/1000; deferred 525864/120000; top deferred scripts 464561; resource governance governed; quality density 140.3",
|
||||
"detail": "initial load 987/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 141.8",
|
||||
"evidence": "reports/context_budget.json"
|
||||
},
|
||||
"paths": [
|
||||
@@ -342,8 +342,8 @@
|
||||
"key": "benchmark-release-lock-self-consistency",
|
||||
"label": "Benchmark release lock matches source dirty state",
|
||||
"status": "pass",
|
||||
"expected": true,
|
||||
"actual": true,
|
||||
"expected": false,
|
||||
"actual": false,
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
],
|
||||
@@ -357,7 +357,7 @@
|
||||
"actual": {
|
||||
"available": true,
|
||||
"clean": false,
|
||||
"changed_file_count": 27
|
||||
"changed_file_count": 39
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json"
|
||||
@@ -398,8 +398,8 @@
|
||||
"key": "overview-benchmark-commit",
|
||||
"label": "overview embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"actual": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"expected": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"actual": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-overview.json"
|
||||
@@ -411,36 +411,36 @@
|
||||
"label": "overview embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -454,13 +454,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -468,13 +468,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -497,8 +497,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -509,8 +509,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -530,7 +530,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11
|
||||
"source_pass_count": 12
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -538,7 +538,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11
|
||||
"source_pass_count": 12
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -550,8 +550,8 @@
|
||||
"key": "interpretation-benchmark-commit",
|
||||
"label": "interpretation embeds the benchmark commit",
|
||||
"status": "pass",
|
||||
"expected": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"actual": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"expected": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"actual": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/skill-interpretation.json"
|
||||
@@ -563,36 +563,36 @@
|
||||
"label": "interpretation embeds benchmark summary fields",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"actual": {
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3
|
||||
"public_claim_blocker_count": 4
|
||||
},
|
||||
"paths": [
|
||||
"reports/benchmark_reproducibility.json",
|
||||
@@ -606,13 +606,13 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -620,13 +620,13 @@
|
||||
},
|
||||
"actual": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"source_types": {
|
||||
"manual": 1
|
||||
@@ -649,8 +649,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -661,8 +661,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"decision": "evidence-pending"
|
||||
},
|
||||
@@ -682,7 +682,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11
|
||||
"source_pass_count": 12
|
||||
},
|
||||
"actual": {
|
||||
"ready": false,
|
||||
@@ -690,7 +690,7 @@
|
||||
"pending_count": 4,
|
||||
"accepted_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11
|
||||
"source_pass_count": 12
|
||||
},
|
||||
"paths": [
|
||||
"reports/world_class_evidence_ledger.json",
|
||||
@@ -739,7 +739,7 @@
|
||||
"label": "可维护性",
|
||||
"score": 100,
|
||||
"reasons": [
|
||||
"SKILL.md 约 339 个词/字。",
|
||||
"SKILL.md 约 314 个词/字。",
|
||||
"入口文件保持克制，可维护性较好。",
|
||||
"references/ 已承载扩展指导。",
|
||||
"scripts/ 已承载确定性逻辑。",
|
||||
@@ -760,7 +760,7 @@
|
||||
"label": "上下文成本",
|
||||
"score": 42,
|
||||
"reasons": [
|
||||
"入口约 339 个词/字，references 约 16934 个词/字。",
|
||||
"入口约 314 个词/字，references 约 16934 个词/字。",
|
||||
"分数越高代表上下文成本越低。",
|
||||
"上下文成本偏高，建议压缩入口或拆分 references。"
|
||||
]
|
||||
@@ -803,7 +803,7 @@
|
||||
"label": "可维护性",
|
||||
"score": 100,
|
||||
"reasons": [
|
||||
"SKILL.md 约 339 个词/字。",
|
||||
"SKILL.md 约 314 个词/字。",
|
||||
"入口文件保持克制，可维护性较好。",
|
||||
"references/ 已承载扩展指导。",
|
||||
"scripts/ 已承载确定性逻辑。",
|
||||
@@ -824,7 +824,7 @@
|
||||
"label": "上下文成本",
|
||||
"score": 42,
|
||||
"reasons": [
|
||||
"入口约 339 个词/字，references 约 16934 个词/字。",
|
||||
"入口约 314 个词/字，references 约 16934 个词/字。",
|
||||
"分数越高代表上下文成本越低。",
|
||||
"上下文成本偏高，建议压缩入口或拆分 references。"
|
||||
]
|
||||
@@ -954,7 +954,7 @@
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"trigger": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -982,7 +982,7 @@
|
||||
"boundary_cards": [
|
||||
{
|
||||
"label": "Owned",
|
||||
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"body": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
},
|
||||
{
|
||||
"label": "Adjacent",
|
||||
@@ -996,7 +996,7 @@
|
||||
},
|
||||
"actual": {
|
||||
"trigger": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -1024,7 +1024,7 @@
|
||||
"boundary_cards": [
|
||||
{
|
||||
"label": "Owned",
|
||||
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"body": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
},
|
||||
{
|
||||
"label": "Adjacent",
|
||||
@@ -1056,7 +1056,7 @@
|
||||
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
||||
],
|
||||
"gaps": [
|
||||
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
|
||||
"上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。"
|
||||
],
|
||||
"recommendations": [
|
||||
"先改触发边界，再扩展工作流。",
|
||||
@@ -1104,7 +1104,7 @@
|
||||
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
||||
],
|
||||
"gaps": [
|
||||
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
|
||||
"上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。"
|
||||
],
|
||||
"recommendations": [
|
||||
"先改触发边界，再扩展工作流。",
|
||||
@@ -1179,7 +1179,7 @@
|
||||
"name": "包体膨胀风险",
|
||||
"impact": 2,
|
||||
"probability": 1,
|
||||
"signal": "SKILL.md 约 339 个词/字。",
|
||||
"signal": "SKILL.md 约 314 个词/字。",
|
||||
"response": "先补证据和边界，再增加包体复杂度。"
|
||||
},
|
||||
{
|
||||
@@ -1338,7 +1338,7 @@
|
||||
"name": "包体膨胀风险",
|
||||
"impact": 2,
|
||||
"probability": 1,
|
||||
"signal": "SKILL.md 约 339 个词/字。",
|
||||
"signal": "SKILL.md 约 314 个词/字。",
|
||||
"response": "先补证据和边界，再增加包体复杂度。"
|
||||
},
|
||||
{
|
||||
@@ -1489,7 +1489,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_pass_count": 12,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1546,8 +1546,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1561,7 +1560,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_pass_count": 12,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -1618,8 +1617,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1670,7 +1668,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1682,10 +1680,10 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"file_count": 456,
|
||||
"file_count": 393,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1710,7 +1708,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 153
|
||||
"value": 155
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -1718,7 +1716,7 @@
|
||||
},
|
||||
{
|
||||
"label": "reports",
|
||||
"value": 235
|
||||
"value": 170
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1758,7 +1756,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -1770,10 +1768,10 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"file_count": 456,
|
||||
"file_count": 393,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -1798,7 +1796,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 153
|
||||
"value": 155
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -1806,7 +1804,7 @@
|
||||
},
|
||||
{
|
||||
"label": "reports",
|
||||
"value": 235
|
||||
"value": 170
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1969,15 +1967,15 @@
|
||||
"expected": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"actual": {
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false
|
||||
},
|
||||
"paths": [
|
||||
@@ -1991,10 +1989,10 @@
|
||||
"label": "Benchmark separates beta testing from public claims",
|
||||
"status": "pass",
|
||||
"expected": {
|
||||
"beta_test_ready": true,
|
||||
"beta_test_ready": false,
|
||||
"public_claim_ready": false,
|
||||
"human_review_complete": false,
|
||||
"beta_release_ready": true,
|
||||
"beta_release_ready": false,
|
||||
"beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
|
||||
"deferred_evidence_keys": [
|
||||
"human-adjudication",
|
||||
@@ -2005,10 +2003,10 @@
|
||||
"deferred_human_review": true
|
||||
},
|
||||
"actual": {
|
||||
"beta_test_ready": true,
|
||||
"beta_test_ready": false,
|
||||
"public_claim_ready": false,
|
||||
"human_review_complete": false,
|
||||
"beta_release_ready": true,
|
||||
"beta_release_ready": false,
|
||||
"beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
|
||||
"deferred_evidence_keys": [
|
||||
"human-adjudication",
|
||||
@@ -2031,8 +2029,8 @@
|
||||
"expected": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -2040,8 +2038,8 @@
|
||||
"actual": {
|
||||
"pending_count": 4,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"ready_to_claim_world_class": false,
|
||||
"preflight_counts_as_evidence": false,
|
||||
"credential_value_exposed": false
|
||||
@@ -2218,7 +2216,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 12,
|
||||
"phase_queue_row_count": 11,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2251,8 +2249,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 8,
|
||||
"row_count": 8,
|
||||
"blocked_count": 7,
|
||||
"row_count": 7,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2376,15 +2374,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2394,7 +2392,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 12,
|
||||
"phase_queue_row_count": 11,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2427,8 +2425,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 8,
|
||||
"row_count": 8,
|
||||
"blocked_count": 7,
|
||||
"row_count": 7,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2552,15 +2550,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2674,15 +2672,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -2693,7 +2691,7 @@
|
||||
"summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 12,
|
||||
"phase_queue_row_count": 11,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2726,8 +2724,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 8,
|
||||
"row_count": 8,
|
||||
"blocked_count": 7,
|
||||
"row_count": 7,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2746,7 +2744,7 @@
|
||||
"operator_runbook_summary": {
|
||||
"phase_queue_count": 2,
|
||||
"phase_queue_blocked_count": 2,
|
||||
"phase_queue_row_count": 12,
|
||||
"phase_queue_row_count": 11,
|
||||
"phase_queue_next_phase": "unblock-access",
|
||||
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
|
||||
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
@@ -2779,8 +2777,8 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 8,
|
||||
"row_count": 8,
|
||||
"blocked_count": 7,
|
||||
"row_count": 7,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator",
|
||||
"human reviewer",
|
||||
@@ -2904,15 +2902,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3026,15 +3024,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3148,15 +3146,15 @@
|
||||
"phase": "collect-source",
|
||||
"priority": 40,
|
||||
"status": "blocked",
|
||||
"blocked_count": 2,
|
||||
"row_count": 2,
|
||||
"blocked_count": 1,
|
||||
"row_count": 1,
|
||||
"owners": [
|
||||
"Browser/Chrome/IDE/provider client integrator"
|
||||
],
|
||||
"evidence_keys": [
|
||||
"native-client-telemetry"
|
||||
],
|
||||
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
|
||||
"next_action_id": "native-client-telemetry-source-check-external_source_events",
|
||||
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
|
||||
"counts_as_completion": false
|
||||
}
|
||||
@@ -3256,8 +3254,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -3414,8 +3412,8 @@
|
||||
"human_pending_count": 1,
|
||||
"external_pending_count": 3,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"plan_keys": [
|
||||
"human-adjudication",
|
||||
"native-client-telemetry",
|
||||
@@ -3579,16 +3577,16 @@
|
||||
"score `91`",
|
||||
"`16` gates",
|
||||
"`3` warnings",
|
||||
"`67` declared internal modules",
|
||||
"`86 / 86` CLI help smoke checks passing across `153` scripts",
|
||||
"`689` zip entries",
|
||||
"archive with `689` entries",
|
||||
"`69` declared internal modules",
|
||||
"`86 / 86` CLI help smoke checks passing across `155` scripts",
|
||||
"`580` zip entries",
|
||||
"archive with `580` entries",
|
||||
"`12` installer permission checks enforced",
|
||||
"`0` permission failures",
|
||||
"`25` required artifacts",
|
||||
"`23` reproduction commands",
|
||||
"initial load `998/1000`",
|
||||
"target count is `82`"
|
||||
"initial load `987/1000`",
|
||||
"target count is `83`"
|
||||
],
|
||||
"actual": "all present",
|
||||
"paths": [
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Evidence Consistency
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-07-02`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -8,7 +8,8 @@
|
||||
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 696,
|
||||
"archive_entry_count": 598,
|
||||
"nested_skill_entry_count": 0,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -33,6 +34,11 @@
|
||||
"status": "pass",
|
||||
"detail": "Archive has no absolute or parent-traversal entries"
|
||||
},
|
||||
{
|
||||
"id": "single-skill-entrypoint",
|
||||
"status": "pass",
|
||||
"detail": "Installed package exposes only the root SKILL.md entrypoint"
|
||||
},
|
||||
{
|
||||
"id": "single-top-level",
|
||||
"status": "pass",
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
- OK: `True`
|
||||
- Package directory: `tests/tmp_review_studio/dist`
|
||||
- Archive extracted: `True`
|
||||
- Nested SKILL.md entries: `0`
|
||||
- Entrypoint loaded: `True`
|
||||
- Manifest loaded: `True`
|
||||
- Interface loaded: `True`
|
||||
@@ -18,6 +19,7 @@
|
||||
| --- | --- | --- |
|
||||
| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
|
||||
| `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
|
||||
| `single-skill-entrypoint` | `pass` | Installed package exposes only the root SKILL.md entrypoint |
|
||||
| `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
|
||||
| `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
|
||||
| `entrypoint-name` | `pass` | Installed SKILL.md name matches package directory |
|
||||
|
||||
@@ -35,8 +35,8 @@
|
||||
"label": "Current",
|
||||
"ranking_state": "selected_by_dev",
|
||||
"promotion_state": "kept_current",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"tokens": 53,
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"tokens": 54,
|
||||
"dev_errors": 0,
|
||||
"holdout_errors": 0,
|
||||
"reason_tags": []
|
||||
@@ -118,8 +118,8 @@
|
||||
],
|
||||
"review_template": {
|
||||
"target": "yao-meta-skill",
|
||||
"current_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"candidate_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"current_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"candidate_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"focus": [
|
||||
"no_candidate_outperformed_current"
|
||||
]
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
| Role | Label | Ranking State | Promotion State | Tokens | Dev Errors | Holdout Errors |
|
||||
| --- | --- | --- | --- | ---: | ---: | ---: |
|
||||
| baseline | `Baseline` | reference | reference | 8 | 1 | 0 |
|
||||
| current | `Current` | selected_by_dev | kept_current | 53 | 0 | 0 |
|
||||
| current | `Current` | selected_by_dev | kept_current | 54 | 0 | 0 |
|
||||
| candidate | `Minimal` | not_selected | blocked | 41 | 2 | 0 |
|
||||
| candidate | `Guardrail` | not_selected | blocked | 56 | 2 | 0 |
|
||||
| candidate | `Balanced` | not_selected | blocked | 60 | 2 | 0 |
|
||||
@@ -37,8 +37,8 @@
|
||||
## Human Review Stub
|
||||
|
||||
- target: yao-meta-skill
|
||||
- current description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
- candidate description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
- current description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
- candidate description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
- review focus: no_candidate_outperformed_current
|
||||
|
||||
## Artifact Paths
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# Human Review
|
||||
|
||||
- target: yao-meta-skill
|
||||
- current description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
- candidate description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
- current description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
- candidate description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
- suggested focus: no_candidate_outperformed_current
|
||||
|
||||
Use the shared template in `references/human-review-template.md` to complete the final decision.
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
|
||||
| Route | Precision | Recall | Avg Margin |
|
||||
| --- | ---: | ---: | ---: |
|
||||
| `yao-meta-skill` | 1.0 | 1.0 | 0.701 |
|
||||
| `yao-meta-skill` | 1.0 | 1.0 | 0.644 |
|
||||
| `team-frontend-review` | 1.0 | 1.0 | 0.805 |
|
||||
| `governed-incident-command` | 1.0 | 1.0 | 0.586 |
|
||||
| `governed-incident-command` | 1.0 | 1.0 | 0.709 |
|
||||
| `no_route` | 1.0 | 1.0 | - |
|
||||
|
||||
@@ -1,15 +1,16 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-21",
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"summary": {
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_entry_count": 689,
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"archive_entry_count": 580,
|
||||
"nested_skill_entry_count": 0,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -614,6 +615,11 @@
|
||||
"status": "pass",
|
||||
"detail": "Archive contains yao-meta-skill/agents/interface.yaml"
|
||||
},
|
||||
{
|
||||
"id": "archive-single-skill-entrypoint",
|
||||
"status": "pass",
|
||||
"detail": "Archive exposes only the root SKILL.md entrypoint"
|
||||
},
|
||||
{
|
||||
"id": "archive-excludes-generated",
|
||||
"status": "pass",
|
||||
|
||||
@@ -4,7 +4,8 @@
|
||||
- Package directory: `dist`
|
||||
- Targets: `4 / 4` adapters present
|
||||
- Archive present: `True`
|
||||
- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2`
|
||||
- Archive SHA256: `c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7`
|
||||
- Nested SKILL.md entries: `0`
|
||||
- Failures: `0`
|
||||
- Warnings: `0`
|
||||
|
||||
@@ -132,6 +133,7 @@
|
||||
| `archive-entry-yao-meta-skill/SKILL.md` | `pass` | Archive contains yao-meta-skill/SKILL.md |
|
||||
| `archive-entry-yao-meta-skill/manifest.json` | `pass` | Archive contains yao-meta-skill/manifest.json |
|
||||
| `archive-entry-yao-meta-skill/agents/interface.yaml` | `pass` | Archive contains yao-meta-skill/agents/interface.yaml |
|
||||
| `archive-single-skill-entrypoint` | `pass` | Archive exposes only the root SKILL.md entrypoint |
|
||||
| `archive-excludes-generated` | `pass` | Archive excludes generated dist/, .previews/, and tests/tmp* contents |
|
||||
| `registry-ok` | `pass` | Registry audit is OK |
|
||||
| `registry-name-match` | `pass` | Registry package name matches package manifest |
|
||||
|
||||
@@ -9,9 +9,9 @@
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"winner_label": "Current",
|
||||
"winner_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"winner_tokens": 53,
|
||||
"current_tokens": 53,
|
||||
"winner_description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"winner_tokens": 54,
|
||||
"current_tokens": 54,
|
||||
"winner_holdout_fp": 0,
|
||||
"winner_holdout_fn": 0,
|
||||
"current_holdout_fp": 0,
|
||||
@@ -42,44 +42,44 @@
|
||||
"calibration": {
|
||||
"holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.908,
|
||||
"mean_non_trigger_score": 0.003,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.767,
|
||||
"max_non_trigger_score": 0.023,
|
||||
"score_gap": 0.744,
|
||||
"threshold_margin": 0.307,
|
||||
"positive_threshold_buffer": 0.437,
|
||||
"negative_threshold_buffer": 0.307,
|
||||
"mean_positive_score": 0.704,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 0.465,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 0.465,
|
||||
"threshold_margin": 0.135,
|
||||
"positive_threshold_buffer": 0.135,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
"risk_band": "healthy"
|
||||
},
|
||||
"blind_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 0.669,
|
||||
"mean_non_trigger_score": 0.116,
|
||||
"mean_near_neighbor_score": 0.152,
|
||||
"min_positive_score": 0.665,
|
||||
"max_non_trigger_score": 0.305,
|
||||
"score_gap": 0.36,
|
||||
"threshold_margin": 0.025,
|
||||
"positive_threshold_buffer": 0.335,
|
||||
"negative_threshold_buffer": 0.025,
|
||||
"boundary_case_count": 1,
|
||||
"boundary_case_rate": 0.167,
|
||||
"risk_band": "tight"
|
||||
"mean_positive_score": 0.377,
|
||||
"mean_non_trigger_score": 0.024,
|
||||
"mean_near_neighbor_score": 0.006,
|
||||
"min_positive_score": 0.374,
|
||||
"max_non_trigger_score": 0.084,
|
||||
"score_gap": 0.29,
|
||||
"threshold_margin": 0.044,
|
||||
"positive_threshold_buffer": 0.044,
|
||||
"negative_threshold_buffer": 0.246,
|
||||
"boundary_case_count": 2,
|
||||
"boundary_case_rate": 0.333,
|
||||
"risk_band": "watch"
|
||||
},
|
||||
"adversarial_holdout": {
|
||||
"threshold": 0.33,
|
||||
"mean_positive_score": 1.0,
|
||||
"mean_positive_score": 0.81,
|
||||
"mean_non_trigger_score": 0.0,
|
||||
"mean_near_neighbor_score": 0.0,
|
||||
"min_positive_score": 1.0,
|
||||
"min_positive_score": 0.808,
|
||||
"max_non_trigger_score": 0.0,
|
||||
"score_gap": 1.0,
|
||||
"score_gap": 0.808,
|
||||
"threshold_margin": 0.33,
|
||||
"positive_threshold_buffer": 0.67,
|
||||
"positive_threshold_buffer": 0.478,
|
||||
"negative_threshold_buffer": 0.33,
|
||||
"boundary_case_count": 0,
|
||||
"boundary_case_rate": 0.0,
|
||||
@@ -170,7 +170,7 @@
|
||||
"route_metrics": {
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.701,
|
||||
"average_margin": 0.644,
|
||||
"misroute_count": 0,
|
||||
"ambiguous_case_count": 0
|
||||
}
|
||||
@@ -193,8 +193,8 @@
|
||||
"label": "Current",
|
||||
"ranking_state": "selected_by_dev",
|
||||
"promotion_state": "kept_current",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"tokens": 53,
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"tokens": 54,
|
||||
"dev_errors": 0,
|
||||
"holdout_errors": 0,
|
||||
"reason_tags": []
|
||||
@@ -702,7 +702,7 @@
|
||||
"route_metrics": {
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.586,
|
||||
"average_margin": 0.709,
|
||||
"misroute_count": 0,
|
||||
"ambiguous_case_count": 0
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"skill_name": "yao-meta-skill",
|
||||
"skill_name": "yao-meta-skill-trigger-coverage-merge",
|
||||
"relevance": "prompt-aware",
|
||||
"primary_task_family": {
|
||||
"key": "execution_operation",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Prompt Quality Profile
|
||||
|
||||
Skill: `yao-meta-skill`
|
||||
Skill: `yao-meta-skill-trigger-coverage-merge`
|
||||
Relevance: `prompt-aware`
|
||||
Overall quality score: `89.0/100`
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
"file_count": 232,
|
||||
"file_count": 235,
|
||||
"issue_count": 0,
|
||||
"syntax_error_count": 0,
|
||||
"fstring_311_violation_count": 0,
|
||||
@@ -35,7 +35,7 @@
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "geo-ranking-article-generator/scripts/build_html_index.py",
|
||||
"path": "reports/blind-human-review-2026-06-29/generate_pack.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
@@ -916,6 +916,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_operator_commands.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_output_commands.py",
|
||||
"ok": true,
|
||||
@@ -940,6 +946,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser_operator.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_report_commands.py",
|
||||
"ok": true,
|
||||
@@ -1090,6 +1102,12 @@
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_operator_ux.py",
|
||||
"ok": true,
|
||||
"issue_count": 0,
|
||||
"issues": []
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_output_eval_lab.py",
|
||||
"ok": true,
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
# Python Compatibility
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `pass`
|
||||
- target python: `3.11`
|
||||
- files scanned: `232`
|
||||
- files scanned: `235`
|
||||
- issues: `0`
|
||||
- syntax errors: `0`
|
||||
- f-string 3.11 violations: `0`
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"skill_name": "yao-meta-skill",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"intent_confidence": {
|
||||
"score": 100,
|
||||
"band": "high",
|
||||
@@ -50,39 +50,41 @@
|
||||
},
|
||||
{
|
||||
"source_type": "research",
|
||||
"name": "Human-in-the-loop verification",
|
||||
"name": "Hypothesis-test-learn loop",
|
||||
"evidence_mode": "curated-pattern-track",
|
||||
"matched_keywords": [
|
||||
"review",
|
||||
"govern"
|
||||
"test",
|
||||
"iteration"
|
||||
],
|
||||
"borrow": "Borrow a review checkpoint wherever trust matters more than raw speed.",
|
||||
"avoid": "Do not force every skill through heavyweight review when the risk is low.",
|
||||
"why_relevant": "This track matches: review, govern."
