diff --git a/SKILL.md b/SKILL.md index ff429c5..a2c7a6e 100644 --- a/SKILL.md +++ b/SKILL.md @@ -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). diff --git a/registry/index.json b/registry/index.json index 6e2ea75..1e1bc3f 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index c6c2310..47fad70 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,7 +16,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json index bfc1ca8..7a9bd9a 100644 --- a/reports/adaptation_proposals.json +++ b/reports/adaptation_proposals.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md index 61b2ec9..fa7315a 100644 --- a/reports/adaptation_proposals.md +++ b/reports/adaptation_proposals.md @@ -1,6 +1,6 @@ # Adaptation Proposals -- Generated at: `2026-07-02T03:41:56Z` +- Generated at: `2026-07-02T06:33:07Z` - Pattern report: `reports/user_patterns.json` - Proposal only: `true` - Writes repository files: `false` diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index a34b0ca..94719e6 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-07-02T03:42:30Z", + "generated_at": "2026-07-02T06:33:44Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 29ac364..d71ba77 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,32 +3,31 @@ "ok": true, "generated_at": "2026-07-02", "skill_dir": ".", - "commit": "1710a5a3e0177313954758908735c147796e8981", + "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "git_status": { "available": true, "dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "generated_dirty": true, - "generated_changed_file_count": 82, + "generated_changed_file_count": 36, "source_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "sample": [ " M SKILL.md", - " M evals/improved_description.txt", " 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/artifact-design-profile.json", - " M reports/artifact-design-profile.md", - " M reports/baseline-compare.json", " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md" + " 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": [ - " M SKILL.md", - " M evals/improved_description.txt" + " M SKILL.md" ], "generated_sample": [ " M registry/index.json", @@ -36,13 +35,13 @@ " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", - " M reports/artifact-design-profile.json", - " M reports/artifact-design-profile.md", - " M reports/baseline-compare.json", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", - " M reports/candidate_registry.json", - " M reports/candidate_registry.md" + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json" ], "generated_dirty_prefixes": [ "dist/", @@ -60,8 +59,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -85,11 +84,11 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, "beta_test_release": { "ready": false, @@ -135,10 +134,10 @@ }, "release_lock": { "ready": false, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 2, - "generated_changed_file_count": 82, + "source_changed_file_count": 1, + "generated_changed_file_count": 36, "reason": "source files were dirty at generation time" }, "evidence_bundle": { @@ -147,7 +146,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873" + "sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -256,7 +255,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 139090, - "sha256": "ffe2c88bbdbac4907bf8db8f01b9a6b2da78e83acdffb3d975e99424274cd9f7" + "sha256": "108aee597a1f245f73d9b69454b6fa8a144545f905231a7c314364c7066541c6" }, { "label": "python_compatibility", @@ -270,7 +269,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3155, - "sha256": "9be6de364d69a2ad40b68b460a35c91476e822eb008cfe4d5e8614c1e989d3d4" + "sha256": "d307675d5c6c3cd2f104ce7d963b37d36113f35334e4c6895b55fbb8b255e915" }, { "label": "package_verification", @@ -318,8 +317,8 @@ "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 90852, - "sha256": "a0b00eed5450b33ec29fea6652d41db216931452eeddd0d99f2d90aa20c44d95" + "bytes": 90854, + "sha256": "06e93b1c0c99107002466d9418a4910c82397bce26c3bbdd5b5cc9875eeb65b2" }, { "label": "world_class_submission_review", @@ -353,8 +352,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 20102, - "sha256": "5eb808496802e8f972e5aa738d99f3b4a37ff34c8ab495f25ff2db3e7237239f" + "bytes": 20713, + "sha256": "911ba833055ab857250f88d88ccdd0bb652076a81214f725c49d763352035572" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 38ce2c6..7cd3bf8 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,11 +1,11 @@ # Benchmark Reproducibility Generated at: `2026-07-02` -Commit: `1710a5a3e0177313954758908735c147796e8981` +Commit: `24bea607a2b16e766bc8f2bc8483f22fae1edc61` Working tree dirty at generation: `true` Source tree dirty at generation: `true` Generated evidence dirty at generation: `true` -Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873` +Evidence bundle SHA256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158` ## Summary @@ -14,7 +14,7 @@ Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc3 - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `e0863533e0a0` +- source contract sha256: `db71157184dc` - archive sha256: `c56a8519244c` - output cases: `5` - disclosed failure cases: `3` @@ -28,9 +28,9 @@ Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc3 - beta deferred evidence: `4` - public claim ready: `false` - public claim blockers: `4` -- changed files at generation: `84` -- source changed files at generation: `2` -- generated changed files at generation: `82` +- 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. @@ -75,7 +75,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `25` / `25` -- sha256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873` +- sha256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158` ## Methodology Sections @@ -102,21 +102,21 @@ This report proves local benchmark reproducibility only. It keeps external provi | review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` | | trigger_scorecard | `reports/route_scorecard.json` | present | `53fc22d220dc` | | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `ffe2c88bbdba` | +| trust_report | `reports/security_trust_report.json` | present | `108aee597a1f` | | python_compatibility | `reports/python_compatibility.json` | present | `4d82942052a2` | -| registry_audit | `reports/registry_audit.json` | present | `9be6de364d69` | +| 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 | `a0b00eed5450` | +| 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 | `5eb808496802` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `911ba833055a` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 54a0825..98d3f8c 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -77,17 +77,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -1034,17 +1034,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -1991,17 +1991,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -2932,17 +2932,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -3873,17 +3873,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", diff --git a/reports/context_budget.json b/reports/context_budget.json index 8a71ea1..28065fb 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -5,10 +5,10 @@ "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, - "skill_body_tokens": 806, - "other_text_tokens": 1200438, - "estimated_initial_load_tokens": 999, - "estimated_total_text_tokens": 1201244, + "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": [ @@ -66,9 +66,9 @@ ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 590, + "relevant_file_count": 591, "unused_resource_dirs": [], "quality_signal_points": 140, - "quality_density": 140.1 + "quality_density": 141.8 } } diff --git a/reports/context_budget.md b/reports/context_budget.md index 66d0f51..1127edf 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 999 | 806 | 531767 | `governed` | scripts:469568 | 140.1 | - | 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 | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 877503b..c198f8d 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -6,8 +6,8 @@ "path": ".", "budget_tier": "production", "budget_limit": 1000, - "initial_tokens": 999, - "skill_body_tokens": 806, + "initial_tokens": 987, + "skill_body_tokens": 794, "deferred_resource_tokens": 531767, "large_deferred_resource_dirs": [ { @@ -42,7 +42,7 @@ ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "quality_density": 140.1, + "quality_density": 141.8, "unused_resource_dirs": [], "ok": true, "warnings": [] diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 9318547..1468539 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -324,12 +324,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 999/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 140.1", + "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 999/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 140.1", + "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": [ @@ -357,7 +357,7 @@ "actual": { "available": true, "clean": false, - "changed_file_count": 76 + "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": "1710a5a3e0177313954758908735c147796e8981", - "actual": "1710a5a3e0177313954758908735c147796e8981", + "expected": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", + "actual": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -414,7 +414,7 @@ "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "f0333ea256d221c8993809b4366f93d9874defe6c722fbf95c8f524bdf9d3289", + "source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, @@ -430,7 +430,7 @@ "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "f0333ea256d221c8993809b4366f93d9874defe6c722fbf95c8f524bdf9d3289", + "source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, @@ -550,8 +550,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "1710a5a3e0177313954758908735c147796e8981", - "actual": "1710a5a3e0177313954758908735c147796e8981", + "expected": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", + "actual": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -566,7 +566,7 @@ "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "f0333ea256d221c8993809b4366f93d9874defe6c722fbf95c8f524bdf9d3289", + "source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, @@ -582,7 +582,7 @@ "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "f0333ea256d221c8993809b4366f93d9874defe6c722fbf95c8f524bdf9d3289", + "source_contract_sha256": "b5cfa61c532d9ecd55d4d3a91aaf249bab0393251319a0f391422edb07a9e658", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 19, @@ -739,7 +739,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 342 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 342 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 342 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 342 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。" ] @@ -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 342 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 342 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 342 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 342 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。" }, { @@ -2139,8 +2139,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 2, "submission_ref_ready_count": 2, - "supporting_evidence_total_count": 8, - "supporting_evidence_ready_count": 7, + "supporting_evidence_total_count": 11, + "supporting_evidence_ready_count": 11, "submission_ref_copy_to_artifact_refs": true, "supporting_evidence_copy_to_artifact_refs": false }, @@ -2185,8 +2185,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 2, "submission_ref_ready_count": 2, - "supporting_evidence_total_count": 8, - "supporting_evidence_ready_count": 7, + "supporting_evidence_total_count": 11, + "supporting_evidence_ready_count": 11, "submission_ref_copy_to_artifact_refs": true, "supporting_evidence_copy_to_artifact_refs": false }, @@ -3200,7 +3200,9 @@ "agents/interface.yaml": true, "evidence/world_class/README.md": true, "security/permission_policy.json": true, - "reports/world_class_evidence_ledger.json": true + "reports/world_class_evidence_ledger.json": true, + "dist/manifest.json": true, + "dist/targets/openai/adapter.json": true }, "prohibited_surfaces": [] }, @@ -3219,7 +3221,9 @@ "agents/interface.yaml": true, "evidence/world_class/README.md": true, "security/permission_policy.json": true, - "reports/world_class_evidence_ledger.json": true + "reports/world_class_evidence_ledger.json": true, + "dist/manifest.json": true, + "dist/targets/openai/adapter.json": true }, "prohibited_surfaces": [] }, @@ -3581,7 +3585,7 @@ "`0` permission failures", "`25` required artifacts", "`23` reproduction commands", - "initial load `999/1000`", + "initial load `987/1000`", "target count is `83`" ], "actual": "all present", diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 356a913..902803e 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,7 +21,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 852f7c5..048b3cf 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,7 +6,7 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3` +- Package SHA256: `db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c` - Archive SHA256: `c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7` - Install simulated: `True` diff --git a/reports/review-studio.html b/reports/review-studio.html index c4fac5d..76d880d 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -772,12 +772,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 10; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

