Track 2.0 reference extension gaps
This commit is contained in:
yaojingang
+2
-2
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"package_count": 1,
|
||||
"packages": [
|
||||
{
|
||||
@@ -16,7 +16,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -53,5 +53,5 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-14T07:17:33Z",
|
||||
"generated_at": "2026-06-15T11:07:11Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
@@ -25,14 +25,14 @@
|
||||
},
|
||||
"summary": {
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"activation_count": 0,
|
||||
"accepted_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"activation_count": 1,
|
||||
"accepted_count": 1,
|
||||
"edited_count": 0,
|
||||
"rejected_count": 0,
|
||||
"missed_count": 0,
|
||||
"failed_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_rate": 100.0,
|
||||
"missed_trigger_count": 0,
|
||||
"wrong_trigger_count": 0,
|
||||
"bad_output_count": 0,
|
||||
@@ -41,7 +41,7 @@
|
||||
"review_overdue_count": 0,
|
||||
"risk_band": "low",
|
||||
"event_types": {
|
||||
"review_event": 1
|
||||
"skill_activation": 1
|
||||
},
|
||||
"failure_types": {},
|
||||
"source_types": {
|
||||
@@ -53,31 +53,31 @@
|
||||
{
|
||||
"skill": "yao-meta-skill",
|
||||
"events": 1,
|
||||
"adoption_events": 0,
|
||||
"accepted": 0,
|
||||
"adoption_events": 1,
|
||||
"accepted": 1,
|
||||
"edited": 0,
|
||||
"rejected": 0,
|
||||
"missed": 0,
|
||||
"adoption_rate": 0
|
||||
"adoption_rate": 100.0
|
||||
}
|
||||
],
|
||||
"next_iteration_candidates": [],
|
||||
"recent_events": [
|
||||
{
|
||||
"command": "unknown",
|
||||
"event": "review_event",
|
||||
"event": "skill_activation",
|
||||
"skill": "yao-meta-skill",
|
||||
"source": "manual",
|
||||
"version": "1.1.0",
|
||||
"activation_type": "manual",
|
||||
"outcome": "reviewed",
|
||||
"activation_type": "explicit",
|
||||
"outcome": "accepted",
|
||||
"failure_type": "none",
|
||||
"timestamp": "2026-06-13T12:00:00Z"
|
||||
"timestamp": "2026-06-13T10:00:00Z"
|
||||
}
|
||||
],
|
||||
"failures": [],
|
||||
"artifacts": {
|
||||
"events_jsonl": "reports/telemetry_events.jsonl",
|
||||
"events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl",
|
||||
"json": "reports/adoption_drift_report.json",
|
||||
"markdown": "reports/adoption_drift_report.md"
|
||||
}
|
||||
|
||||
@@ -5,9 +5,9 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
## Summary
|
||||
|
||||
- Events: `1`
|
||||
- Adoption samples: `0`
|
||||
- Activation events: `0`
|
||||
- Adoption rate: `0`
|
||||
- Adoption samples: `1`
|
||||
- Activation events: `1`
|
||||
- Adoption rate: `100.0`
|
||||
- Missed trigger signals: `0`
|
||||
- Bad output signals: `0`
|
||||
- Script error signals: `0`
|
||||
@@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
|
||||
| Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate |
|
||||
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
||||
| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
|
||||
| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 |
|
||||
|
||||
## Next Iteration Candidates
|
||||
|
||||
@@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs,
|
||||
|
||||
## Recent Metadata Events
|
||||
|
||||
- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none`
|
||||
- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none`
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"python_file_count": 162,
|
||||
@@ -46,6 +46,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 745,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 741,
|
||||
@@ -60,13 +67,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 734,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/build_skill_atlas.py",
|
||||
"lines": 730,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Architecture Maintainability
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -29,9 +29,9 @@ No file-size hotspots found.
|
||||
| `scripts/yao.py` | `881` | `cli-script` | `pass` |
|
||||
| `scripts/skill_report_layout.py` | `805` | `internal-module` | `pass` |
|
||||
| `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` |
|
||||
| `tests/verify_review_studio.py` | `745` | `test` | `pass` |
|
||||
| `scripts/yao_cli_parser.py` | `741` | `internal-module` | `pass` |
|
||||
| `scripts/compile_skill.py` | `734` | `cli-script` | `pass` |
|
||||
| `tests/verify_review_studio.py` | `734` | `test` | `pass` |
|
||||
| `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` |
|
||||
| `scripts/optimize_description.py` | `723` | `cli-script` | `pass` |
|
||||
| `scripts/trust_check.py` | `714` | `internal-module` | `pass` |
|
||||
|
||||
@@ -3,22 +3,35 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"skill_dir": ".",
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 38,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/benchmark_reproducibility.json",
|
||||
" M reports/benchmark_reproducibility.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/install_simulation.json",
|
||||
" M reports/install_simulation.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021",
|
||||
"source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
|
||||
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -37,14 +50,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 38
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -53,10 +67,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"ready": false,
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -64,7 +78,7 @@
|
||||
"existing_count": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021"
|
||||
"sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -137,8 +151,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7964,
|
||||
"sha256": "ebef496866a9d52e5a4cef5a855a997915b820612d87c777b85e3ed1f0458efc"
|
||||
"bytes": 7967,
|
||||
"sha256": "712890e85fdd3334e3196b2597555491be047313728c2e2891134da71e1ca7e8"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -173,7 +187,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 101852,
|
||||
"sha256": "abe52fcdab2d2345783e353644acd66913995cc9048b3f3e0c758c5fca43672f"
|
||||
"sha256": "3cd8c1c2d119e2db480411a9839281e0a9e1b03eb4d9d535c9b0138ef72ba6e4"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -187,7 +201,7 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "e97001fe6bf7553dfc3f748d67146284d5e363336954bec7991dd0d6add240cb"
|
||||
"sha256": "9b8e6521f9455e654850975e3625132fb998ba4e03f7ceebaf4eded9ccd32bb5"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
@@ -200,15 +214,15 @@
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8604,
|
||||
"sha256": "d6972a9ab9966a8eff922b175f885b953c6300afd55bd4dc08b5baf20a518c20"
|
||||
"bytes": 8758,
|