|
||||
"borrow": "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
|
||||
"avoid": "Do not create experimental overhead that exceeds the skill's real risk tier.",
|
||||
"why_relevant": "This track matches: test, iteration."
|
||||
},
|
||||
{
|
||||
"source_type": "principles",
|
||||
"name": "Boundary-first design",
|
||||
"evidence_mode": "curated-pattern-track",
|
||||
"matched_keywords": [
|
||||
"route"
|
||||
"route",
|
||||
"trigger",
|
||||
"exclude"
|
||||
],
|
||||
"borrow": "Borrow the discipline of defining what the skill should not own before growing the package.",
|
||||
"avoid": "Do not expand execution assets until route boundaries stay clean.",
|
||||
"why_relevant": "This track matches: route."
|
||||
"why_relevant": "This track matches: route, trigger, exclude."
|
||||
}
|
||||
],
|
||||
"synthesis": {
|
||||
"borrow_now": [
|
||||
"Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
|
||||
"Borrow a review checkpoint wherever trust matters more than raw speed.",
|
||||
"Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
|
||||
"Borrow the discipline of defining what the skill should not own before growing the package.",
|
||||
"Borrow the way it turns a messy workflow into a repeatable operating path.",
|
||||
"Borrow the clear execution entrypoints and command structure."
|
||||
],
|
||||
"avoid_now": [
|
||||
"Do not let packaging or platform concerns swallow the core job boundary.",
|
||||
"Do not force every skill through heavyweight review when the risk is low.",
|
||||
"Do not create experimental overhead that exceeds the skill's real risk tier.",
|
||||
"Do not expand execution assets until route boundaries stay clean.",
|
||||
"Do not import process overhead that only exists for that project's scale.",
|
||||
"Do not copy repo-specific commands or environment assumptions verbatim."
|
||||
@@ -118,10 +120,10 @@
|
||||
"score": 4
|
||||
},
|
||||
{
|
||||
"name": "Human-in-the-loop verification",
|
||||
"name": "Hypothesis-test-learn loop",
|
||||
"source_type": "research",
|
||||
"borrow": "Borrow a review checkpoint wherever trust matters more than raw speed.",
|
||||
"avoid": "Do not force every skill through heavyweight review when the risk is low.",
|
||||
"borrow": "Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
|
||||
"avoid": "Do not create experimental overhead that exceeds the skill's real risk tier.",
|
||||
"gates": {
|
||||
"recurrence": true,
|
||||
"generativity": true,
|
||||
@@ -235,11 +237,11 @@
|
||||
"summary": "Start by borrowing this pattern: Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts. Avoid this for the first pass: Do not let packaging or platform concerns swallow the core job boundary.",
|
||||
"borrow_now": [
|
||||
"Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
|
||||
"Borrow a review checkpoint wherever trust matters more than raw speed."
|
||||
"Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed."
|
||||
],
|
||||
"avoid_for_now": [
|
||||
"Do not let packaging or platform concerns swallow the core job boundary.",
|
||||
"Do not force every skill through heavyweight review when the risk is low."
|
||||
"Do not create experimental overhead that exceeds the skill's real risk tier."
|
||||
],
|
||||
"why": "There is a real design conflict to resolve: The stated preference leans lightweight or speed-first, while the benchmark mix leans toward governance, review, or heavier evaluation structure.",
|
||||
"user_decision_required": true
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Reference Synthesis
|
||||
|
||||
Skill: `yao-meta-skill`
|
||||
- Description: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.
|
||||
- Description: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.
|
||||
- Intent confidence: `100/100` (`high`)
|
||||
|
||||
## Live GitHub Benchmarks
|
||||
@@ -33,24 +33,24 @@ Skill: `yao-meta-skill`
|
||||
- Borrow: Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.
|
||||
- Avoid: Do not let packaging or platform concerns swallow the core job boundary.
|
||||
|
||||
### Human-in-the-loop verification
|
||||
### Hypothesis-test-learn loop
|
||||
- Type: `research`
|
||||
- Evidence mode: `curated-pattern-track`
|
||||
- Why relevant: This track matches: review, govern.
|
||||
- Borrow: Borrow a review checkpoint wherever trust matters more than raw speed.
|
||||
- Avoid: Do not force every skill through heavyweight review when the risk is low.
|
||||
- Why relevant: This track matches: test, iteration.
|
||||
- Borrow: Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.
|
||||
- Avoid: Do not create experimental overhead that exceeds the skill's real risk tier.
|
||||
|
||||
### Boundary-first design
|
||||
- Type: `principles`
|
||||
- Evidence mode: `curated-pattern-track`
|
||||
- Why relevant: This track matches: route.
|
||||
- Why relevant: This track matches: route, trigger, exclude.
|
||||
- Borrow: Borrow the discipline of defining what the skill should not own before growing the package.
|
||||
- Avoid: Do not expand execution assets until route boundaries stay clean.
|
||||
|
||||
## Borrow Now
|
||||
|
||||
- Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.
|
||||
- Borrow a review checkpoint wherever trust matters more than raw speed.
|
||||
- Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.
|
||||
- Borrow the discipline of defining what the skill should not own before growing the package.
|
||||
- Borrow the way it turns a messy workflow into a repeatable operating path.
|
||||
- Borrow the clear execution entrypoints and command structure.
|
||||
@@ -58,7 +58,7 @@ Skill: `yao-meta-skill`
|
||||
## Avoid Now
|
||||
|
||||
- Do not let packaging or platform concerns swallow the core job boundary.
|
||||
- Do not force every skill through heavyweight review when the risk is low.
|
||||
- Do not create experimental overhead that exceeds the skill's real risk tier.
|
||||
- Do not expand execution assets until route boundaries stay clean.
|
||||
- Do not import process overhead that only exists for that project's scale.
|
||||
- Do not copy repo-specific commands or environment assumptions verbatim.
|
||||
@@ -69,7 +69,7 @@ Skill: `yao-meta-skill`
|
||||
- Acceptance threshold: `4/4`
|
||||
- Accepted patterns:
|
||||
- **Official skill anatomy and context discipline**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
- **Human-in-the-loop verification**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
- **Hypothesis-test-learn loop**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
- **Boundary-first design**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
- **obra/superpowers**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
- **affaan-m/ECC**: 4/4 (recurrence, generativity, distinctiveness, boundary)
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
"schema_version": "2.0",
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.1.0",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"targets": [
|
||||
"openai",
|
||||
"claude",
|
||||
@@ -21,8 +21,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -53,7 +53,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257`
|
||||
- Archive SHA256: `7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2`
|
||||
- Package SHA256: `db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c`
|
||||
- Archive SHA256: `c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7`
|
||||
- Install simulated: `True`
|
||||
|
||||
## Compatibility
|
||||
|
||||
+22
-22
File diff suppressed because one or more lines are too long
+758
-797
File diff suppressed because it is too large
Load Diff
@@ -188,7 +188,7 @@ th {
|
||||
<section class="hero">
|
||||
<p class="minor">Review Viewer</p>
|
||||
<h1>Yao Meta Skill</h1>
|
||||
<p class="lede">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</p>
|
||||
<p class="lede">Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</p>
|
||||
<div class="meta">
|
||||
<span>maturity: governed</span>
|
||||
<span>archetype: governed</span>
|
||||
@@ -200,17 +200,17 @@ th {
|
||||
|
||||
<section>
|
||||
<h2>Architecture at a glance</h2>
|
||||
<div class="arch-grid"><div class='arch-step'><div class='step-label'>Inputs</div><div class='step-detail'>workflow, prompt, transcript, docs, or notes</div></div><div class='arch-step'><div class='step-label'>Boundary</div><div class='step-detail'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</div></div><div class='arch-step'><div class='step-label'>Logic</div><div class='step-detail'>For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.; Capture job, output, exclusions, constraints, standards, and the lightest fit.; Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.</div></div><div class='arch-step'><div class='step-label'>Usage</div><div class='step-detail'>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.; Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</div></div><div class='arch-step'><div class='step-label'>Next</div><div class='step-detail'>Review the top iteration directions before growing the package.</div></div></div>
|
||||
<div class="arch-grid"><div class='arch-step'><div class='step-label'>Inputs</div><div class='step-detail'>workflow, prompt, transcript, docs, or notes</div></div><div class='arch-step'><div class='step-label'>Boundary</div><div class='step-detail'>Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</div></div><div class='arch-step'><div class='step-label'>Logic</div><div class='step-detail'>One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.; Capture job, output, exclusions, constraints, standards, lightest fit.; Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.</div></div><div class='arch-step'><div class='step-label'>Usage</div><div class='step-detail'>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.; Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</div></div><div class='arch-step'><div class='step-label'>Next</div><div class='step-detail'>Review the top iteration directions before growing the package.</div></div></div>
|
||||
</section>
|
||||
|
||||
<section class="grid">
|
||||
<div class="panel">
|
||||
<h2>Core logic</h2>
|
||||
<ul><li>For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</li><li>Capture job, output, exclusions, constraints, standards, and the lightest fit.</li><li>Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.</li><li>Write `description` early, test route quality, then add only earned folders and gates.</li><li>Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.</li></ul>
|
||||
<ul><li>One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</li><li>Capture job, output, exclusions, constraints, standards, lightest fit.</li><li>Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.</li><li>Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.</li><li>Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.</li></ul>
|
||||
</div>
|
||||
<div class="panel">
|
||||
<h2>How to use it</h2>
|
||||
<ul><li>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</li><li>Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</li></ul>
|
||||
<ul><li>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</li><li>Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</li></ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@@ -232,13 +232,13 @@ th {
|
||||
</div>
|
||||
<div class="panel">
|
||||
<h2>Compare view</h2>
|
||||
<div class='baseline-box'><p><strong>Winner:</strong> Current</p><p class='minor'>{'priority': ['fewest false positives', 'fewest false negatives', 'highest near-neighbor pass rate', 'highest negative pass rate', 'highest precision', 'highest recall', 'shortest description']}</p><table><thead><tr><th>Variant</th><th>Tokens</th><th>Dev Errors</th><th>Holdout Errors</th><th>Strategy</th></tr></thead><tbody><tr><td>Baseline</td><td>8</td><td>0</td><td>0</td><td>existing</td></tr><tr><td>Current</td><td>53</td><td>0</td><td>0</td><td>current</td></tr><tr><td>Current</td><td>53</td><td>0</td><td>0</td><td>current</td></tr></tbody></table></div>
|
||||
<div class='baseline-box'><p><strong>Winner:</strong> Current</p><p class='minor'>{'priority': ['fewest false positives', 'fewest false negatives', 'highest near-neighbor pass rate', 'highest negative pass rate', 'highest precision', 'highest recall', 'shortest description']}</p><table><thead><tr><th>Variant</th><th>Tokens</th><th>Dev Errors</th><th>Holdout Errors</th><th>Strategy</th></tr></thead><tbody><tr><td>Baseline</td><td>8</td><td>0</td><td>0</td><td>existing</td></tr><tr><td>Current</td><td>54</td><td>0</td><td>0</td><td>current</td></tr><tr><td>Current</td><td>54</td><td>0</td><td>0</td><td>current</td></tr></tbody></table></div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h2>Variant diff studio</h2>
|
||||
<div class="variant-grid"><div class='variant-card'><div class='variant-head'><h3>Baseline</h3><span>existing</span></div><p class='variant-description'>Create and improve agent skills.</p><div class='variant-metrics'><span>tokens 8 (0)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create and improve agent skills.</li></ul><p><strong>Drops from baseline</strong></p><p class='minor'>No dropped cues.</p></div></div><div class='variant-card'><div class='variant-head'><h3>Current</h3><span>current</span></div><p class='variant-description'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</p><div class='variant-metrics'><span>tokens 53 (+45)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.</li><li>Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div><div class='variant-card'><div class='variant-head'><h3>Winner — Current</h3><span>current</span></div><p class='variant-description'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</p><div class='variant-metrics'><span>tokens 53 (+45)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.</li><li>Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div></div>
|
||||
<div class="variant-grid"><div class='variant-card'><div class='variant-head'><h3>Baseline</h3><span>existing</span></div><p class='variant-description'>Create and improve agent skills.</p><div class='variant-metrics'><span>tokens 8 (0)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create and improve agent skills.</li></ul><p><strong>Drops from baseline</strong></p><p class='minor'>No dropped cues.</p></div></div><div class='variant-card'><div class='variant-head'><h3>Current</h3><span>current</span></div><p class='variant-description'>Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</p><div class='variant-metrics'><span>tokens 54 (+46)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts.</li><li>Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测.</li><li>Exclude no-skill summary/translation/docs.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div><div class='variant-card'><div class='variant-head'><h3>Winner — Current</h3><span>current</span></div><p class='variant-description'>Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</p><div class='variant-metrics'><span>tokens 54 (+46)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts.</li><li>Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测.</li><li>Exclude no-skill summary/translation/docs.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div></div>
|
||||
</section>
|
||||
|
||||
<section class="grid">
|
||||
@@ -310,11 +310,11 @@ th {
|
||||
<section class="grid">
|
||||
<div class="panel">
|
||||
<h2>Reference synthesis</h2>
|
||||
<div class="direction-grid"><div class='direction-card'><h3>Official skill anatomy and context discipline</h3><p><strong>Borrow now</strong></p><ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not let packaging or platform concerns swallow the core job boundary.</li></ul></div><div class='direction-card'><h3>Human-in-the-loop verification</h3><p><strong>Borrow now</strong></p><ul><li>Borrow a review checkpoint wherever trust matters more than raw speed.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not force every skill through heavyweight review when the risk is low.</li></ul></div><div class='direction-card'><h3>Boundary-first design</h3><p><strong>Borrow now</strong></p><ul><li>Borrow the discipline of defining what the skill should not own before growing the package.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not expand execution assets until route boundaries stay clean.</li></ul></div></div>
|
||||
<div class="direction-grid"><div class='direction-card'><h3>Official skill anatomy and context discipline</h3><p><strong>Borrow now</strong></p><ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not let packaging or platform concerns swallow the core job boundary.</li></ul></div><div class='direction-card'><h3>Hypothesis-test-learn loop</h3><p><strong>Borrow now</strong></p><ul><li>Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not create experimental overhead that exceeds the skill's real risk tier.</li></ul></div><div class='direction-card'><h3>Boundary-first design</h3><p><strong>Borrow now</strong></p><ul><li>Borrow the discipline of defining what the skill should not own before growing the package.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not expand execution assets until route boundaries stay clean.</li></ul></div></div>
|
||||
</div>
|
||||
<div class="panel">
|
||||
<h2>Borrow now</h2>
|
||||
<ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li><li>Borrow a review checkpoint wherever trust matters more than raw speed.</li><li>Borrow the discipline of defining what the skill should not own before growing the package.</li><li>Borrow the way it turns a messy workflow into a repeatable operating path.</li></ul>
|
||||
<ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li><li>Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.</li><li>Borrow the discipline of defining what the skill should not own before growing the package.</li><li>Borrow the way it turns a messy workflow into a repeatable operating path.</li></ul>
|
||||
<p class="minor">Use the recommendation by default. Only surface the underlying benchmark tradeoffs when intent is uncertain or a real design conflict needs a deliberate call.</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
+994
-771
File diff suppressed because it is too large
Load Diff
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"source": "reports/review_annotations_input.json",
|
||||
"source": "tests/tmp_review_studio/empty_review_annotations_input.json",
|
||||
"summary": {
|
||||
"annotation_count": 0,
|
||||
"open_count": 0,
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"summary": {
|
||||
"waiver_count": 0,
|
||||
"active_count": 0,
|
||||
@@ -92,7 +92,7 @@
|
||||
"Reviewer links output_review_adjudication or output_execution evidence."