155 scripts scanned; secrets found

Py Compat0

235 files scanned for Python 3.11

Arch Debt0

719 largest lines; 0 watchlist; 6 early; 71 CLI handlers; 18 in entrypoint

Atlas5

11 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

194 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

580 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 10; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

2.0 coverage; extensions partial 0, planned 0; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

155 scripts scanned; secrets found

Py Compat0

235 files scanned for Python 3.11

Arch Debt0

719 largest lines; 0 watchlist; 6 early; 71 CLI handlers; 18 in entrypoint

Atlas5

11 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Daily Ops5

proposal-review; approval 0; release lock false

Weekly Queue5

curator-review; ready 1; top score 88

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

201 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

580 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 10; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 999/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 140.1

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 155 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 235 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

232 Python files; 0 hotspots; 0 watchlist files; 6 early watch files; 0 blockers; largest 719 lines; 71 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

11 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 22 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 12/19 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md 证据
+
通过

意图画布

intent confidence 100/100; Intent is clear enough to package the first routeable version.

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 10; recorded 0; reviewed 0/5; review pending 5

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 987/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 141.8

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 155 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 235 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

232 Python files; 0 hotspots; 0 watchlist files; 6 early watch files; 0 blockers; largest 719 lines; 71 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

3/3 permissions approved; gaps 0; required file_write, network, subprocess

reports/security_trust_report.json + security/permission_policy.json 证据
通过

权限探针

4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4

reports/runtime_permission_probes.json 证据
通过

组合治理

11 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 22 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false

reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 12/19 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures

reports/registry_audit.json + reports/install_simulation.json 证据
通过

发布路线

0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended

@@ -792,7 +792,7 @@

修复动作

-
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。

没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md + reports/output_review_decisions.json
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。

warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 10; token-observed 10

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
0 blocked / 3 pass
修复
1 repair rows; counts as completion: false
阶段
1 blocked phases; counts as completion: false
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查

暂无阻断检查。

阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: operator with provider credentialsevidence: provider-holdoutSet one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · precheckprovider-api-keyoperator with provider credentialsRequired env_any precheck is missing.Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.
  2. For OpenAI Responses: python3 scripts/yao.py output-exec --provider-runner openai --provider-model ${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini} --timeout-seconds 60
  3. For DeepSeek Chat Completions: python3 scripts/yao.py output-exec --provider-runner deepseek --provider-model deepseek-v4-flash --provider-api-format chat-completions --provider-thinking disabled --api-key-env DEEPSEEK_API_KEY --timeout-seconds 120
采集契约
来源要求
  • provider-backed model run
  • observed timing
  • observed token metadata
通过条件
  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass
证据资产
  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref1 / 1 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
5 blocked / 5 pass
修复
6 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: human reviewerevidence: human-adjudicationAssign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source5 / 5 blockedowners: human reviewerevidence: human-adjudicationSet reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · precheckhuman-reviewerhuman reviewerRequired human precheck is human-required.Assign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkblind_review_attestedhuman reviewerCurrent value False does not satisfy 'true'.Set reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkjudgment_counthuman reviewerCurrent value 0 does not satisfy '==pair_count'.Every pair needs one valid human judgment.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkpending_counthuman reviewerCurrent value 5 does not satisfy '==0'.Record a reviewer choice and reason for every pair.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkready_for_human_evidencehuman reviewerCurrent value False does not satisfy 'true'.Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkreviewer_metadata_presenthuman reviewerCurrent value False does not satisfy 'true'.Record reviewer and reviewed_at before adjudication can count.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
采集契约
来源要求
  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist
通过条件
  • reports/output_review_adjudication.json summary.pending_count == 0
  • reports/output_review_adjudication.json summary.judgment_count == summary.pair_count
  • reports/output_review_adjudication.json summary.invalid_decision_count == 0
  • reports/output_review_adjudication.json summary.reviewer_metadata_present is true
  • reports/output_review_adjudication.json summary.blind_review_attested is true
  • reports/output_review_adjudication.json review_integrity.blind_pack_sha256 exists and matches reports/output_review_decisions.json
  • reports/output_review_adjudication.json pairs and reviewer_checklist store prompt_sha256, not raw prompt text
  • reports/output_review_adjudication.json summary.ready_for_human_evidence is true
  • reports/skill_os2_audit.json item human-adjudication status becomes pass
证据资产
  • reports/output_blind_review_pack.md
  • reports/output_review_kit.md
  • reports/output_review_decisions.json
  • reports/output_review_adjudication.json
  • reports/output_review_adjudication.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence8 / 8 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Reviewer decisions should not include raw user data or private customer detail.
  • Reviewer reasons must be rubric-based and must not include raw user data or private customer detail.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • The adjudication evidence stores prompt_sha256 instead of raw prompt text.
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: target client or installer integratorevidence: native-permission-enforcementAttach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source1 / 1 blockedowners: target client or installer integratorevidence: native-permission-enforcementCollect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · prechecknative-guardtarget client or installer integratorRequired external precheck is external-required.Attach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checknative_enforcement_counttarget client or installer integratorCurrent value 0 does not satisfy '>0'.Collect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
采集契约
来源要求
  • real target client or external installer runtime guard
  • native enforcement flag or externally accepted guard proof
  • residual risk retained for fallback targets
通过条件
  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass
证据资产
  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence7 / 8 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.
pending · external

Native Client Telemetry

external source events 0; adoption samples 1

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: Browser/Chrome/IDE/provider client integratorevidence: native-client-telemetryInstall a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source1 / 1 blockedowners: Browser/Chrome/IDE/provider client integratorevidence: native-client-telemetryImport at least one metadata-only event from a real client.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
修复清单
  • #20 · unblock-access · precheckexternal-clientBrowser/Chrome/IDE/provider client integratorRequired external precheck is external-required.Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkexternal_source_eventsBrowser/Chrome/IDE/provider client integratorCurrent value 0 does not satisfy '>0'.Import at least one metadata-only event from a real client.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
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
采集契约
来源要求
  • real external client source
  • metadata-only event
  • local-first import path
通过条件
  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass
证据资产
  • reports/adoption_drift_report.json
  • reports/adoption_drift_report.md
  • reports/telemetry_hook_recipes.json
  • scripts/telemetry_native_host.py
  • evidence/world_class/intake.schema.json
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
+
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。同步补足盲审声明。

没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。
修复位置
evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_kit.html + reports/output_review_adjudication.md + reports/output_review_decisions.json
验证命令
python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review
关注

人工批准

对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。

warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。
修复位置
reports/review_waivers.md
验证命令
python3 scripts/render_review_waivers.py .
关注

世界证据

补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。

世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。
修复位置
reports/world_class_operator_runbook.html + reports/world_class_evidence_ledger.md + reports/world_class_evidence_intake.md + reports/world_class_submission_review.md
验证命令
python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py review-studio .