||||
"sha256": "ee7554d8362d05f2bf6e7389e0524cd6336d42312ab7a05b9c0c6ddacdb0e339"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
"path": "reports/skill_os2_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 14310,
|
||||
"sha256": "cbce716b87a924ea08161d75851d14acb4ce76099f63ae4bc4f7bdf967f9f2fa"
|
||||
"sha256": "8a7f73832d4da2f63856d7f5be02488db6eac72a3a6149aa26a39c7a15a27053"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_plan",
|
||||
|
||||
@@ -1,18 +1,18 @@
|
||||
# Benchmark Reproducibility
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Commit: `5f187cdb46510a6881a8353c0c1744b90e0b05bd`
|
||||
Working tree dirty at generation: `false`
|
||||
Evidence bundle SHA256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021`
|
||||
Commit: `7acc6d9cf780e38570c20813186d0efea5ac8ad0`
|
||||
Working tree dirty at generation: `true`
|
||||
Evidence bundle SHA256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56`
|
||||
|
||||
## Summary
|
||||
|
||||
- reproducibility ready: `true`
|
||||
- release lock ready: `true`
|
||||
- release lock ready: `false`
|
||||
- methodology complete: `true`
|
||||
- required artifacts: `24`
|
||||
- missing artifacts: `0`
|
||||
- source contract sha256: `0a4768c86c9a`
|
||||
- source contract sha256: `fe193ec81d0e`
|
||||
- archive sha256: `6852cf91a74d`
|
||||
- output cases: `5`
|
||||
- disclosed failure cases: `3`
|
||||
@@ -22,8 +22,8 @@ Evidence bundle SHA256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd692
|
||||
- world-class ready: `false`
|
||||
- world-class source checks: `6` pass / `13` total; `7` blocked
|
||||
- public claim ready: `false`
|
||||
- public claim blockers: `4`
|
||||
- changed files at generation: `0`
|
||||
- public claim blockers: `5`
|
||||
- changed files at generation: `38`
|
||||
|
||||
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 is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
|
||||
|
||||
@@ -35,6 +35,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
| Blocker |
|
||||
| --- |
|
||||
| release lock is not clean or commit is unavailable |
|
||||
| provider-backed model holdout evidence is incomplete |
|
||||
| human blind-review adjudication is incomplete |
|
||||
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
|
||||
@@ -42,15 +43,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
|
||||
## Release Lock
|
||||
|
||||
- ready: `true`
|
||||
- reason: clean generation-time HEAD
|
||||
- ready: `false`
|
||||
- reason: working tree was dirty at generation time
|
||||
- status scope: generation-time status before this report is written
|
||||
|
||||
## Evidence Bundle
|
||||
|
||||
- algorithm: `sha256(path,label,exists,artifact_sha256)`
|
||||
- artifacts: `24` / `24`
|
||||
- sha256: `dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021`
|
||||
- sha256: `3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56`
|
||||
|
||||
## Methodology Sections
|
||||
|
||||
@@ -72,17 +73,17 @@ This report proves local benchmark reproducibility only. It keeps external provi
|
||||
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
|
||||
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
|
||||
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `ebef496866a9` |
|
||||
| output_execution | `reports/output_execution_runs.json` | present | `712890e85fdd` |
|
||||
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
|
||||
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
|
||||
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
|
||||
| runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `abe52fcdab2d` |
|
||||
| trust_report | `reports/security_trust_report.json` | present | `3cd8c1c2d119` |
|
||||
| python_compatibility | `reports/python_compatibility.json` | present | `5be76147f3cb` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `e97001fe6bf7` |
|
||||
| registry_audit | `reports/registry_audit.json` | present | `9b8e6521f945` |
|
||||
| package_verification | `reports/package_verification.json` | present | `2476ae8ec9c4` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `d6972a9ab996` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `cbce716b87a9` |
|
||||
| install_simulation | `reports/install_simulation.json` | present | `ee7554d8362d` |
|
||||
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `8a7f73832d4d` |
|
||||
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `933cdb002181` |
|
||||
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `5407409841eb` |
|
||||
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `b10e1ce0a5a1` |
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"target_count": 5,
|
||||
|
||||
@@ -6,15 +6,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 767,
|
||||
"other_text_tokens": 1260693,
|
||||
"other_text_tokens": 1265845,
|
||||
"estimated_initial_load_tokens": 960,
|
||||
"estimated_total_text_tokens": 1261460,
|
||||
"deferred_resource_tokens": 404827,
|
||||
"estimated_total_text_tokens": 1266612,
|
||||
"deferred_resource_tokens": 406347,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102
|
||||
},
|
||||
{
|
||||
@@ -31,7 +31,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102
|
||||
}
|
||||
],
|
||||
@@ -54,7 +54,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
| Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status |
|
||||
| --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- |
|
||||
| root | `.` | `production` | 1000 | 960 | 767 | 404827 | `governed` | scripts:357091 | 135.4 | - | ok |
|
||||
| root | `.` | `production` | 1000 | 960 | 767 | 406347 | `governed` | scripts:358611 | 135.4 | - | 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 |
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-03-31",
|
||||
"targets": [
|
||||
{
|
||||
"label": "root",
|
||||
@@ -8,11 +8,11 @@
|
||||
"budget_limit": 1000,
|
||||
"initial_tokens": 960,
|
||||
"skill_body_tokens": 767,
|
||||
"deferred_resource_tokens": 404827,
|
||||
"deferred_resource_tokens": 406347,
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102
|
||||
}
|
||||
],
|
||||
@@ -35,7 +35,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 586,
|
||||
@@ -26,7 +26,7 @@
|
||||
{
|
||||
"id": "archive-present",
|
||||
"status": "pass",
|
||||
"detail": "Package archive exists: dist/yao-meta-skill.zip"
|
||||
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
|
||||
},
|
||||
{
|
||||
"id": "archive-safe-paths",
|
||||
@@ -272,9 +272,9 @@
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
"artifacts": {
|
||||
"archive": "dist/yao-meta-skill.zip",
|
||||
"package_manifest": "dist/manifest.json",
|
||||
"json": "reports/install_simulation.json",
|
||||