|
||||
],
|
||||
"suggested_evidence": "reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
|
||||
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
|
||||
},
|
||||
{
|
||||
|
||||
@@ -38,7 +38,7 @@
|
||||
- waiver allowed: `true`
|
||||
- risk: review pending 5; model-executed 10; output failures 0
|
||||
- evidence: `reports/output_review_adjudication.md`
|
||||
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-17 --evidence reports/output_review_adjudication.md`
|
||||
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
|
||||
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
|
||||
|
||||
#### Required Review
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"correct_count": 3,
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.701
|
||||
"average_margin": 0.644
|
||||
},
|
||||
"team-frontend-review": {
|
||||
"expected_count": 3,
|
||||
@@ -31,7 +31,7 @@
|
||||
"correct_count": 3,
|
||||
"precision": 1.0,
|
||||
"recall": 1.0,
|
||||
"average_margin": 0.586
|
||||
"average_margin": 0.709
|
||||
},
|
||||
"no_route": {
|
||||
"expected_count": 4,
|
||||
@@ -77,18 +77,18 @@
|
||||
"expected_route": "yao-meta-skill",
|
||||
"predicted_route": "yao-meta-skill",
|
||||
"correct": true,
|
||||
"margin": 1.0,
|
||||
"margin": 0.681,
|
||||
"ambiguous": false,
|
||||
"ranked_routes": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 1.0,
|
||||
"score": 0.681,
|
||||
"passed_threshold": true,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [
|
||||
"eval_optimize",
|
||||
"iterate_existing_skill",
|
||||
"reuse_package",
|
||||
"team_operationalize",
|
||||
"transform_workflow"
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
@@ -117,16 +117,17 @@
|
||||
"expected_route": "yao-meta-skill",
|
||||
"predicted_route": "yao-meta-skill",
|
||||
"correct": true,
|
||||
"margin": 0.661,
|
||||
"margin": 0.51,
|
||||
"ambiguous": false,
|
||||
"ranked_routes": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.661,
|
||||
"score": 0.51,
|
||||
"passed_threshold": true,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [
|
||||
"eval_optimize",
|
||||
"iterate_existing_skill",
|
||||
"reuse_package"
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
@@ -155,16 +156,19 @@
|
||||
"expected_route": "yao-meta-skill",
|
||||
"predicted_route": "yao-meta-skill",
|
||||
"correct": true,
|
||||
"margin": 0.441,
|
||||
"margin": 0.74,
|
||||
"ambiguous": false,
|
||||
"ranked_routes": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.441,
|
||||
"score": 0.74,
|
||||
"passed_threshold": true,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [
|
||||
"reuse_package"
|
||||
"build_skill",
|
||||
"multi_asset",
|
||||
"reuse_package",
|
||||
"transform_workflow"
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
@@ -211,14 +215,6 @@
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.012,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "governed-incident-command",
|
||||
"score": 0.012,
|
||||
@@ -226,6 +222,14 @@
|
||||
"threshold": 0.48,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.006,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -251,14 +255,6 @@
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.008,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "governed-incident-command",
|
||||
"score": 0.008,
|
||||
@@ -266,6 +262,14 @@
|
||||
"threshold": 0.48,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.004,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -293,7 +297,7 @@
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.012,
|
||||
"score": 0.006,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
@@ -331,14 +335,6 @@
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.016,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "team-frontend-review",
|
||||
"score": 0.011,
|
||||
@@ -346,6 +342,14 @@
|
||||
"threshold": 0.48,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.005,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -371,7 +375,7 @@
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.328,
|
||||
"score": 0.179,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [
|
||||
@@ -395,7 +399,7 @@
|
||||
"expected_route": "governed-incident-command",
|
||||
"predicted_route": "governed-incident-command",
|
||||
"correct": true,
|
||||
"margin": 0.252,
|
||||
"margin": 0.621,
|
||||
"ambiguous": false,
|
||||
"ranked_routes": [
|
||||
{
|
||||
@@ -413,12 +417,11 @@
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.748,
|
||||
"score": 0.379,
|
||||
"passed_threshold": true,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [
|
||||
"reuse_package",
|
||||
"team_operationalize",
|
||||
"transform_workflow"
|
||||
],
|
||||
"matched_negative_concepts": []
|
||||
@@ -481,14 +484,6 @@
|
||||
"margin": null,
|
||||
"ambiguous": false,
|
||||
"ranked_routes": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.008,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "governed-incident-command",
|
||||
"score": 0.008,
|
||||
@@ -497,6 +492,14 @@
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.0,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
"matched_negative_concepts": []
|
||||
},
|
||||
{
|
||||
"name": "team-frontend-review",
|
||||
"score": 0.0,
|
||||
@@ -522,7 +525,7 @@
|
||||
"ranked_routes": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"score": 0.024,
|
||||
"score": 0.016,
|
||||
"passed_threshold": false,
|
||||
"threshold": 0.33,
|
||||
"matched_desired_concepts": [],
|
||||
|
||||
@@ -9,9 +9,9 @@
|
||||
|
||||
| Route | Expected | Predicted | Precision | Recall | Avg Margin |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: |
|
||||
| `yao-meta-skill` | 3 | 3 | 1.0 | 1.0 | 0.701 |
|
||||
| `yao-meta-skill` | 3 | 3 | 1.0 | 1.0 | 0.644 |
|
||||
| `team-frontend-review` | 3 | 3 | 1.0 | 1.0 | 0.805 |
|
||||
| `governed-incident-command` | 3 | 3 | 1.0 | 1.0 | 0.586 |
|
||||
| `governed-incident-command` | 3 | 3 | 1.0 | 1.0 | 0.709 |
|
||||
| `no_route` | 4 | 4 | 1.0 | 1.0 | - |
|
||||
|
||||
## Confusion Matrix
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"scanned_files": 245,
|
||||
"script_count": 153,
|
||||
"internal_module_count": 67,
|
||||
"scanned_files": 247,
|
||||
"script_count": 155,
|
||||
"internal_module_count": 69,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -12,7 +12,7 @@
|
||||
"network_script_count": 3,
|
||||
"network_policy_covered_count": 3,
|
||||
"network_policy_missing_count": 0,
|
||||
"file_write_script_count": 73,
|
||||
"file_write_script_count": 74,
|
||||
"permission_required_count": 3,
|
||||
"permission_approved_count": 3,
|
||||
"permission_missing_count": 0,
|
||||
@@ -22,8 +22,8 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 245,
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"package_hash_file_count": 247,
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -2092,6 +2092,20 @@
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_operator_commands.py",
|
||||
"interface": "internal-module",
|
||||
"interface_declared": true,
|
||||
"interface_reason": "Imported by yao.py for operator-facing install, localized docs, and PR review diagnostics.",
|
||||
"has_argparse": true,
|
||||
"has_main_guard": false,
|
||||
"uses_input": false,
|
||||
"uses_network": false,
|
||||
"uses_file_write": true,
|
||||
"uses_subprocess": true,
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_output_commands.py",
|
||||
"interface": "internal-module",
|
||||
@@ -2148,6 +2162,20 @@
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser_operator.py",
|
||||
"interface": "internal-module",
|
||||
"interface_declared": true,
|
||||
"interface_reason": "Imported by yao_cli_parser.py to keep operator UX command declarations out of the main parser module.",
|
||||
"has_argparse": true,
|
||||
"has_main_guard": false,
|
||||
"uses_input": false,
|
||||
"uses_network": false,
|
||||
"uses_file_write": false,
|
||||
"uses_subprocess": false,
|
||||
"network_urls": [],
|
||||
"network_hosts": []
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_report_commands.py",
|
||||
"interface": "internal-module",
|
||||
@@ -2225,7 +2253,7 @@
|
||||
"checked_count": 86,
|
||||
"passed_count": 86,
|
||||
"failed_count": 0,
|
||||
"skipped_count": 67,
|
||||
"skipped_count": 69,
|
||||
"failed_scripts": [],
|
||||
"results": [
|
||||
{
|
||||
@@ -3330,6 +3358,10 @@
|
||||
"path": "scripts/yao_cli_distribution_commands.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_operator_commands.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_output_commands.py",
|
||||
"reason": "internal module"
|
||||
@@ -3346,6 +3378,10 @@
|
||||
"path": "scripts/yao_cli_parser_operations.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser_operator.py",
|
||||
"reason": "internal module"
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_report_commands.py",
|
||||
"reason": "internal module"
|
||||
@@ -3484,7 +3520,8 @@
|
||||
"scripts/telemetry_native_host.py",
|
||||
"scripts/trust_check.py",
|
||||
"scripts/upgrade_check.py",
|
||||
"scripts/verify_package.py"
|
||||
"scripts/verify_package.py",
|
||||
"scripts/yao_cli_operator_commands.py"
|
||||
],
|
||||
"reviewer": "Yao Team",
|
||||
"scope": "Local generated reports, registry metadata, temporary test outputs, and package artifacts under the skill workspace.",
|
||||
@@ -3518,6 +3555,7 @@
|
||||
"scripts/sync_local_install.py",
|
||||
"scripts/trust_check.py",
|
||||
"scripts/yao.py",
|
||||
"scripts/yao_cli_operator_commands.py",
|
||||
"scripts/yao_cli_runtime.py"
|
||||
],
|
||||
"reviewer": "Yao Team",
|
||||
|
||||
@@ -1,22 +1,22 @@
|
||||
# Security Trust Report
|
||||
|
||||
- OK: `True`
|
||||
- Scanned files: `245`
|
||||
- Scripts: `153`
|
||||
- Internal script modules: `67`
|
||||
- Scanned files: `247`
|
||||
- Scripts: `155`
|
||||
- Internal script modules: `69`
|
||||
- Secret findings: `0`
|
||||
- Network-capable scripts: `3`
|
||||
- Network policy covered scripts: `3`
|
||||
- Network policy missing scripts: `0`
|
||||
- File-write scripts: `73`
|
||||
- File-write scripts: `74`
|
||||
- Permission approvals: `3 / 3`
|
||||
- Permission approval gaps: `0`
|
||||
- CLI help smoke checked: `86`
|
||||
- CLI help smoke failures: `0`
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `245`
|
||||
- Package SHA256: `5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257`
|
||||
- Package hash files: `247`
|
||||
- Package SHA256: `db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c`
|
||||
|
||||
## Failures
|
||||
|
||||
@@ -208,10 +208,12 @@
|
||||
| scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. |
|
||||
| scripts/yao_cli_create_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator. |
|
||||
| scripts/yao_cli_distribution_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep distribution and runtime gate handlers outside the thin CLI orchestrator. |
|
||||
| scripts/yao_cli_operator_commands.py | internal-module | True | True | False | False | False | True | True | Imported by yao.py for operator-facing install, localized docs, and PR review diagnostics. |
|
||||
| scripts/yao_cli_output_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep output evaluation and review handlers outside the thin CLI orchestrator. |
|
||||
| scripts/yao_cli_parser.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep CLI parser declarations separate from command orchestration. |
|
||||
| scripts/yao_cli_parser_evidence.py | internal-module | True | True | False | False | False | False | False | Imported by yao_cli_parser.py to keep evidence command declarations out of the main parser module. |
|
||||
| scripts/yao_cli_parser_operations.py | internal-module | True | True | False | False | False | False | False | Imported by yao_cli_parser.py to keep SkillOps, telemetry, and review-loop command declarations out of the main parser module. |
|
||||
| scripts/yao_cli_parser_operator.py | internal-module | True | True | False | False | False | False | False | Imported by yao_cli_parser.py to keep operator UX command declarations out of the main parser module. |
|
||||
| scripts/yao_cli_report_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep report and evidence command handlers out of the CLI orchestrator. |
|
||||
| scripts/yao_cli_runtime.py | internal-module | True | False | False | False | False | False | True | Imported by yao.py and command modules for shared subprocess execution and JSON payload parsing. |
|
||||
| scripts/yao_cli_telemetry.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to record opt-in metadata-only CLI run telemetry. |
|
||||
|
||||
@@ -761,7 +761,7 @@
|
||||
<p class="eyebrow"><span data-lang="zh-CN">YAO Skill 生成审计报告</span><span data-lang="en">YAO Skill Generation Audit</span></p>
|
||||
<p class="slug">yao-meta-skill</p>
|
||||
<h1 id="report-title"><span data-lang="zh-CN">技能审计报告</span><span data-lang="en">Yao Meta Skill Audit Report</span></h1>
|
||||
<p class="lead"><span data-lang="zh-CN">这份报告默认使用中文简体，把新 Skill 的定位、指标、原理、契约、质量、风险、资产和迭代路线整理为一份可审计的 HTML 报告。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></p>
|
||||
<p class="lead"><span data-lang="zh-CN">这份报告默认使用中文简体，把新 Skill 的定位、指标、原理、契约、质量、风险、资产和迭代路线整理为一份可审计的 HTML 报告。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></p>
|
||||
<div class="hero-meta"><span><span data-lang="zh-CN">技能名称：yao-meta-skill</span><span data-lang="en">Skill name: yao-meta-skill</span></span><span><span data-lang="zh-CN">成熟度：治理</span><span data-lang="en">Maturity: governed</span></span><span><span data-lang="zh-CN">格式：Agent Skills</span><span data-lang="en">Format: agent-skills</span></span><span><span data-lang="zh-CN">更新时间：2026-03-31</span><span data-lang="en">Updated: 2026-03-31</span></span></div>
|
||||
<div class="badges"><span><span data-lang="zh-CN">openai</span><span data-lang="en">openai</span></span><span><span data-lang="zh-CN">claude</span><span data-lang="en">claude</span></span><span><span data-lang="zh-CN">generic</span><span data-lang="en">generic</span></span><span><span data-lang="zh-CN">vscode</span><span data-lang="en">vscode</span></span></div>
|
||||
</div>
|
||||
@@ -770,7 +770,7 @@
|
||||
<ul class="list"><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">Skill 作者、复用团队和后续 reviewer。</span><span data-lang="en">Skill authors, reuse teams, and later reviewers.</span></li><li><span data-lang="zh-CN">创建完成后建议先打开 reports/skill-interpretation.html，再继续扩展包体。</span><span data-lang="en">After creation, open reports/skill-interpretation.html before expanding the package further.</span></li></ul>
|
||||
</aside>
|
||||
</div>
|
||||
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></small></article></div>
|
||||
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></small></article></div>
|
||||
</section>
|
||||
|
||||
<section id="overview">
|
||||
@@ -782,7 +782,7 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">作用定位</span><span data-lang="en">Role</span></h3>
|
||||
<ul class="list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></li><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">交付结果：SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html, reports/skill-interpretation.json</span><span data-lang="en">Deliverables: SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html, reports/skill-interpretation.json</span></li></ul>
|
||||
<ul class="list"><li><span data-lang="zh-CN">Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">交付结果：SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html, reports/skill-interpretation.json</span><span data-lang="en">Deliverables: SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html, reports/skill-interpretation.json</span></li></ul>
|
||||
</article>
|
||||
<figure class="chart-figure" data-chart="flow"><svg viewBox="0 0 620 170" role="img" aria-label="交付流程"><text data-lang="zh-CN" x="20" y="28" class="chart-title">交付流程</text><text data-lang="en" x="20" y="28" class="chart-title">Delivery Flow</text><path d="M188 93 H248 M398 93 H458" class="chart-line"/><g><rect x="38" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="113" y="99" text-anchor="middle">输入材料</text><text data-lang="en" x="113" y="99" text-anchor="middle">Input material</text></g><g><rect x="248" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="323" y="99" text-anchor="middle">Skill 包体</text><text data-lang="en" x="323" y="99" text-anchor="middle">Skill package</text></g><g><rect x="458" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="533" y="99" text-anchor="middle">可复用能力</text><text data-lang="en" x="533" y="99" text-anchor="middle">Reusable capability</text></g></svg><figcaption><span data-lang="zh-CN">交付流程把用户输入、生成的包体和可复用能力放在一条线上。</span><span data-lang="en">The delivery flow places user input, generated package, and reusable capability on one path.</span></figcaption></figure>
|
||||
</div>
|
||||
@@ -807,12 +807,12 @@
|
||||
<article class="panel metrics-note metrics-summary-panel">
|
||||
<h3><span data-lang="zh-CN">成熟度条</span><span data-lang="en">Maturity Bar</span></h3>
|
||||
<p><span data-lang="zh-CN">这里把每个指标压缩为状态、分数和第一条证据，先给出整体判断，再进入下方明细。</span><span data-lang="en">This compresses each metric into status, score, and the first evidence item before the detailed cards below.</span></p>
|
||||
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></small></li></ol>
|
||||
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></small></li></ol>
|
||||
</article>
|
||||
</div>
|
||||
<div class="metric-detail-section">
|
||||
<div class="detail-section-kicker"><span data-lang="zh-CN">指标明细</span><span data-lang="en">Metric Details</span></div>
|
||||
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">skill-ir.json exists.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">compiled_targets.json exists.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
|
||||
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">skill-ir.json exists.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">compiled_targets.json exists.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -845,11 +845,11 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">执行流程</span><span data-lang="en">Execution Flow</span></h3>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Capture job, output, exclusions, constraints, standards, and the lightest fit.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Write `description` early, test route quality, then add only earned folders and gates.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.</span></li></ol>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Capture job, output, exclusions, constraints, standards, lightest fit.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.</span></li></ol>
|
||||
</article>
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">调用方式</span><span data-lang="en">How To Use</span></h3>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">当你需要把工作流或笔记沉淀成结构精简、触发清晰且带必要 eval 的可复用 Skill 时使用 $yao-meta-skill。</span><span data-lang="en">Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</span></li><li><span data-lang="zh-CN">当用户请求与该 Skill 的触发描述匹配时使用。</span><span data-lang="en">Use this skill when the request matches the frontmatter description.</span></li></ol>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">当你需要把工作流或笔记沉淀成结构精简、触发清晰且带必要 eval 的可复用 Skill 时使用 $yao-meta-skill。</span><span data-lang="en">Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</span></li><li><span data-lang="zh-CN">Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Use this skill when the request matches the frontmatter description.</span></li></ol>
|
||||
</article>
|
||||
</div>
|
||||
</div>
|
||||
@@ -865,7 +865,7 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">触发描述</span><span data-lang="en">Trigger</span></h3>
|
||||
<p><span data-lang="zh-CN">该 Skill 的触发描述来自 SKILL.md frontmatter；默认中文报告先呈现能力边界，原始英文描述可切换到英文查看。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></p>
|
||||
<p><span data-lang="zh-CN">Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></p>
|
||||
<h3><span data-lang="zh-CN">输入材料</span><span data-lang="en">Inputs</span></h3>
|
||||
<ul class="list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">an existing skill directory that needs refactor, evaluation, packaging, or governance hardening</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">benchmark references, local constraints, desired maturity tier, and review standards</span></li></ul>
|
||||
</article>
|
||||
@@ -888,7 +888,7 @@
|
||||
<div>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th><th><span data-lang="zh-CN">证据</span><span data-lang="en">Evidence</span></th><th><span data-lang="zh-CN">建议</span><span data-lang="en">Action</span></th></tr></thead>
|
||||
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 339 words/characters; references are about 16934.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
|
||||
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 314 words/characters; references are about 16934.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
|
||||
</table>
|
||||
<div class="two-col quality-panels">
|
||||
<article class="panel">
|
||||
@@ -925,11 +925,11 @@
|
||||
<div>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">风险</span><span data-lang="en">Risk</span></th><th><span data-lang="zh-CN">信号</span><span data-lang="en">Signal</span></th><th><span data-lang="zh-CN">应对</span><span data-lang="en">Response</span></th></tr></thead>
|
||||
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
|
||||
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
|
||||
</table>
|
||||
</div>
|
||||
</div>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>11 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><p class='blocked-checks-empty'><span data-lang="zh-CN">当前没有阻塞检查。</span><span data-lang="en">No blocked checks right now.</span></p></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>12 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><p class='blocked-checks-empty'><span data-lang="zh-CN">当前没有阻塞检查。</span><span data-lang="en">No blocked checks right now.</span></p></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@@ -940,7 +940,7 @@
|
||||
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
|
||||
</div>
|
||||
<div class="two-col">
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.2 81.8" stroke-dashoffset="-2.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="79.7 20.3" stroke-dashoffset="-20.3" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">456项</text><text data-lang="en" x="130" y="136" text-anchor="middle">456 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.0 82.0" stroke-dashoffset="-2.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="79.9 20.1" stroke-dashoffset="-20.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">393项</text><text data-lang="en" x="130" y="136" text-anchor="middle">393 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
|
||||
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
"name": "yao-meta-skill",
|
||||
"title": "Yao Meta Skill",
|
||||
"display_name": "Yao Meta Skill",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"maturity": "governed",
|
||||
"updated_at": "2026-03-31",
|
||||
"core_value": "把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。",
|
||||
@@ -81,7 +81,7 @@
|
||||
"label": "可维护性",
|
||||
"score": 100,
|
||||
"reasons": [
|
||||
"SKILL.md 约 339 个词/字。",
|
||||
"SKILL.md 约 314 个词/字。",
|
||||
"入口文件保持克制，可维护性较好。",
|
||||
"references/ 已承载扩展指导。",
|
||||
"scripts/ 已承载确定性逻辑。",
|
||||
@@ -102,7 +102,7 @@
|
||||
"label": "上下文成本",
|
||||
"score": 42,
|
||||
"reasons": [
|
||||
"入口约 339 个词/字，references 约 16934 个词/字。",
|
||||
"入口约 314 个词/字，references 约 16934 个词/字。",
|
||||
"分数越高代表上下文成本越低。",
|
||||
"上下文成本偏高，建议压缩入口或拆分 references。"
|
||||
]
|
||||
@@ -156,7 +156,7 @@
|
||||
},
|
||||
"contract_boundary": {
|
||||
"trigger": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -184,7 +184,7 @@
|
||||
"boundary_cards": [
|
||||
{
|
||||
"label": "Owned",
|
||||
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"body": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
},
|
||||
{
|
||||
"label": "Adjacent",
|
||||
@@ -206,7 +206,7 @@
|
||||
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
||||
],
|
||||
"gaps": [
|
||||
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
|
||||
"上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。"
|
||||
],
|
||||
"recommendations": [
|
||||
"先改触发边界，再扩展工作流。",
|
||||
@@ -271,7 +271,7 @@
|
||||
"name": "包体膨胀风险",
|
||||
"impact": 2,
|
||||
"probability": 1,
|
||||
"signal": "SKILL.md 约 339 个词/字。",
|
||||
"signal": "SKILL.md 约 314 个词/字。",
|
||||
"response": "先补证据和边界，再增加包体复杂度。"
|
||||
},
|
||||
{
|
||||
@@ -412,7 +412,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_pass_count": 12,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -469,8 +469,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -511,7 +510,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -523,10 +522,10 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"file_count": 456,
|
||||
"file_count": 393,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -551,7 +550,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 153
|
||||
"value": 155
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -559,7 +558,7 @@
|
||||
},
|
||||
{
|
||||
"label": "reports",
|
||||
"value": 235
|
||||
"value": 170
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -638,17 +637,17 @@
|
||||
"name": "yao-meta-skill",
|
||||
"title": "Yao Meta Skill",
|
||||
"display_name": "Yao Meta Skill",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"logic_steps": [
|
||||
"For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.",
|
||||
"Capture job, output, exclusions, constraints, standards, and the lightest fit.",
|
||||
"Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.",
|
||||
"Write `description` early, test route quality, then add only earned folders and gates.",
|
||||
"Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful."
|
||||
"One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.",
|
||||
"Capture job, output, exclusions, constraints, standards, lightest fit.",
|
||||
"Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.",
|
||||
"Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.",
|
||||
"Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned."