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 10; token-observed 10

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
0 blocked / 3 pass
修复
1 repair rows; counts as completion: false
阶段
1 blocked phases; counts as completion: false
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查

暂无阻断检查。

阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: operator with provider credentialsevidence: provider-holdoutSet one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · precheckprovider-api-keyoperator with provider credentialsRequired env_any precheck is missing.Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Set one provider API key in the operator shell, such as OPENAI_API_KEY or DEEPSEEK_API_KEY; never commit or print the value.
  2. For OpenAI Responses: python3 scripts/yao.py output-exec --provider-runner openai --provider-model ${YAO_OUTPUT_EVAL_MODEL:-gpt-4.1-mini} --timeout-seconds 60
  3. For DeepSeek Chat Completions: python3 scripts/yao.py output-exec --provider-runner deepseek --provider-model deepseek-v4-flash --provider-api-format chat-completions --provider-thinking disabled --api-key-env DEEPSEEK_API_KEY --timeout-seconds 120
采集契约
来源要求
  • provider-backed model run
  • observed timing
  • observed token metadata
通过条件
  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass
证据资产
  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref1 / 1 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
5 blocked / 5 pass
修复
6 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Record real A/B choices, reviewer metadata, and blind-review attestation, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice and reason for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • Reviewer metadatareviewer_metadata_present: False / trueRecord reviewer and reviewed_at before adjudication can count.
  • Blind review attestedblind_review_attested: False / trueSet reviewer_attestation only after choices are completed before opening the answer key.
  • Human evidence readyready_for_human_evidence: False / trueComplete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: human reviewerevidence: human-adjudicationAssign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source5 / 5 blockedowners: human reviewerevidence: human-adjudicationSet reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · precheckhuman-reviewerhuman reviewerRequired human precheck is human-required.Assign a real reviewer identity before claiming human adjudication.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkblind_review_attestedhuman reviewerCurrent value False does not satisfy 'true'.Set reviewer_attestation only after choices are completed before opening the answer key.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkjudgment_counthuman reviewerCurrent value 0 does not satisfy '==pair_count'.Every pair needs one valid human judgment.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkpending_counthuman reviewerCurrent value 5 does not satisfy '==0'.Record a reviewer choice and reason for every pair.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkready_for_human_evidencehuman reviewerCurrent value False does not satisfy 'true'.Complete all reviewer decisions with metadata and rationale, plus blind-review attestation and integrity fingerprints.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkreviewer_metadata_presenthuman reviewerCurrent value False does not satisfy 'true'.Record reviewer and reviewed_at before adjudication can count.python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
采集契约
来源要求
  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist
通过条件
  • reports/output_review_adjudication.json summary.pending_count == 0
  • reports/output_review_adjudication.json summary.judgment_count == summary.pair_count
  • reports/output_review_adjudication.json summary.invalid_decision_count == 0
  • reports/output_review_adjudication.json summary.reviewer_metadata_present is true
  • reports/output_review_adjudication.json summary.blind_review_attested is true
  • reports/output_review_adjudication.json review_integrity.blind_pack_sha256 exists and matches reports/output_review_decisions.json
  • reports/output_review_adjudication.json pairs and reviewer_checklist store prompt_sha256, not raw prompt text
  • reports/output_review_adjudication.json summary.ready_for_human_evidence is true
  • reports/skill_os2_audit.json item human-adjudication status becomes pass
证据资产
  • reports/output_blind_review_pack.md
  • reports/output_review_kit.md
  • reports/output_review_decisions.json
  • reports/output_review_adjudication.json
  • reports/output_review_adjudication.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence8 / 8 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Reviewer decisions should not include raw user data or private customer detail.
  • Reviewer reasons must be rubric-based and must not include raw user data or private customer detail.
  • The decision importer rejects raw prompt, output, transcript, message, and answer-key fields.
  • The adjudication evidence stores prompt_sha256 instead of raw prompt text.
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: target client or installer integratorevidence: native-permission-enforcementAttach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source1 / 1 blockedowners: target client or installer integratorevidence: native-permission-enforcementCollect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
修复清单
  • #20 · unblock-access · prechecknative-guardtarget client or installer integratorRequired external precheck is external-required.Attach a real target-client or external installer runtime guard; metadata fallback is not enough.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checknative_enforcement_counttarget client or installer integratorCurrent value 0 does not satisfy '>0'.Collect real target-client or external runtime guard proof.python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
采集契约
来源要求
  • real target client or external installer runtime guard
  • native enforcement flag or externally accepted guard proof
  • residual risk retained for fallback targets
通过条件
  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass
证据资产
  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence11 / 11 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.
pending · external