"markdown": "reports/install_simulation.md"
|
||||
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
|
||||
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
|
||||
"json": "tests/tmp_review_studio/install_simulation.json",
|
||||
"markdown": "tests/tmp_review_studio/install_simulation.md"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Install Simulation
|
||||
|
||||
- OK: `True`
|
||||
- Package directory: `dist`
|
||||
- Package directory: `tests/tmp_review_studio/dist`
|
||||
- Archive extracted: `True`
|
||||
- Entrypoint loaded: `True`
|
||||
- Manifest loaded: `True`
|
||||
@@ -16,7 +16,7 @@
|
||||
|
||||
| Check | Status | Detail |
|
||||
| --- | --- | --- |
|
||||
| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip |
|
||||
| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip |
|
||||
| `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries |
|
||||
| `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill |
|
||||
| `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable |
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.02,
|
||||
"duration_ms": 38.72,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -62,7 +62,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.88,
|
||||
"duration_ms": 37.27,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -85,7 +85,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 36.03,
|
||||
"duration_ms": 39.96,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -113,7 +113,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.76,
|
||||
"duration_ms": 39.8,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -136,7 +136,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.27,
|
||||
"duration_ms": 37.28,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -164,7 +164,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.3,
|
||||
"duration_ms": 34.66,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -187,7 +187,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.36,
|
||||
"duration_ms": 36.08,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -214,7 +214,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.3,
|
||||
"duration_ms": 41.08,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -237,7 +237,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.1,
|
||||
"duration_ms": 34.88,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -266,7 +266,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.83,
|
||||
"duration_ms": 34.91,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
|
||||
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
|
||||
|
||||
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
|
||||
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 33.02 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 32.88 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 36.03 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 32.76 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 30.27 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 32.3 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.36 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 30.3 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 30.1 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 30.83 | 98 | 100.0 | pass |
|
||||
| skill-package-contract | baseline | command | local-output-eval-runner | 38.72 | 33 | 0.0 | pass |
|
||||
| skill-package-contract | with_skill | command | local-output-eval-runner | 37.27 | 73 | 100.0 | pass |
|
||||
| output-eval-expectation | baseline | command | local-output-eval-runner | 39.96 | 36 | 0.0 | pass |
|
||||
| output-eval-expectation | with_skill | command | local-output-eval-runner | 39.8 | 80 | 100.0 | pass |
|
||||
| ir-before-packaging | baseline | command | local-output-eval-runner | 37.28 | 33 | 0.0 | pass |
|
||||
| ir-before-packaging | with_skill | command | local-output-eval-runner | 34.66 | 80 | 100.0 | pass |
|
||||
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 36.08 | 36 | 0.0 | pass |
|
||||
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 41.08 | 65 | 100.0 | pass |
|
||||
| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.88 | 37 | 0.0 | pass |
|
||||
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 34.91 | 98 | 100.0 | pass |
|
||||
|
||||
## Next Fixes
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"root": ".",
|
||||
"summary": {
|
||||
"target_python": "3.11",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Python Compatibility
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -58,11 +58,11 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
},
|
||||
"index": {
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"package_count": 1,
|
||||
"packages": [
|
||||
{
|
||||
@@ -78,7 +78,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
- Maturity: `governed`
|
||||
- Owner: `Yao Team`
|
||||
- License: `MIT`
|
||||
- Package SHA256: `0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822`
|
||||
- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5`
|
||||
- Archive SHA256: `6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc`
|
||||
- Install simulated: `True`
|
||||
|
||||
|
||||
@@ -676,12 +676,12 @@
|
||||
|
||||
<section>
|
||||
<h2>核心指标</h2>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>102 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>165 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>586 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; extensions partial 1, planned 1; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>102 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>165 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>586 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h2>审查闸门</h2>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 102 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>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 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 102 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 165 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>162 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
|
||||
</section>
|
||||
|
||||
<div class="twocol">
|
||||
@@ -743,12 +743,12 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4</p></div>
|
||||
<div class="panel"><h2>上下文</h2><p>initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4</p></div>
|
||||
<div class="panel"><h2>编译证据</h2><p>Review reports/compiled_targets.md before packaging to inspect target adapter modes, generated files, preserved semantics, warnings, and unsupported features.</p></div>
|
||||
</section>
|
||||
|
||||
<section id="trust" class="twocol">
|
||||