|
||||
],
|
||||
"usage_steps": [
|
||||
"Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.",
|
||||
"Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
],
|
||||
"package_map": [
|
||||
{
|
||||
@@ -685,7 +684,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -697,7 +696,7 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"strengths": [
|
||||
@@ -715,7 +714,7 @@
|
||||
"用户说出类似需求时：Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals."
|
||||
],
|
||||
"trigger_contract": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -1017,13 +1016,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0",
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158",
|
||||
"source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1038,21 +1037,21 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 29,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 37,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 1,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 29
|
||||
"generated_changed_file_count": 36
|
||||
},
|
||||
"commit": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -1137,9 +1136,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 245,
|
||||
"script_count": 153,
|
||||
"internal_module_count": 67,
|
||||
"scanned_files": 247,
|
||||
"script_count": 155,
|
||||
"internal_module_count": 69,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1147,7 +1146,7 @@
|
||||
"network_script_count": 3,
|
||||
"network_policy_covered_count": 3,
|
||||
"network_policy_missing_count": 0,
|
||||
"file_write_script_count": 73,
|
||||
"file_write_script_count": 74,
|
||||
"permission_required_count": 3,
|
||||
"permission_approved_count": 3,
|
||||
"permission_missing_count": 0,
|
||||
@@ -1157,24 +1156,24 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 245,
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"package_hash_file_count": 247,
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_skill_count": 1,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 9,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 10,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"shared_resource_count": 0,
|
||||
"no_route_opportunity_count": 0,
|
||||
"telemetry_report_count": 1,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"non_actionable_issue_count": 24
|
||||
"non_actionable_issue_count": 22
|
||||
},
|
||||
"registry_distribution": {
|
||||
"ok": true,
|
||||
@@ -1182,7 +1181,7 @@
|
||||
"schema_version": "2.0",
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.1.0",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"targets": [
|
||||
"openai",
|
||||
"claude",
|
||||
@@ -1196,8 +1195,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1228,7 +1227,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1244,8 +1243,9 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_entry_count": 689,
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"archive_entry_count": 580,
|
||||
"nested_skill_entry_count": 0,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1256,7 +1256,8 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 696,
|
||||
"archive_entry_count": 598,
|
||||
"nested_skill_entry_count": 0,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1316,19 +1317,19 @@
|
||||
{
|
||||
"field": "description",
|
||||
"from": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.",
|
||||
"to": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"to": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
}
|
||||
],
|
||||
"checksum_changes": [
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"to": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1345,14 +1346,14 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"edited_count": 0,
|
||||
"rejected_count": 0,
|
||||
"missed_count": 0,
|
||||
"failed_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_rate": 100.0,
|
||||
"missed_trigger_count": 0,
|
||||
"wrong_trigger_count": 0,
|
||||
"bad_output_count": 0,
|
||||
@@ -1361,7 +1362,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -1636,7 +1637,7 @@
|
||||
"status": "external_required",
|
||||
"category": "external",
|
||||
"owner": "Browser/Chrome/IDE/provider client integrator",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -1689,8 +1690,8 @@
|
||||
"missing_submission_count": 4,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"submitted_but_pending_count": 0,
|
||||
"source_accepted_without_valid_submission_count": 1,
|
||||
"overclaim_guard_active": true,
|
||||
@@ -2116,7 +2117,7 @@
|
||||
"status": "pending",
|
||||
"source_status": "external_required",
|
||||
"source_accepted": false,
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -2153,7 +2154,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -2174,8 +2175,8 @@
|
||||
"label": "Adoption sample",
|
||||
"field": "adoption_sample_count",
|
||||
"expected": ">0",
|
||||
"actual": 0,
|
||||
"status": "blocked",
|
||||
"actual": 1,
|
||||
"status": "pass",
|
||||
"source_accepted": false,
|
||||
"next_action": "Telemetry must include adoption outcome evidence."
|
||||
},
|
||||
@@ -2191,8 +2192,8 @@
|
||||
}
|
||||
],
|
||||
"source_check_count": 3,
|
||||
"source_pass_count": 1,
|
||||
"source_blocked_count": 2,
|
||||
"source_pass_count": 2,
|
||||
"source_blocked_count": 1,
|
||||
"submission_state": {
|
||||
"status": "missing",
|
||||
"path": "evidence/world_class/submissions/native-client-telemetry.json",
|
||||
@@ -2222,7 +2223,7 @@
|
||||
},
|
||||
"synthesis_highlights": [
|
||||
"Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
|
||||
"Borrow a review checkpoint wherever trust matters more than raw speed.",
|
||||
"Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
|
||||
"Borrow the discipline of defining what the skill should not own before growing the package."
|
||||
],
|
||||
"artifact_design": {
|
||||
|
||||
@@ -135,13 +135,13 @@ Next move: add real client or installer permission enforcement integration.
|
||||
| Output Eval | `5` cases, DeepSeek provider-backed execution for `10 / 10` variants, with-skill pass rate `43.67`, baseline pass rate `23.67`, delta `20.0`, with file-backed, near-neighbor, boundary coverage, `10` command execution runs, `0` recorded fixture runs, `10` provider model-executed runs in root release evidence, `10` observed token rows, `0` estimated token rows, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden |
|
||||
| Runtime Conformance | `5 / 5` targets passing |
|
||||
| Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts |
|
||||
| Trust | `0` secret findings, `1` pinned dependency file, `67` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `153` scripts, source-contract hash scope explicit |
|
||||
| Trust | `0` secret findings, `1` pinned dependency file, `69` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `86 / 86` CLI help smoke checks passing across `155` scripts, source-contract hash scope explicit |
|
||||
| Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired |
|
||||
| Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility |
|
||||
| Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility |
|
||||
| Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `689` zip entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `689` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Package Verification | `4 / 4` target adapters present, archive verified, `580` zip entries, `0` nested SKILL.md entries, `0` failures, `0` warnings |
|
||||
| Install Simulation | archive with `580` entries extracted into a local verification root, `0` nested SKILL.md entries, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings |
|
||||
| Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures |
|
||||
| Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes |
|
||||
| Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages |
|
||||
@@ -153,8 +153,8 @@ Next move: add real client or installer permission enforcement integration.
|
||||
| World-Class Evidence Ledger | `4` evidence entries remain pending: `1` human-required and `3` external-required; anti-overclaim guards block planned work, metadata fallbacks, pending review, and local command runners from counting as completion |
|
||||
| Benchmark Reproducibility | local reproducibility ready with `25` required artifacts, `0` missing artifacts, `23` reproduction commands, and `3` disclosed failure cases; human review, native permission enforcement, native telemetry, and provider ledger approval remain explicit limitations |
|
||||
| IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable |
|
||||
| Context Budget | initial load `998/1000`; deferred `512782/120000`; resource governance governed |
|
||||
| CI | `make ci-test` target count is `82` after the dedicated CLI world-class verifier split |
|
||||
| Context Budget | initial load `987/1000`; deferred `530167/120000`; resource governance governed |
|
||||
| CI | `make ci-test` target count is `83` after adding the dedicated Operator UX verifier |
|
||||
|
||||
## Next Highest-Leverage Moves
|
||||
|
||||
|
||||
+12
-12
@@ -761,7 +761,7 @@
|
||||
<p class="eyebrow"><span data-lang="zh-CN">YAO Skill 生成审计报告</span><span data-lang="en">YAO Skill Generation Audit</span></p>
|
||||
<p class="slug">yao-meta-skill</p>
|
||||
<h1 id="report-title"><span data-lang="zh-CN">技能审计报告</span><span data-lang="en">Yao Meta Skill Audit Report</span></h1>
|
||||
<p class="lead"><span data-lang="zh-CN">这份报告默认使用中文简体，把新 Skill 的定位、指标、原理、契约、质量、风险、资产和迭代路线整理为一份可审计的 HTML 报告。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></p>
|
||||
<p class="lead"><span data-lang="zh-CN">这份报告默认使用中文简体，把新 Skill 的定位、指标、原理、契约、质量、风险、资产和迭代路线整理为一份可审计的 HTML 报告。</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></p>
|
||||
<div class="hero-meta"><span><span data-lang="zh-CN">技能名称：yao-meta-skill</span><span data-lang="en">Skill name: yao-meta-skill</span></span><span><span data-lang="zh-CN">成熟度：治理</span><span data-lang="en">Maturity: governed</span></span><span><span data-lang="zh-CN">格式：Agent Skills</span><span data-lang="en">Format: agent-skills</span></span><span><span data-lang="zh-CN">更新时间：2026-03-31</span><span data-lang="en">Updated: 2026-03-31</span></span></div>
|
||||
<div class="badges"><span><span data-lang="zh-CN">openai</span><span data-lang="en">openai</span></span><span><span data-lang="zh-CN">claude</span><span data-lang="en">claude</span></span><span><span data-lang="zh-CN">generic</span><span data-lang="en">generic</span></span><span><span data-lang="zh-CN">vscode</span><span data-lang="en">vscode</span></span></div>
|
||||
</div>
|
||||
@@ -770,7 +770,7 @@
|
||||
<ul class="list"><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">Skill 作者、复用团队和后续 reviewer。</span><span data-lang="en">Skill authors, reuse teams, and later reviewers.</span></li><li><span data-lang="zh-CN">创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。</span><span data-lang="en">After creation, open reports/skill-overview.html before expanding the package further.</span></li></ul>
|
||||
</aside>
|
||||
</div>
|
||||
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></small></article></div>
|
||||
<div class="score-strip" aria-label="报告关键指标"><article class='score-chip'><span><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong><i style='--score:100%'></i><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></article><article class='score-chip'><span><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong><i style='--score:42%'></i><small><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></small></article></div>
|
||||
</section>
|
||||
|
||||
<section id="overview">
|
||||
@@ -782,7 +782,7 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">作用定位</span><span data-lang="en">Role</span></h3>
|
||||
<ul class="list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></li><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">交付结果：SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html</span><span data-lang="en">Deliverables: SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html</span></li></ul>
|
||||
<ul class="list"><li><span data-lang="zh-CN">Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></li><li><span data-lang="zh-CN">把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。</span><span data-lang="en">Turn one-off experience into a reusable, evaluable, and portable skill package.</span></li><li><span data-lang="zh-CN">交付结果：SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html</span><span data-lang="en">Deliverables: SKILL.md, agents/interface.yaml, skill-ir/examples/yao-meta-skill.json, reports/compiled_targets.md, reports/output_quality_scorecard.md, reports/output_execution_runs.md, reports/output_blind_review_pack.md, reports/output_review_kit.md, reports/output_review_adjudication.md, reports/benchmark_reproducibility.md, reports/output_blind_answer_key.json, reports/conformance_matrix.md, reports/security_trust_report.md, reports/runtime_permission_probes.md, reports/skill_atlas.html, reports/registry_audit.md, reports/package_verification.md, reports/install_simulation.md, reports/upgrade_check.md, reports/adoption_drift_report.md, reports/review_waivers.md, reports/world_class_evidence_plan.md, reports/world_class_evidence_ledger.md, reports/review_annotations.md, reports/review-studio.html, reports/skill-interpretation.html, reports/skill-overview.html</span></li></ul>
|
||||
</article>
|
||||
<figure class="chart-figure" data-chart="flow"><svg viewBox="0 0 620 170" role="img" aria-label="交付流程"><text data-lang="zh-CN" x="20" y="28" class="chart-title">交付流程</text><text data-lang="en" x="20" y="28" class="chart-title">Delivery Flow</text><path d="M188 93 H248 M398 93 H458" class="chart-line"/><g><rect x="38" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="113" y="99" text-anchor="middle">输入材料</text><text data-lang="en" x="113" y="99" text-anchor="middle">Input material</text></g><g><rect x="248" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="323" y="99" text-anchor="middle">Skill 包体</text><text data-lang="en" x="323" y="99" text-anchor="middle">Skill package</text></g><g><rect x="458" y="56" width="150" height="74" rx="8" fill="#F6F8FB" stroke="#e8e6dc"/><text data-lang="zh-CN" x="533" y="99" text-anchor="middle">可复用能力</text><text data-lang="en" x="533" y="99" text-anchor="middle">Reusable capability</text></g></svg><figcaption><span data-lang="zh-CN">交付流程把用户输入、生成的包体和可复用能力放在一条线上。</span><span data-lang="en">The delivery flow places user input, generated package, and reusable capability on one path.</span></figcaption></figure>
|
||||
</div>
|
||||
@@ -807,12 +807,12 @@
|
||||
<article class="panel metrics-note metrics-summary-panel">
|
||||
<h3><span data-lang="zh-CN">成熟度条</span><span data-lang="en">Maturity Bar</span></h3>
|
||||
<p><span data-lang="zh-CN">这里把每个指标压缩为状态、分数和第一条证据，先给出整体判断，再进入下方明细。</span><span data-lang="en">This compresses each metric into status, score, and the first evidence item before the detailed cards below.</span></p>
|
||||
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></small></li></ol>
|
||||
<ol class='metric-summary-list'><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></b><em>100</em><small><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></b><em>100</em><small><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></b><em>100</em><small><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">稳定</span><span data-lang="en">Stable</span></span><b><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></b><em>100</em><small><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></small></li><li><span class='metric-status'><span data-lang="zh-CN">关注</span><span data-lang="en">Watch</span></span><b><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></b><em>42</em><small><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></small></li></ol>
|
||||
</article>
|
||||
</div>
|
||||
<div class="metric-detail-section">
|
||||
<div class="detail-section-kicker"><span data-lang="zh-CN">指标明细</span><span data-lang="en">Metric Details</span></div>
|
||||
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">skill-ir.json exists.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">compiled_targets.json exists.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 339 words/characters; references are about 16934.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
|
||||
<div class="metric-grid metric-detail-grid"><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">完整度</span><span data-lang="en">Completeness</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 已存在，是 Skill 的入口。</span><span data-lang="en">SKILL.md exists and acts as the skill entrypoint.</span></li><li><span data-lang="zh-CN">README.md 已存在，便于人工阅读。</span><span data-lang="en">README.md exists for human-readable usage.</span></li><li><span data-lang="zh-CN">agents/interface.yaml 已存在，便于跨平台适配。</span><span data-lang="en">agents/interface.yaml exists for cross-platform adaptation.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">触发清晰</span><span data-lang="en">Trigger clarity</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></li><li><span data-lang="zh-CN">description 有足够长度说明任务边界。</span><span data-lang="en">The description is long enough to explain the task boundary.</span></li><li><span data-lang="zh-CN">description 已包含使用场景或排除边界信号。</span><span data-lang="en">The description includes usage-scenario or exclusion-boundary signals.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">证据充分</span><span data-lang="en">Evidence depth</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></li><li><span data-lang="zh-CN">skill-ir.json 已存在。</span><span data-lang="en">skill-ir.json exists.</span></li><li><span data-lang="zh-CN">compiled_targets.json 已存在。</span><span data-lang="en">compiled_targets.json exists.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可维护性</span><span data-lang="en">Maintainability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></li><li><span data-lang="zh-CN">入口文件保持克制，可维护性较好。</span><span data-lang="en">The entrypoint stays restrained, which supports maintainability.</span></li><li><span data-lang="zh-CN">references/ 已承载扩展指导。</span><span data-lang="en">references/ carries extended guidance.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">可迁移性</span><span data-lang="en">Portability</span></span><strong>100</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></li><li><span data-lang="zh-CN">manifest.json 已存在。</span><span data-lang="en">manifest.json exists.</span></li><li><span data-lang="zh-CN">目标平台或 adapter target 已声明。</span><span data-lang="en">Target platforms or adapter targets are declared.</span></li></ul></div></article><article class='metric-card'><div class='metric-card-head'><span class='metric-label'><span data-lang="zh-CN">上下文成本</span><span data-lang="en">Context cost</span></span><strong>42</strong></div><div class='metric-card-body'><ul class="compact-list"><li><span data-lang="zh-CN">入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Entrypoint is about 314 words/characters; references are about 16934.</span></li><li><span data-lang="zh-CN">分数越高代表上下文成本越低。</span><span data-lang="en">A higher score means lower context cost.</span></li><li><span data-lang="zh-CN">上下文成本偏高，建议压缩入口或拆分 references。</span><span data-lang="en">Context cost is high; compress the entrypoint or split references further.</span></li></ul></div></article></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -845,11 +845,11 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">执行流程</span><span data-lang="en">Execution Flow</span></h3>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Capture job, output, exclusions, constraints, standards, and the lightest fit.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Write `description` early, test route quality, then add only earned folders and gates.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.</span></li></ol>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Capture job, output, exclusions, constraints, standards, lightest fit.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.</span></li></ol>
|
||||
</article>
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">调用方式</span><span data-lang="en">How To Use</span></h3>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">当你需要把工作流或笔记沉淀成结构精简、触发清晰且带必要 eval 的可复用 Skill 时使用 $yao-meta-skill。</span><span data-lang="en">Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</span></li><li><span data-lang="zh-CN">当用户请求与该 Skill 的触发描述匹配时使用。</span><span data-lang="en">Use this skill when the request matches the frontmatter description.</span></li></ol>
|
||||
<ol class="step-list"><li><span data-lang="zh-CN">当你需要把工作流或笔记沉淀成结构精简、触发清晰且带必要 eval 的可复用 Skill 时使用 $yao-meta-skill。</span><span data-lang="en">Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</span></li><li><span data-lang="zh-CN">Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Use this skill when the request matches the frontmatter description.</span></li></ol>
|
||||
</article>
|
||||
</div>
|
||||
</div>
|
||||
@@ -865,7 +865,7 @@
|
||||
<div class="two-col">
|
||||
<article class="panel">
|
||||
<h3><span data-lang="zh-CN">触发描述</span><span data-lang="en">Trigger</span></h3>
|
||||
<p><span data-lang="zh-CN">该 Skill 的触发描述来自 SKILL.md frontmatter；默认中文报告先呈现能力边界，原始英文描述可切换到英文查看。</span><span data-lang="en">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.</span></p>
|
||||
<p><span data-lang="zh-CN">Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.</span><span data-lang="en">Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.</span></p>
|
||||
<h3><span data-lang="zh-CN">输入材料</span><span data-lang="en">Inputs</span></h3>
|
||||