Native Client Telemetry

external source events 0; adoption samples 1

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
1 blocked / 2 pass
修复
2 repair rows; counts as completion: false
阶段
2 blocked phases; counts as completion: false
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
阶段队列
  • #20 · unblock-accessUnblock access1 / 1 blockedowners: Browser/Chrome/IDE/provider client integratorevidence: native-client-telemetryInstall a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-sourceCollect source1 / 1 blockedowners: Browser/Chrome/IDE/provider client integratorevidence: native-client-telemetryImport at least one metadata-only event from a real client.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
修复清单
  • #20 · unblock-access · precheckexternal-clientBrowser/Chrome/IDE/provider client integratorRequired external precheck is external-required.Install a real Browser, Chrome, IDE, or provider client that emits metadata-only events.python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions
  • #40 · collect-source · source-checkexternal_source_eventsBrowser/Chrome/IDE/provider client integratorCurrent value 0 does not satisfy '>0'.Import at least one metadata-only event from a real client.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
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. 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>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
采集契约
来源要求
  • real external client source
  • metadata-only event
  • local-first import path
通过条件
  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass
证据资产
  • reports/adoption_drift_report.json
  • reports/adoption_drift_report.md
  • reports/telemetry_hook_recipes.json
  • scripts/telemetry_native_host.py
  • evidence/world_class/intake.schema.json
资产角色

source: world-class-submission-kit; counts as evidence: false; prefill counts as evidence: false

  • submission-ref2 / 2 readyartifact_refs: trueRows marked submission-ref are the aggregate paths expected in artifact_refs.
  • supporting-evidence6 / 6 readyartifact_refs: falseSupporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.
隐私边界
  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
@@ -844,12 +844,12 @@
-

上下文

initial load 999/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 140.1

+

上下文

initial load 987/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 141.8

编译证据

Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.

-

信任报告

Secret
0
脚本数
155
网络脚本
3
Help 失败
0
包体哈希
e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3
+

信任报告

Secret
0
脚本数
155
网络脚本
3
Help 失败
0
包体哈希
db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c

安全边界

高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。

@@ -929,7 +929,7 @@
-

声明守卫

台账可声明
否
台账待补
4
声明面
194
违规数
0
Overclaim Guard Active
是
+

声明守卫

台账可声明
否
台账待补
4
声明面
201
违规数
0
Overclaim Guard Active
是

声明边界

claim guard 扫描 README、docs 和 reports 中的完成态表述；ledger 未 ready 时，任何英文完成断言、true 状态声明或中文完成态都会阻断发布审查。