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>102</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>102</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5</code></dd></div></dl></div>
|
||||
<div class="panel"><h2>安全边界</h2><p>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。</p></div>
|
||||
</section>
|
||||
|
||||
@@ -785,7 +785,7 @@
|
||||
<div class="panel"><h2>批准台账</h2><dl class='kv-grid'><div><dt>Waiver Count</dt><dd>0</dd></div><div><dt>Active Count</dt><dd>0</dd></div><div><dt>Expired Count</dt><dd>0</dd></div><div><dt>Invalid Count</dt><dd>0</dd></div><div><dt>覆盖 Gate</dt><dd>0</dd></div></dl></div>
|
||||
</div>
|
||||
<h3 class="section-subtitle">批准候选</h3>
|
||||
<div class='waiver-candidate-grid'><article class='waiver-card allowed'><div><span>可批准 · needs-reviewer-decision</span><h3>Output Lab</h3></div><p>review pending 5; model-executed 0; output failures 0</p><dl><dt>Gate</dt><dd><code>output-lab</code></dd><dt>证据</dt><dd><code>reports/output_review_adjudication.md</code></dd><dt>选项</dt><dd>accepted-risk, false-positive, temporary-exception</dd><dt>边界</dt><dd>Does not count as provider, human, or public world-class completion evidence.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.</li><li>Reviewer names the release scope and expiry date.</li><li>Reviewer links output_review_adjudication or output_execution evidence.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md</code></div></article><article class='waiver-card blocked'><div><span>不可批准 · cannot-waive</span><h3>World-Class Evidence</h3></div><p>4 pending evidence entries; 1 human pending; 3 external pending</p><dl><dt>Gate</dt><dd><code>world-class-evidence</code></dd><dt>证据</dt><dd><code>reports/world_class_evidence_ledger.md</code></dd><dt>选项</dt><dd>无</dd><dt>边界</dt><dd>Non-waivable completion boundary.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Do not use a waiver to claim public world-class readiness.</li><li>Either submit accepted ledger evidence or state that this release does not claim world-class completion.</li><li>Keep claim guard active until ledger summary.ready_to_claim_world_class is true.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .</code></div></article></div>
|
||||
<div class='waiver-candidate-grid'><article class='waiver-card allowed'><div><span>可批准 · needs-reviewer-decision</span><h3>Output Lab</h3></div><p>review pending 5; model-executed 0; output failures 0</p><dl><dt>Gate</dt><dd><code>output-lab</code></dd><dt>证据</dt><dd><code>reports/output_review_adjudication.md</code></dd><dt>选项</dt><dd>accepted-risk, false-positive, temporary-exception</dd><dt>边界</dt><dd>Does not count as provider, human, or public world-class completion evidence.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.</li><li>Reviewer names the release scope and expiry date.</li><li>Reviewer links output_review_adjudication or output_execution evidence.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md</code></div></article><article class='waiver-card blocked'><div><span>不可批准 · cannot-waive</span><h3>World-Class Evidence</h3></div><p>4 pending evidence entries; 1 human pending; 3 external pending</p><dl><dt>Gate</dt><dd><code>world-class-evidence</code></dd><dt>证据</dt><dd><code>reports/world_class_evidence_ledger.md</code></dd><dt>选项</dt><dd>无</dd><dt>边界</dt><dd>Non-waivable completion boundary.</dd></dl><div class='waiver-review'><h4>审查条件</h4><ul><li>Do not use a waiver to claim public world-class readiness.</li><li>Either submit accepted ledger evidence or state that this release does not claim world-class completion.</li><li>Keep claim guard active until ledger summary.ready_to_claim_world_class is true.</li></ul></div><div class='waiver-command'><span>建议命令</span><code>python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .</code></div></article></div>
|
||||
</section>
|
||||
|
||||
<section id="world-class">
|
||||
@@ -801,13 +801,13 @@
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>蓝图覆盖</h2><dl class='kv-grid'><div><dt>项目数</dt><dd>20</dd></div><div><dt>模块数</dt><dd>8</dd></div><div><dt>建议 PR</dt><dd>12</dd></div><div><dt>通过数</dt><dd>20</dd></div><div><dt>Warn Count</dt><dd>0</dd></div><div><dt>缺失数</dt><dd>0</dd></div><div><dt>本地蓝图</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>待补证据</dt><dd>4</dd></div></dl></div>
|
||||
<div class="panel"><h2>蓝图覆盖</h2><dl class='kv-grid'><div><dt>项目数</dt><dd>20</dd></div><div><dt>模块数</dt><dd>8</dd></div><div><dt>建议 PR</dt><dd>12</dd></div><div><dt>通过数</dt><dd>20</dd></div><div><dt>Warn Count</dt><dd>0</dd></div><div><dt>缺失数</dt><dd>0</dd></div><div><dt>Extension Track Count</dt><dd>2</dd></div><div><dt>Extension Partial Count</dt><dd>1</dd></div><div><dt>Extension Planned Count</dt><dd>1</dd></div><div><dt>Adaptive Extension Ready</dt><dd>否</dd></div><div><dt>本地蓝图</dt><dd>是</dd></div><div><dt>世界级</dt><dd>否</dd></div><div><dt>待补证据</dt><dd>4</dd></div></dl></div>
|
||||
<div class="panel"><h2>覆盖边界</h2><p>蓝图覆盖只证明 2.0 模块、建议 PR、脚本、报告和测试在本地闭环；public world-class 仍以 world-class evidence ledger 的真人和外部证据为准。</p></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>5</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
|
||||
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li><li><strong>阻断</strong><span>world-class source checks are not all accepted (6/13 pass, 7 blocked)</span></li></ul></div>
|
||||
</section>
|
||||
|
||||
<section class="twocol">
|
||||
|
||||
+201
-87
@@ -43,7 +43,7 @@
|
||||
"key": "context-budget",
|
||||
"label": "上下文",
|
||||
"status": "pass",
|
||||
"detail": "initial load 960/1000; deferred 404827/120000; top deferred scripts 357091; resource governance governed; quality density 135.4",
|
||||
"detail": "initial load 960/1000; deferred 406347/120000; top deferred scripts 358611; resource governance governed; quality density 135.4",
|
||||
"evidence": "reports/context_budget.json",
|
||||
"link": "context_budget.md"
|
||||
},
|
||||
@@ -1672,12 +1672,12 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021",
|
||||
"source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d",
|
||||
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1696,11 +1696,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 34
|
||||
},
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1805,7 +1805,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 186,
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1843,7 +1843,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1880,7 +1880,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1975,7 +1975,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -4342,7 +4342,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 33.02,
|
||||