<ul class="list"><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">an existing skill directory that needs refactor, evaluation, packaging, or governance hardening</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution</span></li><li><span data-lang="zh-CN">原始说明可切换到英文查看；默认中文报告保留结论与结构说明。</span><span data-lang="en">benchmark references, local constraints, desired maturity tier, and review standards</span></li></ul>
|
||||
</article>
|
||||
@@ -888,7 +888,7 @@
|
||||
<div>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th><th><span data-lang="zh-CN">证据</span><span data-lang="en">Evidence</span></th><th><span data-lang="zh-CN">建议</span><span data-lang="en">Action</span></th></tr></thead>
|
||||
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 339 words/characters; references are about 16934.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
|
||||
<tbody><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">触发面保持精简，并锚定在 frontmatter description。</span><span data-lang="en">The trigger surface stays lean and anchored in the frontmatter description.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</span><span data-lang="en">Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">强项</span><span data-lang="en">Strength</span></td><td><span data-lang="zh-CN">已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</span><span data-lang="en">Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.</span></td><td><span data-lang="zh-CN">保留并复用</span><span data-lang="en">Keep</span></td></tr><tr><td><span data-lang="zh-CN">缺口</span><span data-lang="en">Gap</span></td><td><span data-lang="zh-CN">上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。</span><span data-lang="en">Context cost needs improvement: Entrypoint is about 314 words/characters; references are about 16934.</span></td><td><span data-lang="zh-CN">纳入下一轮修复</span><span data-lang="en">Fix next</span></td></tr></tbody>
|
||||
</table>
|
||||
<div class="two-col quality-panels">
|
||||
<article class="panel">
|
||||
@@ -925,11 +925,11 @@
|
||||
<div>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">风险</span><span data-lang="en">Risk</span></th><th><span data-lang="zh-CN">信号</span><span data-lang="en">Signal</span></th><th><span data-lang="zh-CN">应对</span><span data-lang="en">Response</span></th></tr></thead>
|
||||
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 339 个词/字。</span><span data-lang="en">SKILL.md is about 339 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
|
||||
<tbody><tr><td><span data-lang="zh-CN">误触发风险</span><span data-lang="en">Trigger risk</span></td><td><span data-lang="zh-CN">frontmatter description 已存在，具备基础路由面。</span><span data-lang="en">The frontmatter description exists, giving the skill a basic routing surface.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">输出漂移风险</span><span data-lang="en">Output drift risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">证据不足风险</span><span data-lang="en">Evidence gap risk</span></td><td><span data-lang="zh-CN">已生成 20 / 20 类报告证据。</span><span data-lang="en">Generated 20 / 20 evidence report types.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">包体膨胀风险</span><span data-lang="en">Package bloat risk</span></td><td><span data-lang="zh-CN">SKILL.md 约 314 个词/字。</span><span data-lang="en">SKILL.md is about 314 words/characters.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr><tr><td><span data-lang="zh-CN">跨平台迁移风险</span><span data-lang="en">Portability risk</span></td><td><span data-lang="zh-CN">agents/interface.yaml 已存在。</span><span data-lang="en">agents/interface.yaml exists.</span></td><td><span data-lang="zh-CN">先补证据和边界，再增加包体复杂度。</span><span data-lang="en">Improve evidence and boundaries before adding package complexity.</span></td></tr></tbody>
|
||||
</table>
|
||||
</div>
|
||||
</div>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>11 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><p class='blocked-checks-empty'><span data-lang="zh-CN">当前没有阻塞检查。</span><span data-lang="en">No blocked checks right now.</span></p></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li><li><span data-lang="zh-CN">采用样本</span><span data-lang="en">Adoption sample</span></li></ul></article></div></article>
|
||||
<article class='panel world-readiness'><div class='world-readiness-head'><div><h3><span data-lang="zh-CN">世界证据</span><span data-lang="en">World Evidence</span></h3><p><span data-lang="zh-CN">世界级证据尚未完成：4 项待补，0 项已接受。</span><span data-lang="en">World-class evidence is not complete: 4 pending, 0 accepted.</span></p></div><span class='world-status'><span data-lang="zh-CN">证据待补</span><span data-lang="en">Evidence pending</span></span></div><div class='evidence-kpis'><article class='evidence-kpi'><span><span data-lang="zh-CN">待补证据</span><span data-lang="en">Pending</span></span><strong>4</strong><small><span data-lang="zh-CN">仍需外部或人工证据接受。</span><span data-lang="en">External or human evidence still needs acceptance.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">已接受</span><span data-lang="en">Accepted</span></span><strong>0</strong><small><span data-lang="zh-CN">已通过 source check 与提交契约。</span><span data-lang="en">Passed source checks and submission contract.</span></small></article><article class='evidence-kpi'><span><span data-lang="zh-CN">源检查</span><span data-lang="en">Source Checks</span></span><strong>12 / 19</strong><small><span data-lang="zh-CN">通过数 / 总检查数。</span><span data-lang="en">Passed checks / total checks.</span></small></article></div><div class='evidence-list'><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">提供商留出</span><span data-lang="en">Provider Holdout</span></h4></div><p><span data-lang="zh-CN">缺少真实 provider 模型运行和 token metadata。</span><span data-lang="en">Missing a real provider model run and token metadata.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><p class='blocked-checks-empty'><span data-lang="zh-CN">当前没有阻塞检查。</span><span data-lang="en">No blocked checks right now.</span></p></article><article class='evidence-item'><div><span><span data-lang="zh-CN">人工证据</span><span data-lang="en">Human evidence</span></span><h4><span data-lang="zh-CN">人工盲评</span><span data-lang="en">Human Adjudication</span></h4></div><p><span data-lang="zh-CN">盲评 pair 仍待真实 reviewer 决策。</span><span data-lang="en">Blind-review pairs still need real reviewer decisions.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">无待判定</span><span data-lang="en">No pending decisions</span></li><li><span data-lang="zh-CN">盲评完成</span><span data-lang="en">Judgments complete</span></li><li><span data-lang="zh-CN">Reviewer metadata</span><span data-lang="en">Reviewer metadata</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生权限</span><span data-lang="en">Native Permission</span></h4></div><p><span data-lang="zh-CN">原生 runtime enforcement 仍待目标客户端或外部安装器证明。</span><span data-lang="en">Native runtime enforcement still needs target-client or external-installer proof.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">原生执行</span><span data-lang="en">Native enforcement</span></li></ul></article><article class='evidence-item'><div><span><span data-lang="zh-CN">外部证据</span><span data-lang="en">External evidence</span></span><h4><span data-lang="zh-CN">原生遥测</span><span data-lang="en">Native Telemetry</span></h4></div><p><span data-lang="zh-CN">真实外部客户端 metadata-only 事件仍未导入。</span><span data-lang="en">Real external-client metadata-only events have not been imported yet.</span></p><h5><span data-lang="zh-CN">阻塞检查</span><span data-lang="en">Blocked Checks</span></h5><ul class='blocked-checks'><li><span data-lang="zh-CN">外部事件</span><span data-lang="en">External events</span></li></ul></article></div></article>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@@ -940,7 +940,7 @@
|
||||
<p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
|
||||
</div>
|
||||
<div class="two-col">
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.2 81.8" stroke-dashoffset="-2.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="79.7 20.3" stroke-dashoffset="-20.3" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">456项</text><text data-lang="en" x="130" y="136" text-anchor="middle">456 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text data-lang="zh-CN" x="20" y="30" class="chart-title">资产分布</text><text data-lang="en" x="20" y="30" class="chart-title">Asset Distribution</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-0.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.5 99.5" stroke-dashoffset="-1.5" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="18.0 82.0" stroke-dashoffset="-2.1" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="79.9 20.1" stroke-dashoffset="-20.1" pathLength="100" transform="rotate(-90 130 130)"/><text data-lang="zh-CN" x="130" y="136" text-anchor="middle">393项</text><text data-lang="en" x="130" y="136" text-anchor="middle">393 items</text><text data-lang="zh-CN" x="235" y="78">SKILL.md</text><text data-lang="en" x="235" y="78">SKILL.md</text><text data-lang="zh-CN" x="235" y="100">README.md</text><text data-lang="en" x="235" y="100">README.md</text><text data-lang="zh-CN" x="235" y="122">agents/interface.yaml</text><text data-lang="en" x="235" y="122">agents/interface.yaml</text><text data-lang="zh-CN" x="235" y="144">manifest.json</text><text data-lang="en" x="235" y="144">manifest.json</text><text data-lang="zh-CN" x="235" y="166">references</text><text data-lang="en" x="235" y="166">references</text><text data-lang="zh-CN" x="235" y="188">scripts</text><text data-lang="en" x="235" y="188">scripts</text></svg><figcaption><span data-lang="zh-CN">资产分布图展示当前包体的文件和目录重心。</span><span data-lang="en">The asset distribution chart shows where files and directories are concentrated.</span></figcaption></figure>
|
||||
<table>
|
||||
<thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
|
||||
<tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
|
||||
|
||||
+75
-74
@@ -3,7 +3,7 @@
|
||||
"name": "yao-meta-skill",
|
||||
"title": "Yao Meta Skill",
|
||||
"display_name": "Yao Meta Skill",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"maturity": "governed",
|
||||
"updated_at": "2026-03-31",
|
||||
"core_value": "把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。",
|
||||
@@ -80,7 +80,7 @@
|
||||
"label": "可维护性",
|
||||
"score": 100,
|
||||
"reasons": [
|
||||
"SKILL.md 约 339 个词/字。",
|
||||
"SKILL.md 约 314 个词/字。",
|
||||
"入口文件保持克制，可维护性较好。",
|
||||
"references/ 已承载扩展指导。",
|
||||
"scripts/ 已承载确定性逻辑。",
|
||||
@@ -101,7 +101,7 @@
|
||||
"label": "上下文成本",
|
||||
"score": 42,
|
||||
"reasons": [
|
||||
"入口约 339 个词/字，references 约 16934 个词/字。",
|
||||
"入口约 314 个词/字，references 约 16934 个词/字。",
|
||||
"分数越高代表上下文成本越低。",
|
||||
"上下文成本偏高，建议压缩入口或拆分 references。"
|
||||
]
|
||||
@@ -155,7 +155,7 @@
|
||||
},
|
||||
"contract_boundary": {
|
||||
"trigger": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -183,7 +183,7 @@
|
||||
"boundary_cards": [
|
||||
{
|
||||
"label": "Owned",
|
||||
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"body": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
},
|
||||
{
|
||||
"label": "Adjacent",
|
||||
@@ -205,7 +205,7 @@
|
||||
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
||||
],
|
||||
"gaps": [
|
||||
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
|
||||
"上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。"
|
||||
],
|
||||
"recommendations": [
|
||||
"先改触发边界，再扩展工作流。",
|
||||
@@ -270,7 +270,7 @@
|
||||
"name": "包体膨胀风险",
|
||||
"impact": 2,
|
||||
"probability": 1,
|
||||
"signal": "SKILL.md 约 339 个词/字。",
|
||||
"signal": "SKILL.md 约 314 个词/字。",
|
||||
"response": "先补证据和边界，再增加包体复杂度。"
|
||||
},
|
||||
{
|
||||
@@ -411,7 +411,7 @@
|
||||
"external_pending_count": 3,
|
||||
"human_pending_count": 1,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_pass_count": 12,
|
||||
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
||||
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
||||
"entries": [
|
||||
@@ -468,8 +468,7 @@
|
||||
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
||||
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
||||
"blocked_checks": [
|
||||
"External events",
|
||||
"Adoption sample"
|
||||
"External events"
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -510,7 +509,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -522,10 +521,10 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"file_count": 456,
|
||||
"file_count": 393,
|
||||
"folder_count": 4,
|
||||
"distribution": [
|
||||
{
|
||||
@@ -550,7 +549,7 @@
|
||||
},
|
||||
{
|
||||
"label": "scripts",
|
||||
"value": 153
|
||||
"value": 155
|
||||
},
|
||||
{
|
||||
"label": "evals",
|
||||
@@ -558,7 +557,7 @@
|
||||
},
|
||||
{
|
||||
"label": "reports",
|
||||
"value": 235
|
||||
"value": 170
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -633,17 +632,17 @@
|
||||
"name": "yao-meta-skill",
|
||||
"title": "Yao Meta Skill",
|
||||
"display_name": "Yao Meta Skill",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"logic_steps": [
|
||||
"For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.",
|
||||
"Capture job, output, exclusions, constraints, standards, and the lightest fit.",
|
||||
"Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.",
|
||||
"Write `description` early, test route quality, then add only earned folders and gates.",
|
||||
"Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful."
|
||||
"One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.",
|
||||
"Capture job, output, exclusions, constraints, standards, lightest fit.",
|
||||
"Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.",
|
||||
"Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.",
|
||||
"Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned."
|
||||
],
|
||||
"usage_steps": [
|
||||
"Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.",
|
||||
"Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"Use this skill when the request matches: Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
],
|
||||
"package_map": [
|
||||
{
|
||||
@@ -680,7 +679,7 @@
|
||||
"path": "scripts",
|
||||
"label": "Deterministic helpers or local tooling",
|
||||
"kind": "folder",
|
||||
"file_count": 153
|
||||
"file_count": 155
|
||||
},
|
||||
{
|
||||
"path": "evals",
|
||||
@@ -692,7 +691,7 @@
|
||||
"path": "reports",
|
||||
"label": "Generated evidence and overview artifacts",
|
||||
"kind": "folder",
|
||||
"file_count": 235
|
||||
"file_count": 170
|
||||
}
|
||||
],
|
||||
"strengths": [
|
||||
@@ -710,7 +709,7 @@
|
||||
"用户说出类似需求时：Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals."
|
||||
],
|
||||
"trigger_contract": {
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"activation": "manual",
|
||||
"execution": "inline",
|
||||
"shell": "bash"
|
||||
@@ -1012,13 +1011,13 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 25,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "55a6c33c12e14d6507d4a5d4d4cf1268db35fb323d523e8b23ce9c73aedf8db0",
|
||||
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158",
|
||||
"source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
"command_count": 23,
|
||||
@@ -1033,21 +1032,21 @@
|
||||
"world_class_task_count": 4,
|
||||
"world_class_ledger_pending_count": 4,
|
||||
"world_class_source_check_count": 19,
|
||||
"world_class_source_pass_count": 11,
|
||||
"world_class_source_blocked_count": 8,
|
||||
"beta_test_ready": true,
|
||||
"beta_test_blocker_count": 0,
|
||||
"world_class_source_pass_count": 12,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"beta_test_ready": false,
|
||||
"beta_test_blocker_count": 1,
|
||||
"beta_test_deferred_evidence_count": 4,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 3,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 29,
|
||||
"source_tree_dirty": false,
|
||||
"source_changed_file_count": 0,
|
||||
"changed_file_count": 37,
|
||||
"source_tree_dirty": true,
|
||||
"source_changed_file_count": 1,
|
||||
"generated_tree_dirty": true,
|
||||
"generated_changed_file_count": 29
|
||||
"generated_changed_file_count": 36
|
||||
},
|
||||
"commit": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
|
||||
"commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flags are generation-time context; release lock is blocked by source changes, while generated evidence artifacts are tracked separately.",
|
||||
@@ -1132,9 +1131,9 @@
|
||||
"failures": []
|
||||
},
|
||||
"trust_security": {
|
||||
"scanned_files": 245,
|
||||
"script_count": 153,
|
||||
"internal_module_count": 67,
|
||||
"scanned_files": 247,
|
||||
"script_count": 155,
|
||||
"internal_module_count": 69,
|
||||
"secret_findings": 0,
|
||||
"dependency_files": [
|
||||
"requirements-ci.txt"
|
||||
@@ -1142,7 +1141,7 @@
|
||||
"network_script_count": 3,
|
||||
"network_policy_covered_count": 3,
|
||||
"network_policy_missing_count": 0,
|
||||
"file_write_script_count": 73,
|
||||
"file_write_script_count": 74,
|
||||
"permission_required_count": 3,
|
||||
"permission_approved_count": 3,
|
||||
"permission_missing_count": 0,
|
||||
@@ -1152,24 +1151,24 @@
|
||||
"help_smoke_failed_count": 0,
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 245,
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"package_hash_file_count": 247,
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_skill_count": 1,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 9,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 10,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"shared_resource_count": 0,
|
||||
"no_route_opportunity_count": 0,
|
||||
"telemetry_report_count": 1,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"non_actionable_issue_count": 24
|
||||
"non_actionable_issue_count": 22
|
||||
},
|
||||
"registry_distribution": {
|
||||
"ok": true,
|
||||
@@ -1177,7 +1176,7 @@
|
||||
"schema_version": "2.0",
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.1.0",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"targets": [
|
||||
"openai",
|
||||
"claude",
|
||||
@@ -1191,8 +1190,8 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
"compatibility": {
|
||||
"openai": "pass",
|
||||
@@ -1223,7 +1222,7 @@
|
||||
},
|
||||
"distribution": {
|
||||
"archive_verified": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"package_verification": "reports/package_verification.json",
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
@@ -1239,8 +1238,9 @@
|
||||
"target_count": 4,
|
||||
"adapter_count": 4,
|
||||
"archive_present": true,
|
||||
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
|
||||
"archive_entry_count": 689,
|
||||
"archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
|
||||
"archive_entry_count": 580,
|
||||
"nested_skill_entry_count": 0,
|
||||
"failure_count": 0,
|
||||
"warning_count": 0
|
||||
},
|
||||
@@ -1251,7 +1251,8 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 696,
|
||||
"archive_entry_count": 598,
|
||||
"nested_skill_entry_count": 0,
|
||||
"archive_extracted": true,
|
||||
"entrypoint_loaded": true,
|
||||
"manifest_loaded": true,
|
||||
@@ -1311,19 +1312,19 @@
|
||||
{
|
||||
"field": "description",
|
||||
"from": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.",
|
||||
"to": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
|
||||
"to": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs."
|
||||
}
|
||||
],
|
||||
"checksum_changes": [
|
||||
{
|
||||
"field": "archive_sha256",
|
||||
"from": "",
|
||||
"to": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2"
|
||||
"to": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
|
||||
},
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257"
|
||||
"to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -1340,14 +1341,14 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"edited_count": 0,
|
||||
"rejected_count": 0,
|
||||
"missed_count": 0,
|
||||
"failed_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_rate": 100.0,
|
||||
"missed_trigger_count": 0,
|
||||
"wrong_trigger_count": 0,
|
||||
"bad_output_count": 0,
|
||||
@@ -1356,7 +1357,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -1631,7 +1632,7 @@
|
||||
"status": "external_required",
|
||||
"category": "external",
|
||||
"owner": "Browser/Chrome/IDE/provider client integrator",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -1684,8 +1685,8 @@
|
||||
"missing_submission_count": 4,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 19,
|
||||
"source_pass_count": 11,
|
||||
"source_blocked_count": 8,
|
||||
"source_pass_count": 12,
|
||||
"source_blocked_count": 7,
|
||||
"submitted_but_pending_count": 0,
|
||||
"source_accepted_without_valid_submission_count": 1,
|
||||
"overclaim_guard_active": true,
|
||||
@@ -2111,7 +2112,7 @@
|
||||
"status": "pending",
|
||||
"source_status": "external_required",
|
||||
"source_accepted": false,
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -2148,7 +2149,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -2169,8 +2170,8 @@
|
||||
"label": "Adoption sample",
|
||||
"field": "adoption_sample_count",
|
||||
"expected": ">0",
|
||||
"actual": 0,
|
||||
"status": "blocked",
|
||||
"actual": 1,
|
||||
"status": "pass",
|
||||
"source_accepted": false,
|
||||
"next_action": "Telemetry must include adoption outcome evidence."
|
||||
},
|
||||
@@ -2186,8 +2187,8 @@
|
||||
}
|
||||
],
|
||||
"source_check_count": 3,
|
||||
"source_pass_count": 1,
|
||||
"source_blocked_count": 2,
|
||||
"source_pass_count": 2,
|
||||
"source_blocked_count": 1,
|
||||
"submission_state": {
|
||||
"status": "missing",
|
||||
"path": "evidence/world_class/submissions/native-client-telemetry.json",
|
||||
@@ -2217,7 +2218,7 @@
|
||||
},
|
||||
"synthesis_highlights": [
|
||||
"Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
|
||||
"Borrow a review checkpoint wherever trust matters more than raw speed.",
|
||||
"Borrow a small hypothesis-test-learn loop so the first revision is evidence-backed.",
|
||||
"Borrow the discipline of defining what the skill should not own before growing the package."