diff --git a/reports/review-studio.json b/reports/review-studio.json index 0241ab3..2db5773 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -65,7 +65,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 999/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 140.1", + "detail": "initial load 987/1000; deferred 531767/120000; top deferred scripts 469568; resource governance governed; quality density 141.8", "evidence": "reports/context_budget.json", "link": "context_budget.md", "review_action_id": "", @@ -1194,8 +1194,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_ready_count": 2, "submission_ref_total_count": 2, - "supporting_evidence_ready_count": 7, - "supporting_evidence_total_count": 8, + "supporting_evidence_ready_count": 11, + "supporting_evidence_total_count": 11, "roles": [ { "role": "submission-ref", @@ -1208,8 +1208,8 @@ { "role": "supporting-evidence", "label": "Supporting evidence", - "ready_count": 7, - "total_count": 8, + "ready_count": 11, + "total_count": 11, "copy_to_artifact_refs": false, "description": "Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs." } @@ -1523,7 +1523,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 342 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。", @@ -1544,7 +1544,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 342 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。" ] @@ -1648,7 +1648,7 @@ "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 342 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。", @@ -1713,7 +1713,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 342 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。" }, { @@ -2077,11 +2077,11 @@ "display_name": "Yao Meta Skill", "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.", @@ -2458,8 +2458,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -2483,13 +2483,13 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "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.", @@ -2595,7 +2595,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "skill_atlas": { "skill_count": 11, @@ -2633,7 +2633,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -2767,7 +2767,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, @@ -6318,32 +6318,31 @@ "ok": true, "generated_at": "2026-07-02", "skill_dir": ".", - "commit": "1710a5a3e0177313954758908735c147796e8981", + "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "git_status": { "available": true, "dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "generated_dirty": true, - "generated_changed_file_count": 82, + "generated_changed_file_count": 36, "source_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "sample": [ " M SKILL.md", - " M evals/improved_description.txt", " 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/artifact-design-profile.json", - " M reports/artifact-design-profile.md", - " M reports/baseline-compare.json", " M reports/benchmark_reproducibility.json", - " M reports/benchmark_reproducibility.md" + " 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": [ - " M SKILL.md", - " M evals/improved_description.txt" + " M SKILL.md" ], "generated_sample": [ " M registry/index.json", @@ -6351,13 +6350,13 @@ " M reports/adaptation_proposals.json", " M reports/adaptation_proposals.md", " M reports/adoption_drift_report.json", - " M reports/artifact-design-profile.json", - " M reports/artifact-design-profile.md", - " M reports/baseline-compare.json", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", - " M reports/candidate_registry.json", - " M reports/candidate_registry.md" + " M reports/compiled_targets.json", + " M reports/context_budget.json", + " M reports/context_budget.md", + " M reports/context_budget_summary.json", + " M reports/evidence_consistency.json" ], "generated_dirty_prefixes": [ "dist/", @@ -6375,8 +6374,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -6400,11 +6399,11 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, "beta_test_release": { "ready": false, @@ -6450,10 +6449,10 @@ }, "release_lock": { "ready": false, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61", "status_scope": "generation-time status before this report is written", - "source_changed_file_count": 2, - "generated_changed_file_count": 82, + "source_changed_file_count": 1, + "generated_changed_file_count": 36, "reason": "source files were dirty at generation time" }, "evidence_bundle": { @@ -6462,7 +6461,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873" + "sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -6571,7 +6570,7 @@ "path": "reports/security_trust_report.json", "exists": true, "bytes": 139090, - "sha256": "ffe2c88bbdbac4907bf8db8f01b9a6b2da78e83acdffb3d975e99424274cd9f7" + "sha256": "108aee597a1f245f73d9b69454b6fa8a144545f905231a7c314364c7066541c6" }, { "label": "python_compatibility", @@ -6585,7 +6584,7 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3155, - "sha256": "9be6de364d69a2ad40b68b460a35c91476e822eb008cfe4d5e8614c1e989d3d4" + "sha256": "d307675d5c6c3cd2f104ce7d963b37d36113f35334e4c6895b55fbb8b255e915" }, { "label": "package_verification", @@ -6633,8 +6632,8 @@ "label": "world_class_evidence_preflight", "path": "reports/world_class_evidence_preflight.json", "exists": true, - "bytes": 90852, - "sha256": "a0b00eed5450b33ec29fea6652d41db216931452eeddd0d99f2d90aa20c44d95" + "bytes": 90854, + "sha256": "06e93b1c0c99107002466d9418a4910c82397bce26c3bbdd5b5cc9875eeb65b2" }, { "label": "world_class_submission_review", @@ -6668,8 +6667,8 @@ "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, - "bytes": 20102, - "sha256": "5eb808496802e8f972e5aa738d99f3b4a37ff34c8ab495f25ff2db3e7237239f" + "bytes": 20713, + "sha256": "911ba833055ab857250f88d88ccdd0bb652076a81214f725c49d763352035572" } ], "missing_artifacts": [], @@ -7697,17 +7696,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -8654,17 +8653,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -9611,17 +9610,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -10552,17 +10551,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -11493,17 +11492,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.", @@ -13042,7 +13041,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "failures": [], "warnings": [], @@ -18234,10 +18233,10 @@ "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, - "skill_body_tokens": 806, - "other_text_tokens": 1200438, - "estimated_initial_load_tokens": 999, - "estimated_total_text_tokens": 1201244, + "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": [ @@ -18295,10 +18294,10 @@ ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 590, + "relevant_file_count": 591, "unused_resource_dirs": [], "quality_signal_points": 140, - "quality_density": 140.1 + "quality_density": 141.8 } }, "promotion": { @@ -20132,7 +20131,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-07-02T03:42:30Z", + "generated_at": "2026-07-02T06:33:44Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -20216,7 +20215,7 @@ "daily_skillops": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, @@ -20730,7 +20729,7 @@ "weekly_curator": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W27", @@ -21198,7 +21197,7 @@ "adaptation_proposals": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, @@ -23397,8 +23396,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 2, "submission_ref_ready_count": 2, - "supporting_evidence_total_count": 8, - "supporting_evidence_ready_count": 7, + "supporting_evidence_total_count": 11, + "supporting_evidence_ready_count": 11, "roles": [ { "role": "submission-ref", @@ -24541,8 +24540,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 7, "submission_ref_ready_count": 7, - "supporting_evidence_total_count": 28, - "supporting_evidence_ready_count": 27, + "supporting_evidence_total_count": 31, + "supporting_evidence_ready_count": 31, "roles": [ { "role": "submission-ref", @@ -26712,10 +26711,10 @@ "summary": { "ledger_ready_to_claim_world_class": false, "ledger_pending_count": 4, - "claim_surface_count": 194, - "json_claim_surface_count": 92, - "metadata_claim_surface_count": 93, - "package_claim_surface_count": 10, + "claim_surface_count": 201, + "json_claim_surface_count": 97, + "metadata_claim_surface_count": 98, + "package_claim_surface_count": 17, "violation_count": 0, "overclaim_guard_active": true, "decision": "claim-guard-pass-evidence-pending" @@ -26760,6 +26759,34 @@ "path": "agents/interface.yaml", "violation_count": 0 }, + { + "path": "dist/manifest.json", + "violation_count": 0 + }, + { + "path": "dist/targets/claude/README.md", + "violation_count": 0 + }, + { + "path": "dist/targets/claude/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/generic/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/openai/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/vscode/README.md", + "violation_count": 0 + }, + { + "path": "dist/targets/vscode/adapter.json", + "violation_count": 0 + }, { "path": "docs/README.fr-FR.md", "violation_count": 0 @@ -27558,7 +27585,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -27615,7 +27642,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, @@ -28663,7 +28690,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/review-viewer.html b/reports/review-viewer.html index f0c857b..1f94f65 100644 --- a/reports/review-viewer.html +++ b/reports/review-viewer.html @@ -200,13 +200,13 @@ th {

Architecture at a glance

-
Inputs
workflow, prompt, transcript, docs, or notes
Boundary
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
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.
Usage
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.
Next
Review the top iteration directions before growing the package.
+
Inputs
workflow, prompt, transcript, docs, or notes
Boundary
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
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.
Usage
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.
Next
Review the top iteration directions before growing the package.

Core logic

- +

How to use it

diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 6cb5d0a..71b7296 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -81,7 +81,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 342 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 342 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。" ] @@ -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 342 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 342 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。" }, { @@ -635,11 +635,11 @@ "display_name": "Yao Meta Skill", "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.", @@ -1016,8 +1016,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1041,13 +1041,13 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "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.", @@ -1153,7 +1153,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "skill_atlas": { "skill_count": 11, @@ -1191,7 +1191,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -1325,7 +1325,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 61b7fd8..f5cc04b 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -23,7 +23,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "failures": [], "warnings": [], diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 54d8aaf..d070a34 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -16,7 +16,7 @@ - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` - Package hash files: `247` -- Package SHA256: `e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3` +- Package SHA256: `db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c` ## Failures diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 4cc6862..0956b04 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -770,7 +770,7 @@
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
@@ -807,12 +807,12 @@

成熟度条Maturity Bar

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。This compresses each metric into status, score, and the first evidence item before the detailed cards below.