"duration_ms": 33.2,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4370,7 +4370,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.88,
|
||||
"duration_ms": 32.82,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4393,7 +4393,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 36.03,
|
||||
"duration_ms": 33.01,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4421,7 +4421,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.76,
|
||||
"duration_ms": 32.83,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4444,7 +4444,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.27,
|
||||
"duration_ms": 30.81,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4472,7 +4472,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 32.3,
|
||||
"duration_ms": 35.47,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4495,7 +4495,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.36,
|
||||
"duration_ms": 31.19,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4522,7 +4522,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.3,
|
||||
"duration_ms": 29.94,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4545,7 +4545,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.1,
|
||||
"duration_ms": 30.34,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -4574,7 +4574,7 @@
|
||||
"execution_mode": "command",
|
||||
"model_executed": false,
|
||||
"command_executed": true,
|
||||
"duration_ms": 30.83,
|
||||
"duration_ms": 30.94,
|
||||
"provider": "local-output-eval-runner",
|
||||
"model": "",
|
||||
"usage": {
|
||||
@@ -5295,22 +5295,35 @@
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"skill_dir": ".",
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"git_status": {
|
||||
"available": true,
|
||||
"dirty": false,
|
||||
"changed_file_count": 0,
|
||||
"sample": [],
|
||||
"dirty": true,
|
||||
"changed_file_count": 34,
|
||||
"sample": [
|
||||
" M registry/index.json",
|
||||
" M registry/packages/yao-meta-skill.json",
|
||||
" M reports/adoption_drift_report.json",
|
||||
" M reports/architecture_maintainability.json",
|
||||
" M reports/architecture_maintainability.md",
|
||||
" M reports/context_budget.json",
|
||||
" M reports/context_budget.md",
|
||||
" M reports/context_budget_summary.json",
|
||||
" M reports/install_simulation.json",
|
||||
" M reports/install_simulation.md",
|
||||
" M reports/output_execution_runs.json",
|
||||
" M reports/output_execution_runs.md"
|
||||
],
|
||||
"scope": "generation-time status before this report is written"
|
||||
},
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021",
|
||||
"source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"evidence_bundle_sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d",
|
||||
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -5329,14 +5342,15 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 34
|
||||
},
|
||||
"public_claim": {
|
||||
"ready": false,
|
||||
"scope": "public benchmark or world-class readiness claim",
|
||||
"blockers": [
|
||||
"release lock is not clean or commit is unavailable",
|
||||
"provider-backed model holdout evidence is incomplete",
|
||||
"human blind-review adjudication is incomplete",
|
||||
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)",
|
||||
@@ -5345,10 +5359,10 @@
|
||||
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks."
|
||||
},
|
||||
"release_lock": {
|
||||
"ready": true,
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"ready": false,
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"status_scope": "generation-time status before this report is written",
|
||||
"reason": "clean generation-time HEAD"
|
||||
"reason": "working tree was dirty at generation time"
|
||||
},
|
||||
"evidence_bundle": {
|
||||
"algorithm": "sha256(path,label,exists,artifact_sha256)",
|
||||
@@ -5356,7 +5370,7 @@
|
||||
"existing_count": 24,
|
||||
"missing_count": 0,
|
||||
"missing_paths": [],
|
||||
"sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021"
|
||||
"sha256": "6e9d4ffd08e1345536b2b8a017761e75d11d8b4b7a9d86703a081fccaa10ba2d"
|
||||
},
|
||||
"methodology": {
|
||||
"path": "reports/benchmark_methodology.md",
|
||||
@@ -5429,8 +5443,8 @@
|
||||
"label": "output_execution",
|
||||
"path": "reports/output_execution_runs.json",
|
||||
"exists": true,
|
||||
"bytes": 7964,
|
||||
"sha256": "ebef496866a9d52e5a4cef5a855a997915b820612d87c777b85e3ed1f0458efc"
|
||||
"bytes": 7966,
|
||||
"sha256": "3d279da7e011bd3ed71c389195c0490f7dbb011dff90ebe99ff3db133f4a9fd6"
|
||||
},
|
||||
{
|
||||
"label": "blind_review",
|
||||
@@ -5465,7 +5479,7 @@
|
||||
"path": "reports/security_trust_report.json",
|
||||
"exists": true,
|
||||
"bytes": 101852,
|
||||
"sha256": "abe52fcdab2d2345783e353644acd66913995cc9048b3f3e0c758c5fca43672f"
|
||||
"sha256": "3cd8c1c2d119e2db480411a9839281e0a9e1b03eb4d9d535c9b0138ef72ba6e4"
|
||||
},
|
||||
{
|
||||
"label": "python_compatibility",
|
||||
@@ -5479,7 +5493,7 @@
|
||||
"path": "reports/registry_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 3183,
|
||||
"sha256": "e97001fe6bf7553dfc3f748d67146284d5e363336954bec7991dd0d6add240cb"
|
||||
"sha256": "9b8e6521f9455e654850975e3625132fb998ba4e03f7ceebaf4eded9ccd32bb5"
|
||||
},
|
||||
{
|
||||
"label": "package_verification",
|
||||
@@ -5492,15 +5506,15 @@
|
||||
"label": "install_simulation",
|
||||
"path": "reports/install_simulation.json",
|
||||
"exists": true,
|
||||
"bytes": 8604,
|
||||
"sha256": "d6972a9ab9966a8eff922b175f885b953c6300afd55bd4dc08b5baf20a518c20"
|
||||
"bytes": 8758,
|
||||
"sha256": "ee7554d8362d05f2bf6e7389e0524cd6336d42312ab7a05b9c0c6ddacdb0e339"
|
||||
},
|
||||
{
|
||||
"label": "skill_os2_audit",
|
||||
"path": "reports/skill_os2_audit.json",
|
||||
"exists": true,
|
||||
"bytes": 14310,
|
||||
"sha256": "cbce716b87a924ea08161d75851d14acb4ce76099f63ae4bc4f7bdf967f9f2fa"
|
||||
"sha256": "8a7f73832d4da2f63856d7f5be02488db6eac72a3a6149aa26a39c7a15a27053"
|
||||
},
|
||||
{
|
||||
"label": "world_class_evidence_plan",
|
||||
@@ -5695,6 +5709,11 @@
|
||||
"pass_count": 20,
|
||||
"warn_count": 0,
|
||||
"missing_count": 0,
|
||||
"extension_track_count": 2,
|
||||
"extension_partial_count": 1,
|
||||
"extension_planned_count": 1,
|
||||
"extension_covered_count": 0,
|
||||
"adaptive_extension_ready": false,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_evidence_pending_count": 4,
|
||||
@@ -5705,6 +5724,10 @@
|
||||
"warn": 0,
|
||||
"missing": 0
|
||||
},
|
||||
"extension_status_counts": {
|
||||
"partial": 1,
|
||||
"planned": 1
|
||||
},
|
||||
"modules": [
|
||||
{
|
||||
"key": "skill-ir",
|
||||
@@ -6285,14 +6308,105 @@
|
||||
"next_action": "Keep this item covered as the implementation evolves."