|
||||
],
|
||||
"artifact_design": {
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
<h1>Skill Atlas</h1>
|
||||
<p>Portfolio-level review for route overlap, stale ownership, shared resources, telemetry drift, and no-route opportunities.</p>
|
||||
<section class="grid">
|
||||
<div class="card"><span>Skills</span><strong>12</strong></div>
|
||||
<div class="card"><span>Skills</span><strong>11</strong></div>
|
||||
<div class="card"><span>Actionable</span><strong>1</strong></div>
|
||||
<div class="card"><span>Route Collisions</span><strong>0</strong></div>
|
||||
<div class="card"><span>Owner Gaps</span><strong>0</strong></div>
|
||||
@@ -43,13 +43,13 @@
|
||||
</section>
|
||||
<section>
|
||||
<h2>Full Portfolio Counts</h2>
|
||||
<p>All scanned skills remain visible: 5 total route collisions, 9 total owner gaps, 10 total stale signals, and 0 telemetry drift signals.</p>
|
||||
<p>All scanned skills remain visible: 5 total route collisions, 8 total owner gaps, 9 total stale signals, and 0 telemetry drift signals.</p>
|
||||
</section>
|
||||
<section>
|
||||
<h2>Catalog</h2>
|
||||
<table>
|
||||
<thead><tr><th>Name</th><th>Path</th><th>Owner</th><th>Maturity</th><th>Review</th><th>Scope</th></tr></thead>
|
||||
<tbody><tr><td>yao-meta-skill</td><td>.</td><td>Yao Team</td><td>governed</td><td>quarterly</td><td>release</td></tr><tr><td>release-orchestrator</td><td>examples/complex-release-orchestrator/generated-skill</td><td>Yao Team</td><td>production</td><td>quarterly</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/final</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/v0</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/v1</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>incident-command-governor</td><td>examples/governed-incident-command/generated-skill</td><td>Incident Operations Team</td><td>governed</td><td>monthly</td><td>example</td></tr><tr><td>note-cleanup</td><td>examples/simple-note-cleanup/generated-skill</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/team-frontend-review/generated-skill</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>geo-ranking-article-generator</td><td>geo-ranking-article-generator</td><td>missing</td><td>unknown</td><td>missing</td><td>embedded-generated-skill</td></tr><tr><td>invalid-governance-skill</td><td>tests/fixtures/governance_invalid_manifest</td><td>missing</td><td>governed</td><td>missing</td><td>test-fixture</td></tr><tr><td>broken-yaml-skill</td><td>tests/fixtures/package_invalid_yaml</td><td>missing</td><td>unknown</td><td>missing</td><td>test-fixture</td></tr><tr><td>broken-skill</td><td>tests/fixtures/package_missing_interface_field</td><td>missing</td><td>unknown</td><td>missing</td><td>test-fixture</td></tr></tbody>
|
||||
<tbody><tr><td>yao-meta-skill</td><td>.</td><td>Yao Team</td><td>governed</td><td>quarterly</td><td>release</td></tr><tr><td>release-orchestrator</td><td>examples/complex-release-orchestrator/generated-skill</td><td>Yao Team</td><td>production</td><td>quarterly</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/final</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/v0</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/evolution-frontend-review/v1</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>incident-command-governor</td><td>examples/governed-incident-command/generated-skill</td><td>Incident Operations Team</td><td>governed</td><td>monthly</td><td>example</td></tr><tr><td>note-cleanup</td><td>examples/simple-note-cleanup/generated-skill</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>frontend-review</td><td>examples/team-frontend-review/generated-skill</td><td>missing</td><td>unknown</td><td>missing</td><td>example</td></tr><tr><td>invalid-governance-skill</td><td>tests/fixtures/governance_invalid_manifest</td><td>missing</td><td>governed</td><td>missing</td><td>test-fixture</td></tr><tr><td>broken-yaml-skill</td><td>tests/fixtures/package_invalid_yaml</td><td>missing</td><td>unknown</td><td>missing</td><td>test-fixture</td></tr><tr><td>broken-skill</td><td>tests/fixtures/package_missing_interface_field</td><td>missing</td><td>unknown</td><td>missing</td><td>test-fixture</td></tr></tbody>
|
||||
</table>
|
||||
</section>
|
||||
</main>
|
||||
|
||||
+28
-111
@@ -2,20 +2,20 @@
|
||||
"ok": true,
|
||||
"workspace_root": ".",
|
||||
"summary": {
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_skill_count": 1,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 9,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 10,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"shared_resource_count": 0,
|
||||
"no_route_opportunity_count": 0,
|
||||
"telemetry_report_count": 1,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"non_actionable_issue_count": 24
|
||||
"non_actionable_issue_count": 22
|
||||
},
|
||||
"scope_policy": {
|
||||
"present": true,
|
||||
@@ -49,7 +49,7 @@
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
"path": ".",
|
||||
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
||||
"description": "Create/improve/evaluate agent skills from workflows, prompts, SOPs, scripts. Use for migration/release/package, routing, evals/tests, install checks, 优化已有 skill, 补 trigger 评测. Exclude no-skill summary/translation/docs.",
|
||||
"owner": "Yao Team",
|
||||
"version": "1.1.0",
|
||||
"status": "active",
|
||||
@@ -210,10 +210,12 @@
|
||||
"scripts/yao_cli_config.py",
|
||||
"scripts/yao_cli_create_commands.py",
|
||||
"scripts/yao_cli_distribution_commands.py",
|
||||
"scripts/yao_cli_operator_commands.py",
|
||||
"scripts/yao_cli_output_commands.py",
|
||||
"scripts/yao_cli_parser.py",
|
||||
"scripts/yao_cli_parser_evidence.py",
|
||||
"scripts/yao_cli_parser_operations.py",
|
||||
"scripts/yao_cli_parser_operator.py",
|
||||
"scripts/yao_cli_report_commands.py",
|
||||
"scripts/yao_cli_runtime.py",
|
||||
"scripts/yao_cli_telemetry.py",
|
||||
@@ -260,22 +262,28 @@
|
||||
"templates/complex_skill.md.j2"
|
||||
],
|
||||
"token_set": [
|
||||
"creation",
|
||||
"distribution",
|
||||
"checks",
|
||||
"docs",
|
||||
"evals",
|
||||
"evaluate",
|
||||
"improvement",
|
||||
"notes",
|
||||
"or",
|
||||
"exclude",
|
||||
"improve",
|
||||
"install",
|
||||
"migration",
|
||||
"no-skill",
|
||||
"package",
|
||||
"packaging",
|
||||
"prompts",
|
||||
"refactor",
|
||||
"team-ready",
|
||||
"transcripts",
|
||||
"workflow",
|
||||
"workflows"
|
||||
"release",
|
||||
"routing",
|
||||
"scripts",
|
||||
"sops",
|
||||
"summary",
|
||||
"tests",
|
||||
"translation",
|
||||
"trigger",
|
||||
"workflows",
|
||||
"优化已有",
|
||||
"评测"
|
||||
],
|
||||
"atlas_scope": "release",
|
||||
"actionable": true,
|
||||
@@ -629,75 +637,6 @@
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "geo-ranking-article-generator",
|
||||
"path": "geo-ranking-article-generator",
|
||||
"description": "Create GEO ranking-article packs from brand briefs. Use when asked to research a brand, find GEO or 生成式引擎优化 keywords and five competitors, generate timely titles, write five ~2000-character articles, and save them to a fixed knowledge-base folder with an HTML index. Do not use for generic SEO advice, one-off copy, or writing without competitor research.",
|
||||
"owner": "",
|
||||
"version": "",
|
||||
"status": "",
|
||||
"maturity": "",
|
||||
"updated_at": "",
|
||||
"review_cadence": "",
|
||||
"targets": [],
|
||||
"resources": [
|
||||
"scripts/build_html_index.py",
|
||||
"references/article-blueprint.md",
|
||||
"references/feishu-benchmark-patterns.md",
|
||||
"references/geo-research-playbook.md",
|
||||
"templates/brand-brief-template.md"
|
||||
],
|
||||
"token_set": [
|
||||
"2000-character",
|
||||
"advice",
|
||||
"articles",
|
||||
"asked",
|
||||
"brand",
|
||||
"briefs",
|
||||
"competitor",
|
||||
"competitors",
|
||||
"copy",
|
||||
"do",
|
||||
"find",
|
||||
"five",
|
||||
"fixed",
|
||||
"folder",
|
||||
"generate",
|
||||
"generic",
|
||||
"geo",
|
||||
"html",
|
||||
"index",
|
||||
"keywords",
|
||||
"knowledge-base",
|
||||
"not",
|
||||
"one-off",
|
||||
"or",
|
||||
"packs",
|
||||
"ranking-article",
|
||||
"research",
|
||||
"save",
|
||||
"seo",
|
||||
"them",
|
||||
"timely",
|
||||
"titles",
|
||||
"without",
|
||||
"write",
|
||||
"writing",
|
||||
"生成式引擎优化"
|
||||
],
|
||||
"atlas_scope": "embedded-generated-skill",
|
||||
"actionable": false,
|
||||
"scope_reason": "This nested generated skill is retained as local evidence and should not gate the root Meta Skill release.",
|
||||
"telemetry": {
|
||||
"report_present": false,
|
||||
"report": "geo-ranking-article-generator/reports/adoption_drift_report.json",
|
||||
"risk_band": "missing",
|
||||
"event_count": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "invalid-governance-skill",
|
||||
"path": "tests/fixtures/governance_invalid_manifest",
|
||||
@@ -796,20 +735,20 @@
|
||||
}
|
||||
],
|
||||
"summary": {
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_skill_count": 1,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 9,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 10,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"shared_resource_count": 0,
|
||||
"no_route_opportunity_count": 0,
|
||||
"telemetry_report_count": 1,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"non_actionable_issue_count": 24
|
||||
"non_actionable_issue_count": 22
|
||||
}
|
||||
},
|
||||
"route_collisions": [
|
||||
@@ -904,10 +843,6 @@
|
||||
"name": "frontend-review",
|
||||
"path": "examples/team-frontend-review/generated-skill"
|
||||
},
|
||||
{
|
||||
"name": "geo-ranking-article-generator",
|
||||
"path": "geo-ranking-article-generator"
|
||||
},
|
||||
{
|
||||
"name": "invalid-governance-skill",
|
||||
"path": "tests/fixtures/governance_invalid_manifest"
|
||||
@@ -968,13 +903,6 @@
|
||||
"actionable": false,
|
||||
"scope": "example"
|
||||
},
|
||||
{
|
||||
"name": "geo-ranking-article-generator",
|
||||
"path": "geo-ranking-article-generator",
|
||||
"reason": "missing updated_at",
|
||||
"actionable": false,
|
||||
"scope": "embedded-generated-skill"
|
||||
},
|
||||
{
|
||||
"name": "invalid-governance-skill",
|
||||
"path": "tests/fixtures/governance_invalid_manifest",
|
||||
@@ -1054,17 +982,6 @@
|
||||
"actionable": false,
|
||||
"scope": "example"
|
||||
},
|
||||
{
|
||||
"name": "geo-ranking-article-generator",
|
||||
"path": "geo-ranking-article-generator",
|
||||
"missing": [
|
||||
"owner",
|
||||
"review_cadence",
|
||||
"maturity"
|
||||
],
|
||||
"actionable": false,
|
||||
"scope": "embedded-generated-skill"
|
||||
},
|
||||
{
|
||||
"name": "invalid-governance-skill",
|
||||
"path": "tests/fixtures/governance_invalid_manifest",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 15,
|
||||
@@ -197,7 +197,7 @@
|
||||
"key": "trust-security",
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"current": "secrets 0; scripts 153; help failures 0",
|
||||
"current": "secrets 0; scripts 155; help failures 0",
|
||||
"target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -259,7 +259,7 @@
|
||||
"key": "skill-atlas",
|
||||
"label": "Skill Atlas",
|
||||
"status": "pass",
|
||||
"current": "12 skills; actionable collisions 0",
|
||||
"current": "11 skills; actionable collisions 0",
|
||||
"target": "Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -285,7 +285,7 @@
|
||||
"key": "registry-distribution",
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"current": "zip entries 689; install failures 0; permission failures 0",
|
||||
"current": "zip entries 580; install failures 0; permission failures 0",
|
||||
"target": "Package metadata, archive checksum, package verification, and install simulation pass",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -351,7 +351,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -415,7 +415,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Audit
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -23,14 +23,14 @@ Generated at: `2026-06-17`
|
||||
| Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions, blind-review attestation, and integrity fingerprints recorded before claiming output review completion | Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication. |
|
||||
| Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. |
|
||||
| Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. |
|
||||
| Trust Security | pass | secrets 0; scripts 153; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
|
||||
| Trust Security | pass | secrets 0; scripts 155; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. |
|
||||
| Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. |
|
||||
| Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
|
||||
| Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
|
||||
| Registry Distribution | pass | zip entries 689; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Skill Atlas | pass | 11 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. |
|
||||
| Registry Distribution | pass | zip entries 580; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
|
||||
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
|
||||
## Open Highest-Leverage Gaps
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17",
|
||||
"generated_at": "2026-07-02",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 21,
|
||||
@@ -130,7 +130,7 @@
|
||||
"label": "Trust Security",
|
||||
"status": "pass",
|
||||
"objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
|
||||
"current": "153 scripts; secrets 0; help failures 0",
|
||||
"current": "155 scripts; secrets 0; help failures 0",
|
||||
"command": "python3 scripts/yao.py trust .",
|
||||
"test": "python3 tests/verify_trust_check.py",
|
||||
"evidence": [
|
||||
@@ -167,7 +167,7 @@
|
||||
"label": "Skill Atlas",
|
||||
"status": "pass",
|
||||
"objective": "Team skill portfolio reveals route collisions, stale ownership, dependency graph, and no-route opportunities.",
|
||||
"current": "12 scanned skills; actionable collisions 0",
|
||||
"current": "11 scanned skills; actionable collisions 0",
|
||||
"command": "python3 scripts/yao.py skill-atlas --workspace-root .",
|
||||
"test": "python3 tests/verify_skill_atlas.py",
|
||||
"evidence": [
|
||||
@@ -204,7 +204,7 @@
|
||||
"label": "Registry Distribution",
|
||||
"status": "pass",
|
||||
"objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
|
||||
"current": "archive entries 689; install failures 0",
|
||||
"current": "archive entries 580; install failures 0",
|
||||
"command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .",
|
||||
"test": "python3 tests/verify_registry_audit.py",
|
||||
"evidence": [
|
||||
@@ -513,7 +513,7 @@
|
||||
"label": "Skill Atlas Generator",
|
||||
"status": "pass",
|
||||
"objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
|
||||
"current": "12 scanned skills",
|
||||
"current": "11 scanned skills",
|
||||
"command": "make ci-test",
|
||||
"test": "tests/verify_skill_atlas.py",
|
||||
"evidence": [
|
||||
@@ -749,11 +749,11 @@
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skillops/daily/2026-06-17.json",
|
||||
"path": "reports/skillops/daily/2026-07-02.json",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skillops/daily/2026-06-17.md",
|
||||
"path": "reports/skillops/daily/2026-07-02.md",
|
||||
"exists": true
|
||||
}
|
||||
],
|
||||
@@ -776,11 +776,11 @@
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skillops/weekly/2026-W25.json",
|
||||
"path": "reports/skillops/weekly/2026-W27.json",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skillops/weekly/2026-W25.md",
|
||||
"path": "reports/skillops/weekly/2026-W27.md",
|
||||
"exists": true
|
||||
}
|
||||
],
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Blueprint Coverage
|
||||
|
||||
Generated at: `2026-06-17`
|
||||
Generated at: `2026-07-02`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
|
||||
| Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
|
||||
| Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
|
||||
| Trust Security | `pass` | 153 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
|
||||
| Registry Distribution | `pass` | archive entries 689; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Trust Security | `pass` | 155 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
|
||||
| Skill Atlas | `pass` | 11 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` |
|
||||
| Registry Distribution | `pass` | archive entries 580; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
|
||||
| Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
|
||||
| Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` |
|
||||
|
||||
@@ -44,7 +44,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Compiler Refactor | `pass` | 5/5 compiled targets | `make ci-test` | `tests/verify_compile_skill.py` |
|
||||
| Agent Skills Conformance | `pass` | agent-skills target present | `make ci-test` | `tests/verify_conformance_suite.py` |
|
||||
| Trust Check | `pass` | secret findings 0 | `make ci-test` | `tests/verify_trust_check.py` |
|
||||
| Skill Atlas Generator | `pass` | 12 scanned skills | `make ci-test` | `tests/verify_skill_atlas.py` |
|
||||
| Skill Atlas Generator | `pass` | 11 scanned skills | `make ci-test` | `tests/verify_skill_atlas.py` |
|
||||
| Registry Package Format | `pass` | registry ok True | `make ci-test` | `tests/verify_registry_audit.py` |
|
||||
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
|
||||
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
|
||||
@@ -235,12 +235,12 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are
|
||||
|
||||
- objective: Daily operations layer summarizes explicit-source conversation patterns, proposal-only adaptation work, approval state, release locks, and world-class evidence gaps.
|
||||
- status: `covered`
|
||||
- existing evidence: `scripts/render_daily_skillops_report.py`, `tests/verify_daily_skillops.py`, `reports/skillops/daily/2026-06-17.json`, `reports/skillops/daily/2026-06-17.md`
|
||||
- existing evidence: `scripts/render_daily_skillops_report.py`, `tests/verify_daily_skillops.py`, `reports/skillops/daily/2026-07-02.json`, `reports/skillops/daily/2026-07-02.md`
|
||||
- next action: Keep Daily SkillOps report aligned with proposal, approval, coverage, and world-class ledger contracts as the operations layer evolves.
|
||||
|
||||
### Weekly Curator Report
|
||||
|
||||
- objective: Weekly curator layer aggregates Daily SkillOps opportunities, Skill Atlas portfolio signals, release locks, and world-class evidence gaps into a maintenance queue.
|
||||
- status: `covered`
|
||||
- existing evidence: `scripts/render_weekly_curator_report.py`, `tests/verify_weekly_curator.py`, `reports/skillops/weekly/2026-W25.json`, `reports/skillops/weekly/2026-W25.md`
|
||||
- existing evidence: `scripts/render_weekly_curator_report.py`, `tests/verify_weekly_curator.py`, `reports/skillops/weekly/2026-W27.json`, `reports/skillops/weekly/2026-W27.md`
|
||||
- next action: Use weekly curator output as the Skill Librarian maintenance queue before approving any durable skill-library changes.
|
||||
|
||||
@@ -0,0 +1,513 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-20T12:35:26Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0,
|
||||
"summary": {
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0
|
||||
},
|
||||
"operations_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"explicit_source_required_for_scan": true,
|
||||
"implicit_private_log_scan": false,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true,
|
||||
"proposal_only": true,
|
||||
"approval_required_for_writes": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"daily_report_counts_as_world_class_evidence": false
|
||||
},
|
||||
"report_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"top_level_mirrors_summary": true,
|
||||
"summary_fields": [
|
||||
"decision",
|
||||
"source_supplied",
|
||||
"pattern_count",
|
||||
"proposal_count",
|
||||
"approval_count",
|
||||
"pending_review_count",
|
||||
"applied_count",
|
||||
"rollback_count",
|
||||
"local_blueprint_ready",
|
||||
"public_world_class_ready",
|
||||
"world_class_pending_count",
|
||||
"release_lock_ready",
|
||||
"evidence_consistency_ok",
|
||||
"writes_source_files",
|
||||
"auto_patch_enabled",
|
||||
"failure_count"
|
||||
],
|
||||
"source_of_truth": [
|
||||
"summary",
|
||||
"operations_contract"
|
||||
]
|
||||
},
|
||||
"source": {
|
||||
"path": "evals/adaptation/user_signals.example.jsonl",
|
||||
"fingerprint_sha256": "48f94a4f3b82f90db29921c13d09c765ec10aabfde1adce65710c137cc6c5abf",
|
||||
"record_count": 8,
|
||||
"explicit_source": true,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true
|
||||
},
|
||||
"patterns": [
|
||||
{
|
||||
"pattern_id": "language_default",
|
||||
"label": "Default language preference",
|
||||
"signal_type": "report-language",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated report-language signals.",
|
||||
"recommended_action": "Keep generated reports Chinese-first with an English switch where user-facing.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "report_ui",
|
||||
"label": "Report UI and visualization preference",
|
||||
"signal_type": "artifact-design",
|
||||
"support_count": 5,
|
||||
"confidence": 0.95,
|
||||
"reason": "5 redacted records matched repeated artifact-design signals.",
|
||||
"recommended_action": "Prioritize white-background Kami-style reports with readable charts and stable navigation.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-3",
|
||||
"excerpt": "报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "approval_safety",
|
||||
"label": "Approval and privacy boundary",
|
||||
"signal_type": "governance",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated governance signals.",
|
||||
"recommended_action": "Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-5",
|
||||
"excerpt": "自适应升级必须先生成提案，不能直接自动修改源文件。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "delivery_format",
|
||||
"label": "Delivery format preference",
|
||||
"signal_type": "artifact-format",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated artifact-format signals.",
|
||||
"recommended_action": "Surface stable artifact paths and formats in CLI output and generated summaries.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "evidence_testing",
|
||||
"label": "Evidence and testing preference",
|
||||
"signal_type": "quality-gate",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated quality-gate signals.",
|
||||
"recommended_action": "Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-7",
|
||||
"excerpt": "每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-8",
|
||||
"excerpt": "涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"proposals": [
|
||||
{
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"opportunity_summary": {
|
||||
"opportunity_count": 5,
|
||||
"top_score": 88,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"action_type_counts": {
|
||||
"patch_existing_skill": 3,
|
||||
"agents_update": 1,
|
||||
"add_eval": 1
|
||||
},
|
||||
"decision_counts": {
|
||||
"ready_for_approval_review": 1,
|
||||
"proposal_review": 4
|
||||
}
|
||||
},
|
||||
"opportunities": [
|
||||
{
|
||||
"opportunity_id": "skillops-4ad91c18dd",
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"opportunity_type": "artifact-quality",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "ready_for_approval_review",
|
||||
"priority": "medium",
|
||||
"score": 88,
|
||||
"score_reasons": [
|
||||
"support_count=5",
|
||||
"confidence=0.95",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 5,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-531e13c1c6",
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"opportunity_type": "governance",
|
||||
"action_type": "agents_update",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-709ef884f3",
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"opportunity_type": "report-experience",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated language preferences can improve existing report templates after approval.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-f9e43237aa",
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"opportunity_type": "artifact-discoverability",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-0a3a2de7c3",
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"opportunity_type": "quality-gate",
|
||||
"action_type": "add_eval",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 74,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated verification and evidence requests should become focused checks.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"decision_policy": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "skillops-opportunity-scoring",
|
||||
"score_range": [
|
||||
0,
|
||||
100
|
||||
],
|
||||
"score_bands": {
|
||||
"85-100": "ready_for_approval_review",
|
||||
"70-84": "proposal_review",
|
||||
"50-69": "observe_more_evidence",
|
||||
"0-49": "report_only_or_no_action"
|
||||
},
|
||||
"action_types": [
|
||||
"add_eval",
|
||||
"agents_update",
|
||||
"patch_existing_skill",
|
||||
"report_only"
|
||||
],
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"approval_required_for_writes": true
|
||||
},
|
||||
"approval": {
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
{
|
||||
"key": "review-adaptation-proposals",
|
||||
"priority": "high",
|
||||
"action": "Review proposal-only adaptation items before preparing any approval ledger entry."
|
||||
},
|
||||
{
|
||||
"key": "close-world-class-evidence",
|
||||
"priority": "high",
|
||||
"action": "Collect accepted external or human evidence for the pending world-class ledger entries."