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
指标明细Metric Details
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -845,7 +845,7 @@

执行流程Execution Flow

-
  1. 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。For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
  2. 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。Capture job, output, exclusions, constraints, standards, and the lightest fit.
  3. 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。Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
  4. 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。Write `description` early, test route quality, then add only earned folders and gates.
  5. 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。Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
+
  1. 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。One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
  2. 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。Capture job, output, exclusions, constraints, standards, lightest fit.
  3. 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。Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.
  4. 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。Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.
  5. 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。Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.

调用方式How To Use

@@ -888,7 +888,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 342 个词/字，references 约 16934 个词/字。Context cost needs improvement: Entrypoint is about 342 words/characters; references are about 16934.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。Context cost needs improvement: Entrypoint is about 314 words/characters; references are about 16934.纳入下一轮修复Fix next
@@ -925,7 +925,7 @@
- +
风险Risk信号Signal应对Response
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 11bfb6c..a190723 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -81,7 +81,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 342 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 342 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。" ] @@ -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 342 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 342 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。" }, { @@ -639,11 +639,11 @@ "display_name": "Yao Meta Skill", "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.", @@ -1020,8 +1020,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1045,13 +1045,13 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "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.", @@ -1157,7 +1157,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "skill_atlas": { "skill_count": 11, @@ -1195,7 +1195,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -1329,7 +1329,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index 3f22292..51af1f9 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -153,7 +153,7 @@ 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 `999/1000`; deferred `530167/120000`; resource governance governed | +| 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 diff --git a/reports/skill-overview.html b/reports/skill-overview.html index d124b1c..c5a0f6d 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -770,7 +770,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。After creation, open reports/skill-overview.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
@@ -807,12 +807,12 @@

成熟度条Maturity Bar

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。This compresses each metric into status, score, and the first evidence item before the detailed cards below.

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
指标明细Metric Details
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 342 个词/字，references 约 16934 个词/字。Entrypoint is about 342 words/characters; references are about 16934.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。skill-ir.json exists.
  • compiled_targets.json 已存在。compiled_targets.json exists.
可维护性Maintainability100
  • SKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 314 个词/字，references 约 16934 个词/字。Entrypoint is about 314 words/characters; references are about 16934.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -845,7 +845,7 @@

执行流程Execution Flow

-
  1. 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。For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
  2. 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。Capture job, output, exclusions, constraints, standards, and the lightest fit.
  3. 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。Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
  4. 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。Write `description` early, test route quality, then add only earned folders and gates.
  5. 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。Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
+
  1. 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。One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
  2. 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。Capture job, output, exclusions, constraints, standards, lightest fit.
  3. 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。Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.
  4. 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。Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.
  5. 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。Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.

调用方式How To Use

@@ -888,7 +888,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 342 个词/字，references 约 16934 个词/字。Context cost needs improvement: Entrypoint is about 342 words/characters; references are about 16934.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength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。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 314 个词/字，references 约 16934 个词/字。Context cost needs improvement: Entrypoint is about 314 words/characters; references are about 16934.纳入下一轮修复Fix next
@@ -925,7 +925,7 @@
- +
风险Risk信号Signal应对Response
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 342 个词/字。SKILL.md is about 342 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 314 个词/字。SKILL.md is about 314 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 92cabd0..bea4304 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -80,7 +80,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 342 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 342 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。" ] @@ -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 342 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 342 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。" }, { @@ -634,11 +634,11 @@ "display_name": "Yao Meta Skill", "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.", @@ -1015,8 +1015,8 @@ "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873", - "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158", + "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7", "output_case_count": 5, "failure_disclosure_count": 3, @@ -1040,13 +1040,13 @@ "public_claim_ready": false, "public_claim_blocker_count": 4, "working_tree_dirty": true, - "changed_file_count": 84, + "changed_file_count": 37, "source_tree_dirty": true, - "source_changed_file_count": 2, + "source_changed_file_count": 1, "generated_tree_dirty": true, - "generated_changed_file_count": 82 + "generated_changed_file_count": 36 }, - "commit": "1710a5a3e0177313954758908735c147796e8981", + "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.", @@ -1152,7 +1152,7 @@ "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", "package_hash_file_count": 247, - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" }, "skill_atlas": { "skill_count": 11, @@ -1190,7 +1190,7 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3", + "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c", "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7" }, "compatibility": { @@ -1324,7 +1324,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/skillops/daily/2026-07-02.json b/reports/skillops/daily/2026-07-02.json index 82e729a..0bf6cd8 100644 --- a/reports/skillops/daily/2026-07-02.json +++ b/reports/skillops/daily/2026-07-02.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "decision": "proposal-review", "source_supplied": false, diff --git a/reports/skillops/daily/2026-07-02.md b/reports/skillops/daily/2026-07-02.md index a3c85a2..ec4ec29 100644 --- a/reports/skillops/daily/2026-07-02.md +++ b/reports/skillops/daily/2026-07-02.md @@ -1,6 +1,6 @@ # Daily SkillOps Report -Generated at: `2026-07-02T03:41:56Z` +Generated at: `2026-07-02T06:33:07Z` ## Summary diff --git a/reports/skillops/weekly/2026-W27.json b/reports/skillops/weekly/2026-W27.json index 8830acc..123e670 100644 --- a/reports/skillops/weekly/2026-W27.json +++ b/reports/skillops/weekly/2026-W27.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-07-02T03:41:56Z", + "generated_at": "2026-07-02T06:33:07Z", "skill_dir": ".", "decision": "curator-review", "week_id": "2026-W27", diff --git a/reports/skillops/weekly/2026-W27.md b/reports/skillops/weekly/2026-W27.md index 13f65fb..ea7ec3b 100644 --- a/reports/skillops/weekly/2026-W27.md +++ b/reports/skillops/weekly/2026-W27.md @@ -1,6 +1,6 @@ # Weekly SkillOps Curator Report -Generated at: `2026-07-02T03:41:56Z` +Generated at: `2026-07-02T06:33:07Z` Week: `2026-W27` ## Summary diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index e824cd2..73b1562 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -75,7 +75,7 @@ { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3" + "to": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c" } ] }, diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index 482c64c..00fb284 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -6,10 +6,10 @@ "summary": { "ledger_ready_to_claim_world_class": false, "ledger_pending_count": 4, - "claim_surface_count": 194, - "json_claim_surface_count": 92, - "metadata_claim_surface_count": 93, - "package_claim_surface_count": 10, + "claim_surface_count": 201, + "json_claim_surface_count": 97, + "metadata_claim_surface_count": 98, + "package_claim_surface_count": 17, "violation_count": 0, "overclaim_guard_active": true, "decision": "claim-guard-pass-evidence-pending" @@ -54,6 +54,34 @@ "path": "agents/interface.yaml", "violation_count": 0 }, + { + "path": "dist/manifest.json", + "violation_count": 0 + }, + { + "path": "dist/targets/claude/README.md", + "violation_count": 0 + }, + { + "path": "dist/targets/claude/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/generic/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/openai/adapter.json", + "violation_count": 0 + }, + { + "path": "dist/targets/vscode/README.md", + "violation_count": 0 + }, + { + "path": "dist/targets/vscode/adapter.json", + "violation_count": 0 + }, { "path": "docs/README.fr-FR.md", "violation_count": 0 diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index 0e254e6..a48871b 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -7,10 +7,10 @@ Generated at: `2026-07-02` - decision: `claim-guard-pass-evidence-pending` - ledger ready to claim world-class: `false` - ledger pending evidence: `4` -- claim surfaces scanned: `194` -- JSON claim surfaces scanned: `92` -- metadata claim surfaces scanned: `93` -- package/runtime claim surfaces scanned: `10` +- claim surfaces scanned: `201` +- JSON claim surfaces scanned: `97` +- metadata claim surfaces scanned: `98` +- package/runtime claim surfaces scanned: `17` - violations: `0` - overclaim guard active: `true` diff --git a/reports/world_class_evidence_preflight.html b/reports/world_class_evidence_preflight.html index 71a5afa..3f03cb5 100644 --- a/reports/world_class_evidence_preflight.html +++ b/reports/world_class_evidence_preflight.html @@ -92,7 +92,7 @@
Supporting evidence