|
||||
}
|
||||
],
|
||||
"reference_extension_tracks": [
|
||||
{
|
||||
"key": "skill-interpretation-report",
|
||||
"label": "Skill Interpretation Report",
|
||||
"status": "partial",
|
||||
"objective": "User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.",
|
||||
"current": "Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.",
|
||||
"target": "Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.",
|
||||
"evidence": [
|
||||
{
|
||||
"path": "reports/skill-overview.html",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skill-overview.json",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_skill_overview.py",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_skill_interpretation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "schemas/skill-interpretation.schema.json",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_skill_interpretation.py",
|
||||
"exists": false
|
||||
}
|
||||
],
|
||||
"next_action": "Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests."
|
||||
},
|
||||
{
|
||||
"key": "adaptive-self-iteration",
|
||||
"label": "Adaptive Self-Iteration",
|
||||
"status": "planned",
|
||||
"objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.",
|
||||
"current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.",
|
||||
"target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.",
|
||||
"evidence": [
|
||||
{
|
||||
"path": "references/autonomous-adaptation.md",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "references/user-memory-policy.md",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "schemas/adaptation-proposal.schema.json",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/summarize_user_signals.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/propose_adaptation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/apply_adaptation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_adaptation_safety.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "reports/iteration-directions.md",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/adoption_drift_report.md",
|
||||
"exists": true
|
||||
}
|
||||
],
|
||||
"next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path."
|
||||
}
|
||||
],
|
||||
"next_highest_leverage": [
|
||||
"Close the four world-class evidence ledger entries with accepted human or external evidence.",
|
||||
"Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.",
|
||||
"Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.",
|
||||
"Keep the blueprint coverage report in CI so 2.0 plan drift is visible."
|
||||
],
|
||||
"source_blueprint": {
|
||||
"title": "Skill Overview / Skill OS 2.0 upgrade plan",
|
||||
"core_module_count": 8,
|
||||
"recommended_pr_count": 12
|
||||
"recommended_pr_count": 12,
|
||||
"reference_extension_count": 2,
|
||||
"reference_extensions": [
|
||||
"Skill interpretation report",
|
||||
"Adaptive self-iteration with local preference memory and approval gates"
|
||||
]
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skill_os2_coverage.json",
|
||||
@@ -10776,7 +10890,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"expected_capabilities": [
|
||||
"file_write",
|
||||
"network",
|
||||
@@ -10816,7 +10930,7 @@
|
||||
{
|
||||
"target": "openai",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/openai/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
|
||||
"permission_model": "metadata-only",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -10913,7 +11027,7 @@
|
||||
{
|
||||
"target": "claude",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/claude/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
|
||||
"permission_model": "neutral-source-plus-adapter",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -10995,7 +11109,7 @@
|
||||
{
|
||||
"target": "generic",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/generic/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
|
||||
"permission_model": "agent-skills-compatible-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -11077,7 +11191,7 @@
|
||||
{
|
||||
"target": "vscode",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/vscode/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
|
||||
"permission_model": "vscode-workspace-trust-plus-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -11188,7 +11302,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 186,
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
@@ -14796,6 +14910,13 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 745,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/yao_cli_parser.py",
|
||||
"lines": 741,
|
||||
@@ -14810,13 +14931,6 @@
|
||||
"severity": "pass",
|
||||
"recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_review_studio.py",
|
||||
"lines": 734,
|
||||
"kind": "test",
|
||||
"severity": "pass",
|
||||
"recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands."