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"source_reports": {
|
||||
"patterns": "reports/user_patterns.json",
|
||||
"proposals": "reports/adaptation_proposals.json",
|
||||
"approval_ledger": "reports/adaptation_approval_ledger.json",
|
||||
"regression": "reports/adaptation_regression_report.json",
|
||||
"skill_os2_coverage": "reports/skill_os2_coverage.json",
|
||||
"world_class_ledger": "reports/world_class_evidence_ledger.json",
|
||||
"evidence_consistency": "reports/evidence_consistency.json",
|
||||
"benchmark_reproducibility": "reports/benchmark_reproducibility.json"
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skillops/daily/2026-06-20.json",
|
||||
"markdown": "reports/skillops/daily/2026-06-20.md"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,174 @@
|
||||
# Daily SkillOps Report
|
||||
|
||||
Generated at: `2026-06-20T12:35:26Z`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `proposal-review`
|
||||
- source supplied: `false`
|
||||
- patterns: `5`
|
||||
- proposals: `5`
|
||||
- pending approvals: `0`
|
||||
- applied patches: `0`
|
||||
- rollbacks: `0`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- world-class pending: `4`
|
||||
- release lock ready: `true`
|
||||
- evidence consistency ok: `true`
|
||||
|
||||
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
|
||||
|
||||
## Privacy Boundary
|
||||
|
||||
- explicit_source_required_for_scan: `true`
|
||||
- implicit_private_log_scan: `false`
|
||||
- raw_content_stored: `false`
|
||||
- redacted_excerpts_only: `true`
|
||||
- proposal_only: `true`
|
||||
- approval_required_for_writes: `true`
|
||||
- writes_source_files: `false`
|
||||
- auto_patch_enabled: `false`
|
||||
- daily_report_counts_as_world_class_evidence: `false`
|
||||
|
||||
## Actions
|
||||
|
||||
- `high` Review proposal-only adaptation items before preparing any approval ledger entry.
|
||||
- `high` Collect accepted external or human evidence for the pending world-class ledger entries.
|
||||
|
||||
## Opportunities
|
||||
|
||||
- count: `5`
|
||||
- top score: `88`
|
||||
- ready for approval review: `1`
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `skillops-4ad91c18dd`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `ready_for_approval_review`
|
||||
- Score: `88`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes.
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `skillops-531e13c1c6`
|
||||
- Action: `agents_update`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated privacy and approval signals should tighten durable operating guidance.
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `skillops-709ef884f3`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated language preferences can improve existing report templates after approval.
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `skillops-f9e43237aa`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability.
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `skillops-0a3a2de7c3`
|
||||
- Action: `add_eval`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `74`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated verification and evidence requests should become focused checks.
|
||||
|
||||
## Patterns
|
||||
|
||||
- `language_default`: Default language preference (support `2`, confidence `0.79`)
|
||||
- `report_ui`: Report UI and visualization preference (support `5`, confidence `0.95`)
|
||||
- `approval_safety`: Approval and privacy boundary (support `2`, confidence `0.79`)
|
||||
- `delivery_format`: Delivery format preference (support `2`, confidence `0.79`)
|
||||
- `evidence_testing`: Evidence and testing preference (support `2`, confidence `0.79`)
|
||||
|
||||
## Proposals
|
||||
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `adapt-18c7517f3d`
|
||||
- Pattern: `language_default`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `adapt-fbfe921ba5`
|
||||
- Pattern: `report_ui`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- `tests/verify_skill_overview.py`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
- `python3 tests/verify_skill_report_charts.py`
|
||||
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `adapt-59d219a1fb`
|
||||
- Pattern: `approval_safety`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `references/user-memory-policy.md`
|
||||
- `references/autonomous-adaptation.md`
|
||||
- `schemas/adaptation-proposal.schema.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `adapt-457baca160`
|
||||
- Pattern: `delivery_format`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/yao.py`
|
||||
- `README.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_yao_cli.py`
|
||||
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `adapt-abfee25d3a`
|
||||
- Pattern: `evidence_testing`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `tests/verify_adaptation_safety.py`
|
||||
- `scripts/render_skill_os2_coverage.py`
|
||||
- `reports/skill_os2_coverage.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
- `python3 tests/verify_skill_os2_coverage.py`
|
||||
|
||||
## Evidence
|
||||
|
||||
- patterns: `reports/user_patterns.json`
|
||||
- proposals: `reports/adaptation_proposals.json`
|
||||
- approval_ledger: `reports/adaptation_approval_ledger.json`
|
||||
- regression: `reports/adaptation_regression_report.json`
|
||||
- skill_os2_coverage: `reports/skill_os2_coverage.json`
|
||||
- world_class_ledger: `reports/world_class_evidence_ledger.json`
|
||||
- evidence_consistency: `reports/evidence_consistency.json`
|
||||
- benchmark_reproducibility: `reports/benchmark_reproducibility.json`
|
||||
@@ -0,0 +1,513 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-21",
|
||||
"skill_dir": ".",
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0,
|
||||
"summary": {
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0
|
||||
},
|
||||
"operations_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"explicit_source_required_for_scan": true,
|
||||
"implicit_private_log_scan": false,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true,
|
||||
"proposal_only": true,
|
||||
"approval_required_for_writes": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"daily_report_counts_as_world_class_evidence": false
|
||||
},
|
||||
"report_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"top_level_mirrors_summary": true,
|
||||
"summary_fields": [
|
||||
"decision",
|
||||
"source_supplied",
|
||||
"pattern_count",
|
||||
"proposal_count",
|
||||
"approval_count",
|
||||
"pending_review_count",
|
||||
"applied_count",
|
||||
"rollback_count",
|
||||
"local_blueprint_ready",
|
||||
"public_world_class_ready",
|
||||
"world_class_pending_count",
|
||||
"release_lock_ready",
|
||||
"evidence_consistency_ok",
|
||||
"writes_source_files",
|
||||
"auto_patch_enabled",
|
||||
"failure_count"
|
||||
],
|
||||
"source_of_truth": [
|
||||
"summary",
|
||||
"operations_contract"
|
||||
]
|
||||
},
|
||||
"source": {
|
||||
"path": "evals/adaptation/user_signals.example.jsonl",
|
||||
"fingerprint_sha256": "48f94a4f3b82f90db29921c13d09c765ec10aabfde1adce65710c137cc6c5abf",
|
||||
"record_count": 8,
|
||||
"explicit_source": true,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true
|
||||
},
|
||||
"patterns": [
|
||||
{
|
||||
"pattern_id": "language_default",
|
||||
"label": "Default language preference",
|
||||
"signal_type": "report-language",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated report-language signals.",
|
||||
"recommended_action": "Keep generated reports Chinese-first with an English switch where user-facing.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "report_ui",
|
||||
"label": "Report UI and visualization preference",
|
||||
"signal_type": "artifact-design",
|
||||
"support_count": 5,
|
||||
"confidence": 0.95,
|
||||
"reason": "5 redacted records matched repeated artifact-design signals.",
|
||||
"recommended_action": "Prioritize white-background Kami-style reports with readable charts and stable navigation.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-3",
|
||||
"excerpt": "报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "approval_safety",
|
||||
"label": "Approval and privacy boundary",
|
||||
"signal_type": "governance",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated governance signals.",
|
||||
"recommended_action": "Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-5",
|
||||
"excerpt": "自适应升级必须先生成提案，不能直接自动修改源文件。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "delivery_format",
|
||||
"label": "Delivery format preference",
|
||||
"signal_type": "artifact-format",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated artifact-format signals.",
|
||||
"recommended_action": "Surface stable artifact paths and formats in CLI output and generated summaries.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "evidence_testing",
|
||||
"label": "Evidence and testing preference",
|
||||
"signal_type": "quality-gate",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated quality-gate signals.",
|
||||
"recommended_action": "Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-7",
|
||||
"excerpt": "每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-8",
|
||||
"excerpt": "涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"proposals": [
|
||||
{
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"opportunity_summary": {
|
||||
"opportunity_count": 5,
|
||||
"top_score": 88,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"action_type_counts": {
|
||||
"patch_existing_skill": 3,
|
||||
"agents_update": 1,
|
||||
"add_eval": 1
|
||||
},
|
||||
"decision_counts": {
|
||||
"ready_for_approval_review": 1,
|
||||
"proposal_review": 4
|
||||
}
|
||||
},
|
||||
"opportunities": [
|
||||
{
|
||||
"opportunity_id": "skillops-4ad91c18dd",
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"opportunity_type": "artifact-quality",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "ready_for_approval_review",
|
||||
"priority": "medium",
|
||||
"score": 88,
|
||||
"score_reasons": [
|
||||
"support_count=5",
|
||||
"confidence=0.95",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 5,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-531e13c1c6",
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"opportunity_type": "governance",
|
||||
"action_type": "agents_update",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-709ef884f3",
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"opportunity_type": "report-experience",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated language preferences can improve existing report templates after approval.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-f9e43237aa",
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"opportunity_type": "artifact-discoverability",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-0a3a2de7c3",
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"opportunity_type": "quality-gate",
|
||||
"action_type": "add_eval",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 74,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated verification and evidence requests should become focused checks.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"decision_policy": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "skillops-opportunity-scoring",
|
||||
"score_range": [
|
||||
0,
|
||||
100
|
||||
],
|
||||
"score_bands": {
|
||||
"85-100": "ready_for_approval_review",
|
||||
"70-84": "proposal_review",
|
||||
"50-69": "observe_more_evidence",
|
||||
"0-49": "report_only_or_no_action"
|
||||
},
|
||||
"action_types": [
|
||||
"add_eval",
|
||||
"agents_update",
|
||||
"patch_existing_skill",
|
||||
"report_only"
|
||||
],
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"approval_required_for_writes": true
|
||||
},
|
||||
"approval": {
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
{
|
||||
"key": "review-adaptation-proposals",
|
||||
"priority": "high",
|
||||
"action": "Review proposal-only adaptation items before preparing any approval ledger entry."
|
||||
},
|
||||
{
|
||||
"key": "close-world-class-evidence",
|
||||
"priority": "high",
|
||||
"action": "Collect accepted external or human evidence for the pending world-class ledger entries."
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"source_reports": {
|
||||
"patterns": "reports/user_patterns.json",
|
||||
"proposals": "reports/adaptation_proposals.json",
|
||||
"approval_ledger": "reports/adaptation_approval_ledger.json",
|
||||
"regression": "reports/adaptation_regression_report.json",
|
||||
"skill_os2_coverage": "reports/skill_os2_coverage.json",
|
||||
"world_class_ledger": "reports/world_class_evidence_ledger.json",
|
||||
"evidence_consistency": "reports/evidence_consistency.json",
|
||||
"benchmark_reproducibility": "reports/benchmark_reproducibility.json"
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skillops/daily/2026-06-21.json",
|
||||
"markdown": "reports/skillops/daily/2026-06-21.md"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,174 @@
|
||||
# Daily SkillOps Report
|
||||
|
||||
Generated at: `2026-06-21`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `proposal-review`
|
||||
- source supplied: `false`
|
||||
- patterns: `5`
|
||||
- proposals: `5`
|
||||
- pending approvals: `0`
|
||||
- applied patches: `0`
|
||||
- rollbacks: `0`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- world-class pending: `4`
|
||||
- release lock ready: `true`
|
||||
- evidence consistency ok: `true`
|
||||
|
||||
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
|
||||
|
||||
## Privacy Boundary
|
||||
|
||||
- explicit_source_required_for_scan: `true`
|
||||
- implicit_private_log_scan: `false`
|
||||
- raw_content_stored: `false`
|
||||
- redacted_excerpts_only: `true`
|
||||
- proposal_only: `true`
|
||||
- approval_required_for_writes: `true`
|
||||
- writes_source_files: `false`
|
||||
- auto_patch_enabled: `false`
|
||||
- daily_report_counts_as_world_class_evidence: `false`
|
||||
|
||||
## Actions
|
||||
|
||||
- `high` Review proposal-only adaptation items before preparing any approval ledger entry.
|
||||
- `high` Collect accepted external or human evidence for the pending world-class ledger entries.
|
||||
|
||||
## Opportunities
|
||||
|
||||
- count: `5`
|
||||
- top score: `88`
|
||||
- ready for approval review: `1`
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `skillops-4ad91c18dd`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `ready_for_approval_review`
|
||||
- Score: `88`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes.
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `skillops-531e13c1c6`
|
||||
- Action: `agents_update`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated privacy and approval signals should tighten durable operating guidance.
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `skillops-709ef884f3`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated language preferences can improve existing report templates after approval.
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `skillops-f9e43237aa`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability.
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `skillops-0a3a2de7c3`
|
||||
- Action: `add_eval`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `74`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated verification and evidence requests should become focused checks.
|
||||
|
||||
## Patterns
|
||||
|
||||
- `language_default`: Default language preference (support `2`, confidence `0.79`)
|
||||
- `report_ui`: Report UI and visualization preference (support `5`, confidence `0.95`)
|
||||
- `approval_safety`: Approval and privacy boundary (support `2`, confidence `0.79`)
|
||||
- `delivery_format`: Delivery format preference (support `2`, confidence `0.79`)
|
||||
- `evidence_testing`: Evidence and testing preference (support `2`, confidence `0.79`)
|
||||
|
||||
## Proposals
|
||||
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `adapt-18c7517f3d`
|
||||
- Pattern: `language_default`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `adapt-fbfe921ba5`
|
||||
- Pattern: `report_ui`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- `tests/verify_skill_overview.py`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
- `python3 tests/verify_skill_report_charts.py`
|
||||
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `adapt-59d219a1fb`
|
||||
- Pattern: `approval_safety`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `references/user-memory-policy.md`
|
||||
- `references/autonomous-adaptation.md`
|
||||
- `schemas/adaptation-proposal.schema.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `adapt-457baca160`
|
||||
- Pattern: `delivery_format`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/yao.py`
|
||||
- `README.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_yao_cli.py`
|
||||
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `adapt-abfee25d3a`
|
||||
- Pattern: `evidence_testing`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `tests/verify_adaptation_safety.py`
|
||||
- `scripts/render_skill_os2_coverage.py`
|
||||
- `reports/skill_os2_coverage.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
- `python3 tests/verify_skill_os2_coverage.py`
|
||||
|
||||
## Evidence
|
||||
|
||||
- patterns: `reports/user_patterns.json`
|
||||
- proposals: `reports/adaptation_proposals.json`
|
||||
- approval_ledger: `reports/adaptation_approval_ledger.json`
|
||||
- regression: `reports/adaptation_regression_report.json`
|
||||
- skill_os2_coverage: `reports/skill_os2_coverage.json`
|
||||
- world_class_ledger: `reports/world_class_evidence_ledger.json`
|
||||
- evidence_consistency: `reports/evidence_consistency.json`
|
||||
- benchmark_reproducibility: `reports/benchmark_reproducibility.json`
|
||||
@@ -0,0 +1,513 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-07-02T06:33:07Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0,
|
||||
"summary": {
|
||||
"decision": "proposal-review",
|
||||
"source_supplied": false,
|
||||
"pattern_count": 5,
|
||||
"proposal_count": 5,
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0
|
||||
},
|
||||
"operations_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"explicit_source_required_for_scan": true,
|
||||
"implicit_private_log_scan": false,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true,
|
||||
"proposal_only": true,
|
||||
"approval_required_for_writes": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"daily_report_counts_as_world_class_evidence": false
|
||||
},
|
||||
"report_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "daily-skillops-report",
|
||||
"top_level_mirrors_summary": true,
|
||||
"summary_fields": [
|
||||
"decision",
|
||||
"source_supplied",
|
||||
"pattern_count",
|
||||
"proposal_count",
|
||||
"approval_count",
|
||||
"pending_review_count",
|
||||
"applied_count",
|
||||
"rollback_count",
|
||||
"local_blueprint_ready",
|
||||
"public_world_class_ready",
|
||||
"world_class_pending_count",
|
||||
"release_lock_ready",
|
||||
"evidence_consistency_ok",
|
||||
"writes_source_files",
|
||||
"auto_patch_enabled",
|
||||
"failure_count"
|
||||
],
|
||||
"source_of_truth": [
|
||||
"summary",
|
||||
"operations_contract"
|
||||
]
|
||||
},
|
||||
"source": {
|
||||
"path": "evals/adaptation/user_signals.example.jsonl",
|
||||
"fingerprint_sha256": "48f94a4f3b82f90db29921c13d09c765ec10aabfde1adce65710c137cc6c5abf",
|
||||
"record_count": 8,
|
||||
"explicit_source": true,
|
||||
"raw_content_stored": false,
|
||||
"redacted_excerpts_only": true
|
||||
},
|
||||
"patterns": [
|
||||
{
|
||||
"pattern_id": "language_default",
|
||||
"label": "Default language preference",
|
||||
"signal_type": "report-language",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated report-language signals.",
|
||||
"recommended_action": "Keep generated reports Chinese-first with an English switch where user-facing.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "report_ui",
|
||||
"label": "Report UI and visualization preference",
|
||||
"signal_type": "artifact-design",
|
||||
"support_count": 5,
|
||||
"confidence": 0.95,
|
||||
"reason": "5 redacted records matched repeated artifact-design signals.",
|
||||
"recommended_action": "Prioritize white-background Kami-style reports with readable charts and stable navigation.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-1",
|
||||
"excerpt": "新生成的 Skill 报告默认使用中文简体，并在右上角提供英文切换。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-3",
|
||||
"excerpt": "报告排版采用白底 Kami 风格，图表、模块和导航都要清晰。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "approval_safety",
|
||||
"label": "Approval and privacy boundary",
|
||||
"signal_type": "governance",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated governance signals.",
|
||||
"recommended_action": "Keep adaptive work proposal-only until a reviewer approves an allowlisted patch path.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-5",
|
||||
"excerpt": "自适应升级必须先生成提案，不能直接自动修改源文件。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "delivery_format",
|
||||
"label": "Delivery format preference",
|
||||
"signal_type": "artifact-format",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated artifact-format signals.",
|
||||
"recommended_action": "Surface stable artifact paths and formats in CLI output and generated summaries.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-2",
|
||||
"excerpt": "HTML 报告需要双语能力，但默认内容应该保持中文简体。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-6",
|
||||
"excerpt": "用户偏好扫描必须由用户提供明确路径，不要默认扫描私人日志。"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"pattern_id": "evidence_testing",
|
||||
"label": "Evidence and testing preference",
|
||||
"signal_type": "quality-gate",
|
||||
"support_count": 2,
|
||||
"confidence": 0.79,
|
||||
"reason": "2 redacted records matched repeated quality-gate signals.",
|
||||
"recommended_action": "Attach focused tests and refreshed evidence reports to every non-trivial skill upgrade.",
|
||||
"evidence": [
|
||||
{
|
||||
"record_id": "line-7",
|
||||
"excerpt": "每次升级都需要测试、覆盖报告和可审计证据，推送前要跑 CI。"
|
||||
},
|
||||
{
|
||||
"record_id": "line-8",
|
||||
"excerpt": "涉及 GitHub 推送时，要保留证据链，避免把计划当作完成证明。"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"proposals": [
|
||||
{
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"risk_level": "low",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"risk_level": "medium",
|
||||
"status": "proposal-only",
|
||||
"requires_approval": true,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"opportunity_summary": {
|
||||
"opportunity_count": 5,
|
||||
"top_score": 88,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"action_type_counts": {
|
||||
"patch_existing_skill": 3,
|
||||
"agents_update": 1,
|
||||
"add_eval": 1
|
||||
},
|
||||
"decision_counts": {
|
||||
"ready_for_approval_review": 1,
|
||||
"proposal_review": 4
|
||||
}
|
||||
},
|
||||
"opportunities": [
|
||||
{
|
||||
"opportunity_id": "skillops-4ad91c18dd",
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"opportunity_type": "artifact-quality",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "ready_for_approval_review",
|
||||
"priority": "medium",
|
||||
"score": 88,
|
||||
"score_reasons": [
|
||||
"support_count=5",
|
||||
"confidence=0.95",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 5,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-531e13c1c6",
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"opportunity_type": "governance",
|
||||
"action_type": "agents_update",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-709ef884f3",
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"opportunity_type": "report-experience",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated language preferences can improve existing report templates after approval.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-f9e43237aa",
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"opportunity_type": "artifact-discoverability",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
]
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-0a3a2de7c3",
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"opportunity_type": "quality-gate",
|
||||
"action_type": "add_eval",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 74,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated verification and evidence requests should become focused checks.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
]
|
||||
}
|
||||
],
|
||||
"decision_policy": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "skillops-opportunity-scoring",
|
||||
"score_range": [
|
||||
0,
|
||||
100
|
||||
],
|
||||
"score_bands": {
|
||||
"85-100": "ready_for_approval_review",
|
||||
"70-84": "proposal_review",
|
||||
"50-69": "observe_more_evidence",
|
||||
"0-49": "report_only_or_no_action"
|
||||
},
|
||||
"action_types": [
|
||||
"add_eval",
|
||||
"agents_update",
|
||||
"patch_existing_skill",
|
||||
"report_only"
|
||||
],
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"approval_required_for_writes": true
|
||||
},
|
||||
"approval": {
|
||||
"approval_count": 0,
|
||||
"pending_review_count": 0,
|
||||
"applied_count": 0,
|
||||
"rollback_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true
|
||||
},
|
||||
"actions": [
|
||||
{
|
||||
"key": "review-adaptation-proposals",
|
||||
"priority": "high",
|
||||
"action": "Review proposal-only adaptation items before preparing any approval ledger entry."
|
||||
},
|
||||
{
|
||||
"key": "close-world-class-evidence",
|
||||
"priority": "high",
|
||||
"action": "Collect accepted external or human evidence for the pending world-class ledger entries."