supporting-evidence

- 27/28 ready + 31/31 ready

Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.

copy to artifact_refs: false
@@ -667,7 +667,7 @@
Supporting evidence

supporting-evidence

- 7/8 ready + 11/11 ready

Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs.

copy to artifact_refs: false
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index 31fc038..996b080 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -802,8 +802,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 2, "submission_ref_ready_count": 2, - "supporting_evidence_total_count": 8, - "supporting_evidence_ready_count": 7, + "supporting_evidence_total_count": 11, + "supporting_evidence_ready_count": 11, "roles": [ { "role": "submission-ref", @@ -1946,8 +1946,8 @@ "artifact_prefill_counts_as_evidence": false, "submission_ref_total_count": 7, "submission_ref_ready_count": 7, - "supporting_evidence_total_count": 28, - "supporting_evidence_ready_count": 27, + "supporting_evidence_total_count": 31, + "supporting_evidence_ready_count": 31, "roles": [ { "role": "submission-ref", diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 3fa9cf1..ac6f5bd 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -33,14 +33,14 @@ This preflight report checks whether an operator can start collecting the remain - drafts count as evidence: `false` - artifact prefill counts as evidence: `false` - submission refs ready: `7` / `7` -- supporting evidence ready: `27` / `28` +- supporting evidence ready: `31` / `31` Generate the submission kit after the real provider, human, native-permission, or native-client work exists. The generated JSON drafts remain `template_only: true` until an operator edits them with real aggregate artifact references and matching SHA-256 digests. The prefill command only inserts local artifact SHA-256 digests; it does not make a draft count as evidence. | Role | Copy to artifact_refs | Ready | Meaning | | --- | --- | --- | --- | | `submission-ref` | `true` | `7 / 7` | Rows marked submission-ref are the aggregate paths expected in artifact_refs. | -| `supporting-evidence` | `false` | `27 / 28` | Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs. | +| `supporting-evidence` | `false` | `31 / 31` | Supporting-evidence rows help reviewers audit the packet but do not all need to be copied into artifact_refs. | `submission-ref` rows are the only checklist rows expected in `artifact_refs`; `supporting-evidence` rows stay available for audit context and reviewer traceability. @@ -149,7 +149,7 @@ Repair rows convert preflight and source blockers into a prioritized operator qu - prepare draft: `python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions` - prepare draft with artifact SHA prefill: `python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions --prefill-artifacts` - submission refs ready: `2` / `2` -- supporting evidence ready: `7` / `8` +- supporting evidence ready: `11` / `11` ### Prechecks diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index 70f5136..5329e5a 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -40,17 +40,17 @@ }, "workflow": { "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." ], "decision_points": [ "Route by frontmatter `description`.", "Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.", "Use the lightest reliable process.", - "`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).", "Ask one focused clarification when the real job, output, or exclusion boundary is unclear.", "Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",