|
||||
},
|
||||
{
|
||||
"path": "scripts/build_skill_atlas.py",
|
||||
"lines": 730,
|
||||
@@ -14868,15 +14982,15 @@
|
||||
"context_budget_tier": "production",
|
||||
"context_budget_limit": 1000,
|
||||
"skill_body_tokens": 767,
|
||||
"other_text_tokens": 1260693,
|
||||
"other_text_tokens": 1265424,
|
||||
"estimated_initial_load_tokens": 960,
|
||||
"estimated_total_text_tokens": 1261460,
|
||||
"deferred_resource_tokens": 404827,
|
||||
"estimated_total_text_tokens": 1266191,
|
||||
"deferred_resource_tokens": 406347,
|
||||
"deferred_resource_warn_threshold": 120000,
|
||||
"deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102
|
||||
},
|
||||
{
|
||||
@@ -14893,7 +15007,7 @@
|
||||
"large_deferred_resource_dirs": [
|
||||
{
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102
|
||||
}
|
||||
],
|
||||
@@ -14916,7 +15030,7 @@
|
||||
],
|
||||
"missing": [],
|
||||
"path": "scripts",
|
||||
"estimated_tokens": 357091,
|
||||
"estimated_tokens": 358611,
|
||||
"file_count": 102,
|
||||
"rationale": "Script resources are deterministic deferred tools, not initial-load prompt context."
|
||||
}
|
||||
@@ -15767,7 +15881,7 @@
|
||||
},
|
||||
"catalog": {
|
||||
"workspace_root": ".",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skills": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
@@ -15952,8 +16066,8 @@
|
||||
"report": "reports/adoption_drift_report.json",
|
||||
"risk_band": "low",
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
@@ -16616,7 +16730,7 @@
|
||||
"name": "incident-command-governor",
|
||||
"path": "examples/governed-incident-command/generated-skill",
|
||||
"reason": "review overdue by cadence monthly",
|
||||
"age_days": 76,
|
||||
"age_days": 74,
|
||||
"allowed_days": 31,
|
||||
"actionable": false,
|
||||
"scope": "example"
|
||||
@@ -16784,7 +16898,7 @@
|
||||
"adoption_drift": {
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-14T07:17:33Z",
|
||||
"generated_at": "2026-06-15T11:05:04Z",
|
||||
"skill_dir": ".",
|
||||
"privacy_contract": {
|
||||
"storage": "local-first",
|
||||
@@ -16869,7 +16983,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"generated_at": "2026-06-14",
|
||||
"generated_at": "2026-06-15",
|
||||
"summary": {
|
||||
"waiver_count": 0,
|
||||
"active_count": 0,
|
||||
@@ -16919,7 +17033,7 @@
|
||||
"Reviewer links output_review_adjudication or output_execution evidence."
|
||||
],
|
||||
"suggested_evidence": "reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-15 --evidence reports/output_review_adjudication.md",
|
||||
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
|
||||
},
|
||||
{
|
||||
@@ -19020,7 +19134,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -19057,11 +19171,11 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
},
|
||||
"index": {
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"package_count": 1,
|
||||
"packages": [
|
||||
{
|
||||
@@ -19077,7 +19191,7 @@
|
||||
"vscode"
|
||||
],
|
||||
"package_metadata": "registry/packages/yao-meta-skill.json",
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -19759,11 +19873,11 @@
|
||||
"install_simulation": {
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"install_root": "dist/install-simulation/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill",
|
||||
"installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill",
|
||||
"summary": {
|
||||
"archive_present": true,
|
||||
"archive_entry_count": 586,
|
||||
@@ -19784,7 +19898,7 @@
|
||||
{
|
||||
"id": "archive-present",
|
||||
"status": "pass",
|
||||
"detail": "Package archive exists: dist/yao-meta-skill.zip"
|
||||
"detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip"
|
||||
},
|
||||
{
|
||||
"id": "archive-safe-paths",
|
||||
@@ -20030,16 +20144,16 @@
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
"artifacts": {
|
||||
"archive": "dist/yao-meta-skill.zip",
|
||||
"package_manifest": "dist/manifest.json",
|
||||
"json": "reports/install_simulation.json",
|
||||
"markdown": "reports/install_simulation.md"
|
||||
"archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip",
|
||||
"package_manifest": "tests/tmp_review_studio/dist/manifest.json",
|
||||
"json": "tests/tmp_review_studio/install_simulation.json",
|
||||
"markdown": "tests/tmp_review_studio/install_simulation.md"
|
||||
}
|
||||
},
|
||||
"upgrade_check": {
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"previous": {
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.0.0",
|
||||
@@ -20113,7 +20227,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -20128,8 +20242,8 @@
|
||||
"artifacts": {
|
||||
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
|
||||
"current_package": "reports/registry_audit.json",
|
||||
"json": "reports/upgrade_check.json",
|
||||
"markdown": "reports/upgrade_check.md"
|
||||
"json": "tests/tmp_review_studio/upgrade_check.json",
|
||||
"markdown": "tests/tmp_review_studio/upgrade_check.md"
|
||||
}
|
||||
},
|
||||
"manifest": {
|
||||
|
||||
+11
-11
@@ -995,12 +995,12 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021",
|
||||
"source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
|
||||
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1019,11 +1019,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 38
|
||||
},
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1128,7 +1128,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 186,
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1166,7 +1166,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1203,7 +1203,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1298,7 +1298,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"source": "reports/review_annotations_input.json",
|
||||
"source": "tests/tmp_review_studio/empty_review_annotations_input.json",
|
||||
"summary": {
|
||||
"annotation_count": 0,
|
||||
"open_count": 0,
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"generated_at": "2026-06-14",
|
||||
"generated_at": "2026-06-13",
|
||||
"summary": {
|
||||
"waiver_count": 0,
|
||||
"active_count": 0,
|
||||
@@ -52,7 +52,7 @@
|
||||
"Reviewer links output_review_adjudication or output_execution evidence."
|
||||
],
|
||||
"suggested_evidence": "reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md",
|
||||
"suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"<reviewer>\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md",
|
||||
"world_class_boundary": "Does not count as provider, human, or public world-class completion evidence."