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"source_reports": {
|
||||
"patterns": "reports/user_patterns.json",
|
||||
"proposals": "reports/adaptation_proposals.json",
|
||||
"approval_ledger": "reports/adaptation_approval_ledger.json",
|
||||
"regression": "reports/adaptation_regression_report.json",
|
||||
"skill_os2_coverage": "reports/skill_os2_coverage.json",
|
||||
"world_class_ledger": "reports/world_class_evidence_ledger.json",
|
||||
"evidence_consistency": "reports/evidence_consistency.json",
|
||||
"benchmark_reproducibility": "reports/benchmark_reproducibility.json"
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skillops/daily/2026-07-02.json",
|
||||
"markdown": "reports/skillops/daily/2026-07-02.md"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,174 @@
|
||||
# Daily SkillOps Report
|
||||
|
||||
Generated at: `2026-07-02T06:33:07Z`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `proposal-review`
|
||||
- source supplied: `false`
|
||||
- patterns: `5`
|
||||
- proposals: `5`
|
||||
- pending approvals: `0`
|
||||
- applied patches: `0`
|
||||
- rollbacks: `0`
|
||||
- local blueprint ready: `true`
|
||||
- public world-class ready: `false`
|
||||
- world-class pending: `4`
|
||||
- release lock ready: `false`
|
||||
- evidence consistency ok: `true`
|
||||
|
||||
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
|
||||
|
||||
## Privacy Boundary
|
||||
|
||||
- explicit_source_required_for_scan: `true`
|
||||
- implicit_private_log_scan: `false`
|
||||
- raw_content_stored: `false`
|
||||
- redacted_excerpts_only: `true`
|
||||
- proposal_only: `true`
|
||||
- approval_required_for_writes: `true`
|
||||
- writes_source_files: `false`
|
||||
- auto_patch_enabled: `false`
|
||||
- daily_report_counts_as_world_class_evidence: `false`
|
||||
|
||||
## Actions
|
||||
|
||||
- `high` Review proposal-only adaptation items before preparing any approval ledger entry.
|
||||
- `high` Collect accepted external or human evidence for the pending world-class ledger entries.
|
||||
|
||||
## Opportunities
|
||||
|
||||
- count: `5`
|
||||
- top score: `88`
|
||||
- ready for approval review: `1`
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `skillops-4ad91c18dd`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `ready_for_approval_review`
|
||||
- Score: `88`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes.
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `skillops-531e13c1c6`
|
||||
- Action: `agents_update`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated privacy and approval signals should tighten durable operating guidance.
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `skillops-709ef884f3`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated language preferences can improve existing report templates after approval.
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `skillops-f9e43237aa`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability.
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `skillops-0a3a2de7c3`
|
||||
- Action: `add_eval`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `74`
|
||||
- Risk: `medium`
|
||||
- Policy: Repeated verification and evidence requests should become focused checks.
|
||||
|
||||
## Patterns
|
||||
|
||||
- `language_default`: Default language preference (support `2`, confidence `0.79`)
|
||||
- `report_ui`: Report UI and visualization preference (support `5`, confidence `0.95`)
|
||||
- `approval_safety`: Approval and privacy boundary (support `2`, confidence `0.79`)
|
||||
- `delivery_format`: Delivery format preference (support `2`, confidence `0.79`)
|
||||
- `evidence_testing`: Evidence and testing preference (support `2`, confidence `0.79`)
|
||||
|
||||
## Proposals
|
||||
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `adapt-18c7517f3d`
|
||||
- Pattern: `language_default`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `adapt-fbfe921ba5`
|
||||
- Pattern: `report_ui`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/render_skill_overview.py`
|
||||
- `references/artifact-design-doctrine.md`
|
||||
- `tests/verify_skill_overview.py`
|
||||
- Verification:
|
||||
- `python3 tests/verify_skill_overview.py`
|
||||
- `python3 tests/verify_skill_report_charts.py`
|
||||
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `adapt-59d219a1fb`
|
||||
- Pattern: `approval_safety`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `references/user-memory-policy.md`
|
||||
- `references/autonomous-adaptation.md`
|
||||
- `schemas/adaptation-proposal.schema.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `adapt-457baca160`
|
||||
- Pattern: `delivery_format`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `low`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `scripts/yao.py`
|
||||
- `README.md`
|
||||
- Verification:
|
||||
- `python3 tests/verify_yao_cli.py`
|
||||
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `adapt-abfee25d3a`
|
||||
- Pattern: `evidence_testing`
|
||||
- Status: `proposal-only`
|
||||
- Risk: `medium`
|
||||
- Requires approval: `true`
|
||||
- Target files:
|
||||
- `tests/verify_adaptation_safety.py`
|
||||
- `scripts/render_skill_os2_coverage.py`
|
||||
- `reports/skill_os2_coverage.json`
|
||||
- Verification:
|
||||
- `python3 tests/verify_adaptation_safety.py`
|
||||
- `python3 tests/verify_skill_os2_coverage.py`
|
||||
|
||||
## Evidence
|
||||
|
||||
- patterns: `reports/user_patterns.json`
|
||||
- proposals: `reports/adaptation_proposals.json`
|
||||
- approval_ledger: `reports/adaptation_approval_ledger.json`
|
||||
- regression: `reports/adaptation_regression_report.json`
|
||||
- skill_os2_coverage: `reports/skill_os2_coverage.json`
|
||||
- world_class_ledger: `reports/world_class_evidence_ledger.json`
|
||||
- evidence_consistency: `reports/evidence_consistency.json`
|
||||
- benchmark_reproducibility: `reports/benchmark_reproducibility.json`
|
||||
@@ -1,21 +1,21 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-17T08:58:54Z",
|
||||
"generated_at": "2026-06-21",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
"daily_report_count": 2,
|
||||
"opportunity_count": 10,
|
||||
"daily_report_count": 4,
|
||||
"opportunity_count": 20,
|
||||
"unique_opportunity_count": 5,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -25,17 +25,17 @@
|
||||
"summary": {
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W25",
|
||||
"daily_report_count": 2,
|
||||
"opportunity_count": 10,
|
||||
"daily_report_count": 4,
|
||||
"opportunity_count": 20,
|
||||
"unique_opportunity_count": 5,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"top_score": 88,
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
@@ -90,7 +90,9 @@
|
||||
},
|
||||
"daily_reports": [
|
||||
"reports/skillops/daily/2026-06-16.json",
|
||||
"reports/skillops/daily/2026-06-17.json"
|
||||
"reports/skillops/daily/2026-06-17.json",
|
||||
"reports/skillops/daily/2026-06-20.json",
|
||||
"reports/skillops/daily/2026-06-21.json"
|
||||
],
|
||||
"opportunity_summary": {
|
||||
"action_type_counts": {
|
||||
@@ -275,20 +277,20 @@
|
||||
}
|
||||
],
|
||||
"portfolio": {
|
||||
"skill_count": 12,
|
||||
"skill_count": 11,
|
||||
"actionable_issue_count": 0,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 9,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 10,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"release_lock_ready": true,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
|
||||
@@ -1,19 +1,19 @@
|
||||
# Weekly SkillOps Curator Report
|
||||
|
||||
Generated at: `2026-06-17T08:58:54Z`
|
||||
Generated at: `2026-06-21`
|
||||
Week: `2026-W25`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `curator-review`
|
||||
- daily_report_count: `2`
|
||||
- daily_report_count: `4`
|
||||
- unique_opportunity_count: `5`
|
||||
- ready_for_approval_review_count: `1`
|
||||
- proposal_review_count: `4`
|
||||
- top_score: `88`
|
||||
- skill_count: `12`
|
||||
- skill_count: `11`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `False`
|
||||
- release_lock_ready: `True`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
@@ -89,13 +89,13 @@ This report is a weekly curator cockpit for generated SkillOps evidence. It does
|
||||
|
||||
## Portfolio Signals
|
||||
|
||||
- skill_count: `12`
|
||||
- skill_count: `11`
|
||||
- actionable_issue_count: `0`
|
||||
- route_collision_count: `5`
|
||||
- actionable_route_collision_count: `0`
|
||||
- owner_gap_count: `9`
|
||||
- owner_gap_count: `8`
|
||||
- actionable_owner_gap_count: `0`
|
||||
- stale_count: `10`
|
||||
- stale_count: `9`
|
||||
- actionable_stale_count: `0`
|
||||
- drift_signal_count: `0`
|
||||
- actionable_drift_signal_count: `0`
|
||||
|
||||
@@ -0,0 +1,323 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-07-02T06:33:07Z",
|
||||
"skill_dir": ".",
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W27",
|
||||
"daily_report_count": 5,
|
||||
"opportunity_count": 25,
|
||||
"unique_opportunity_count": 5,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"top_score": 88,
|
||||
"skill_count": 11,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0,
|
||||
"summary": {
|
||||
"decision": "curator-review",
|
||||
"week_id": "2026-W27",
|
||||
"daily_report_count": 5,
|
||||
"opportunity_count": 25,
|
||||
"unique_opportunity_count": 5,
|
||||
"ready_for_approval_review_count": 1,
|
||||
"proposal_review_count": 4,
|
||||
"observe_more_evidence_count": 0,
|
||||
"report_only_count": 0,
|
||||
"top_score": 88,
|
||||
"skill_count": 11,
|
||||
"actionable_portfolio_issue_count": 0,
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"failure_count": 0
|
||||
},
|
||||
"curator_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "weekly-skillops-curator-report",
|
||||
"cadence": "weekly",
|
||||
"source_of_truth": [
|
||||
"reports/skillops/daily/*.json",
|
||||
"reports/skill_atlas.json",
|
||||
"reports/benchmark_reproducibility.json",
|
||||
"reports/evidence_consistency.json",
|
||||
"reports/world_class_evidence_ledger.json"
|
||||
],
|
||||
"raw_content_stored": false,
|
||||
"redacted_or_generated_evidence_only": true,
|
||||
"proposal_only": true,
|
||||
"writes_source_files": false,
|
||||
"auto_patch_enabled": false,
|
||||
"approval_required_for_writes": true,
|
||||
"counts_as_world_class_evidence": false
|
||||
},
|
||||
"report_contract": {
|
||||
"schema_version": "1.0",
|
||||
"contract": "weekly-skillops-curator-report",
|
||||
"top_level_mirrors_summary": true,
|
||||
"summary_fields": [
|
||||
"decision",
|
||||
"week_id",
|
||||
"daily_report_count",
|
||||
"opportunity_count",
|
||||
"unique_opportunity_count",
|
||||
"ready_for_approval_review_count",
|
||||
"proposal_review_count",
|
||||
"observe_more_evidence_count",
|
||||
"report_only_count",
|
||||
"top_score",
|
||||
"skill_count",
|
||||
"actionable_portfolio_issue_count",
|
||||
"release_lock_ready",
|
||||
"evidence_consistency_ok",
|
||||
"public_world_class_ready",
|
||||
"world_class_pending_count",
|
||||
"writes_source_files",
|
||||
"auto_patch_enabled",
|
||||
"failure_count"
|
||||
]
|
||||
},
|
||||
"daily_reports": [
|
||||
"reports/skillops/daily/2026-06-16.json",
|
||||
"reports/skillops/daily/2026-06-17.json",
|
||||
"reports/skillops/daily/2026-06-20.json",
|
||||
"reports/skillops/daily/2026-06-21.json",
|
||||
"reports/skillops/daily/2026-07-02.json"
|
||||
],
|
||||
"opportunity_summary": {
|
||||
"action_type_counts": {
|
||||
"add_eval": 1,
|
||||
"agents_update": 1,
|
||||
"patch_existing_skill": 3
|
||||
},
|
||||
"decision_counts": {
|
||||
"proposal_review": 4,
|
||||
"ready_for_approval_review": 1
|
||||
},
|
||||
"risk_level_counts": {
|
||||
"low": 3,
|
||||
"medium": 2
|
||||
}
|
||||
},
|
||||
"curator_queue": [
|
||||
{
|
||||
"opportunity_id": "skillops-4ad91c18dd",
|
||||
"proposal_id": "adapt-fbfe921ba5",
|
||||
"pattern_id": "report_ui",
|
||||
"title": "Improve report layout, visual hierarchy, and chart readability",
|
||||
"opportunity_type": "artifact-quality",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "ready_for_approval_review",
|
||||
"priority": "medium",
|
||||
"score": 88,
|
||||
"score_reasons": [
|
||||
"support_count=5",
|
||||
"confidence=0.95",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 5,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md",
|
||||
"tests/verify_skill_overview.py"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py",
|
||||
"python3 tests/verify_skill_report_charts.py"
|
||||
],
|
||||
"daily_report_date": "2026-06-16"
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-531e13c1c6",
|
||||
"proposal_id": "adapt-59d219a1fb",
|
||||
"pattern_id": "approval_safety",
|
||||
"title": "Keep adaptive iteration approval-gated",
|
||||
"opportunity_type": "governance",
|
||||
"action_type": "agents_update",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"references/user-memory-policy.md",
|
||||
"references/autonomous-adaptation.md",
|
||||
"schemas/adaptation-proposal.schema.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py"
|
||||
],
|
||||
"daily_report_date": "2026-06-16"
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-709ef884f3",
|
||||
"proposal_id": "adapt-18c7517f3d",
|
||||
"pattern_id": "language_default",
|
||||
"title": "Keep reports Chinese-first with optional English",
|
||||
"opportunity_type": "report-experience",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated language preferences can improve existing report templates after approval.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/render_skill_overview.py",
|
||||
"references/artifact-design-doctrine.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_skill_overview.py"
|
||||
],
|
||||
"daily_report_date": "2026-06-16"
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-f9e43237aa",
|
||||
"proposal_id": "adapt-457baca160",
|
||||
"pattern_id": "delivery_format",
|
||||
"title": "Make generated artifact paths explicit in CLI output",
|
||||
"opportunity_type": "artifact-discoverability",
|
||||
"action_type": "patch_existing_skill",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 82,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=low",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.",
|
||||
"risk_level": "low",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"scripts/yao.py",
|
||||
"README.md"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_yao_cli.py"
|
||||
],
|
||||
"daily_report_date": "2026-06-16"
|
||||
},
|
||||
{
|
||||
"opportunity_id": "skillops-0a3a2de7c3",
|
||||
"proposal_id": "adapt-abfee25d3a",
|
||||
"pattern_id": "evidence_testing",
|
||||
"title": "Attach tests and evidence refresh to each upgrade",
|
||||
"opportunity_type": "quality-gate",
|
||||
"action_type": "add_eval",
|
||||
"decision": "proposal_review",
|
||||
"priority": "medium",
|
||||
"score": 74,
|
||||
"score_reasons": [
|
||||
"support_count=2",
|
||||
"confidence=0.79",
|
||||
"risk=medium",
|
||||
"target_files_present",
|
||||
"verification_present",
|
||||
"approval_required"
|
||||
],
|
||||
"policy_reason": "Repeated verification and evidence requests should become focused checks.",
|
||||
"risk_level": "medium",
|
||||
"requires_approval": true,
|
||||
"write_allowed_without_approval": false,
|
||||
"evidence_count": 2,
|
||||
"target_files": [
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"scripts/render_skill_os2_coverage.py",
|
||||
"reports/skill_os2_coverage.json"
|
||||
],
|
||||
"verification_commands": [
|
||||
"python3 tests/verify_adaptation_safety.py",
|
||||
"python3 tests/verify_skill_os2_coverage.py"
|
||||
],
|
||||
"daily_report_date": "2026-06-16"
|
||||
}
|
||||
],
|
||||
"portfolio": {
|
||||
"skill_count": 11,
|
||||
"actionable_issue_count": 0,
|
||||
"route_collision_count": 5,
|
||||
"actionable_route_collision_count": 0,
|
||||
"owner_gap_count": 8,
|
||||
"actionable_owner_gap_count": 0,
|
||||
"stale_count": 9,
|
||||
"actionable_stale_count": 0,
|
||||
"drift_signal_count": 0,
|
||||
"actionable_drift_signal_count": 0,
|
||||
"no_route_opportunity_count": 0
|
||||
},
|
||||
"release_state": {
|
||||
"release_lock_ready": false,
|
||||
"evidence_consistency_ok": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_pending_count": 4
|
||||
},
|
||||
"actions": [
|
||||
{
|
||||
"key": "review-ready-opportunities",
|
||||
"priority": "high",
|
||||
"action": "Review the top ready-for-approval SkillOps opportunities before preparing any approval ledger entry."
|
||||
},
|
||||
{
|
||||
"key": "close-world-class-evidence",
|
||||
"priority": "high",
|
||||
"action": "Collect accepted external or human evidence for pending world-class ledger entries before public claims."
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"source_reports": {
|
||||
"daily_dir": "reports/skillops/daily",
|
||||
"skill_atlas": "reports/skill_atlas.json",
|
||||
"benchmark_reproducibility": "reports/benchmark_reproducibility.json",
|
||||
"evidence_consistency": "reports/evidence_consistency.json",
|
||||
"world_class_ledger": "reports/world_class_evidence_ledger.json"
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skillops/weekly/2026-W27.json",
|
||||
"markdown": "reports/skillops/weekly/2026-W27.md"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,110 @@
|
||||
# Weekly SkillOps Curator Report
|
||||
|
||||
Generated at: `2026-07-02T06:33:07Z`
|
||||
Week: `2026-W27`
|
||||
|
||||
## Summary
|
||||
|
||||
- decision: `curator-review`
|
||||
- daily_report_count: `5`
|
||||
- unique_opportunity_count: `5`
|
||||
- ready_for_approval_review_count: `1`
|
||||
- proposal_review_count: `4`
|
||||
- top_score: `88`
|
||||
- skill_count: `11`
|
||||
- actionable_portfolio_issue_count: `0`
|
||||
- release_lock_ready: `False`
|
||||
- evidence_consistency_ok: `True`
|
||||
- public_world_class_ready: `False`
|
||||
- world_class_pending_count: `4`
|
||||
|
||||
This report is a weekly curator cockpit for generated SkillOps evidence. It does not scan private logs, write source files, apply patches, or count as world-class evidence.
|
||||
|
||||
## Curator Boundary
|
||||
|
||||
- raw_content_stored: `false`
|
||||
- redacted_or_generated_evidence_only: `true`
|
||||
- proposal_only: `true`
|
||||
- writes_source_files: `false`
|
||||
- auto_patch_enabled: `false`
|
||||
- approval_required_for_writes: `true`
|
||||
- counts_as_world_class_evidence: `false`
|
||||
|
||||
## Actions
|
||||
|
||||
- `high` Review the top ready-for-approval SkillOps opportunities before preparing any approval ledger entry.
|
||||
- `high` Collect accepted external or human evidence for pending world-class ledger entries before public claims.
|
||||
|
||||
## Curator Queue
|
||||
|
||||
### Improve report layout, visual hierarchy, and chart readability
|
||||
|
||||
- ID: `skillops-4ad91c18dd`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `ready_for_approval_review`
|
||||
- Score: `88`
|
||||
- Risk: `medium`
|
||||
- Source day: `2026-06-16`
|
||||
- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes.
|
||||
|
||||
### Keep adaptive iteration approval-gated
|
||||
|
||||
- ID: `skillops-531e13c1c6`
|
||||
- Action: `agents_update`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Source day: `2026-06-16`
|
||||
- Policy: Repeated privacy and approval signals should tighten durable operating guidance.
|
||||
|
||||
### Keep reports Chinese-first with optional English
|
||||
|
||||
- ID: `skillops-709ef884f3`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Source day: `2026-06-16`
|
||||
- Policy: Repeated language preferences can improve existing report templates after approval.
|
||||
|
||||
### Make generated artifact paths explicit in CLI output
|
||||
|
||||
- ID: `skillops-f9e43237aa`
|
||||
- Action: `patch_existing_skill`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `82`
|
||||
- Risk: `low`
|
||||
- Source day: `2026-06-16`
|
||||
- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability.
|
||||
|
||||
### Attach tests and evidence refresh to each upgrade
|
||||
|
||||
- ID: `skillops-0a3a2de7c3`
|
||||
- Action: `add_eval`
|
||||
- Decision: `proposal_review`
|
||||
- Score: `74`
|
||||
- Risk: `medium`
|
||||
- Source day: `2026-06-16`
|
||||
- Policy: Repeated verification and evidence requests should become focused checks.
|
||||
|
||||
## Portfolio Signals
|
||||
|
||||
- skill_count: `11`
|
||||
- actionable_issue_count: `0`
|
||||
- route_collision_count: `5`
|
||||
- actionable_route_collision_count: `0`
|
||||
- owner_gap_count: `8`
|
||||
- actionable_owner_gap_count: `0`
|
||||
- stale_count: `9`
|
||||
- actionable_stale_count: `0`
|
||||
- drift_signal_count: `0`
|
||||
- actionable_drift_signal_count: `0`
|
||||
- no_route_opportunity_count: `0`
|
||||
|
||||
## Evidence
|
||||
|
||||
- daily_dir: `reports/skillops/daily`
|
||||
- skill_atlas: `reports/skill_atlas.json`
|
||||
- benchmark_reproducibility: `reports/benchmark_reproducibility.json`
|
||||
- evidence_consistency: `reports/evidence_consistency.json`
|
||||
- world_class_ledger: `reports/world_class_evidence_ledger.json`
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user