|
||||
},
|
||||
{
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
- waiver allowed: `true`
|
||||
- risk: review pending 5; model-executed 0; output failures 0
|
||||
- evidence: `reports/output_review_adjudication.md`
|
||||
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md`
|
||||
- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "<reviewer>" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md`
|
||||
- world-class boundary: Does not count as provider, human, or public world-class completion evidence.
|
||||
|
||||
#### Required Review
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"skill_dir": ".",
|
||||
"package_dir": "dist",
|
||||
"package_dir": "tests/tmp_review_studio/dist",
|
||||
"expected_capabilities": [
|
||||
"file_write",
|
||||
"network",
|
||||
@@ -42,7 +42,7 @@
|
||||
{
|
||||
"target": "openai",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/openai/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json",
|
||||
"permission_model": "metadata-only",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -139,7 +139,7 @@
|
||||
{
|
||||
"target": "claude",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/claude/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json",
|
||||
"permission_model": "neutral-source-plus-adapter",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -221,7 +221,7 @@
|
||||
{
|
||||
"target": "generic",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/generic/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json",
|
||||
"permission_model": "agent-skills-compatible-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
@@ -303,7 +303,7 @@
|
||||
{
|
||||
"target": "vscode",
|
||||
"status": "pass",
|
||||
"adapter": "dist/targets/vscode/adapter.json",
|
||||
"adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json",
|
||||
"permission_model": "vscode-workspace-trust-plus-metadata",
|
||||
"native_enforcement": false,
|
||||
"metadata_fallback_explicit": true,
|
||||
|
||||
@@ -23,7 +23,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 186,
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": [],
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
- Interactive scripts: `0`
|
||||
- Package hash scope: `source-contract-without-generated-reports`
|
||||
- Package hash files: `186`
|
||||
- Package SHA256: `0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822`
|
||||
- Package SHA256: `fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5`
|
||||
|
||||
## Failures
|
||||
|
||||
|
||||
+11
-11
@@ -994,12 +994,12 @@
|
||||
"ok": true,
|
||||
"summary": {
|
||||
"reproducibility_ready": true,
|
||||
"release_lock_ready": true,
|
||||
"release_lock_ready": false,
|
||||
"methodology_complete": true,
|
||||
"required_artifact_count": 24,
|
||||
"missing_artifact_count": 0,
|
||||
"evidence_bundle_sha256": "dccce4bcf5fee2f76a6c3fcdfceafada3bdadf67371edaafebcd69208194e021",
|
||||
"source_contract_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"evidence_bundle_sha256": "3b2b3f509e12a9445841c30b8b2cf5eb0f955d30402a95d54844b70c60d87a56",
|
||||
"source_contract_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
||||
"output_case_count": 5,
|
||||
"failure_disclosure_count": 3,
|
||||
@@ -1018,11 +1018,11 @@
|
||||
"world_class_source_pass_count": 6,
|
||||
"world_class_source_blocked_count": 7,
|
||||
"public_claim_ready": false,
|
||||
"public_claim_blocker_count": 4,
|
||||
"working_tree_dirty": false,
|
||||
"changed_file_count": 0
|
||||
"public_claim_blocker_count": 5,
|
||||
"working_tree_dirty": true,
|
||||
"changed_file_count": 38
|
||||
},
|
||||
"commit": "5f187cdb46510a6881a8353c0c1744b90e0b05bd",
|
||||
"commit": "7acc6d9cf780e38570c20813186d0efea5ac8ad0",
|
||||
"missing_artifacts": [],
|
||||
"limitations": [
|
||||
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
||||
@@ -1127,7 +1127,7 @@
|
||||
"interactive_script_count": 0,
|
||||
"package_hash_scope": "source-contract-without-generated-reports",
|
||||
"package_hash_file_count": 186,
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
},
|
||||
"skill_atlas": {
|
||||
"skill_count": 12,
|
||||
@@ -1165,7 +1165,7 @@
|
||||
"trust_level": "local",
|
||||
"license": "MIT",
|
||||
"checksums": {
|
||||
"package_sha256": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822",
|
||||
"package_sha256": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5",
|
||||
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
||||
},
|
||||
"compatibility": {
|
||||
@@ -1202,7 +1202,7 @@
|
||||
"install_simulated": true,
|
||||
"install_simulation": "reports/install_simulation.json"
|
||||
},
|
||||
"generated_at": "2026-06-15"
|
||||
"generated_at": "2026-06-13"
|
||||
},
|
||||
"failures": [],
|
||||
"warnings": []
|
||||
@@ -1297,7 +1297,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -44,7 +44,7 @@
|
||||
},
|
||||
"catalog": {
|
||||
"workspace_root": ".",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skills": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
@@ -229,8 +229,8 @@
|
||||
"report": "reports/adoption_drift_report.json",
|
||||
"risk_band": "low",
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
@@ -893,7 +893,7 @@
|
||||
"name": "incident-command-governor",
|
||||
"path": "examples/governed-incident-command/generated-skill",
|
||||
"reason": "review overdue by cadence monthly",
|
||||
"age_days": 76,
|
||||
"age_days": 74,
|
||||
"allowed_days": 31,
|
||||
"actionable": false,
|
||||
"scope": "example"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 15,
|
||||
@@ -351,7 +351,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
@@ -433,7 +433,7 @@
|
||||
"key": "native-client-telemetry",
|
||||
"label": "Native Client Telemetry",
|
||||
"status": "external_required",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"target": "A real Browser/Chrome/provider client sends production metadata events",
|
||||
"evidence": [
|
||||
{
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Audit
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -30,7 +30,7 @@ Generated at: `2026-06-15`
|
||||
| Registry Distribution | pass | zip entries 586; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
|
||||
| Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
|
||||
| Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. |
|
||||
|
||||
## Open Highest-Leverage Gaps
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"item_count": 20,
|
||||
@@ -10,6 +10,11 @@
|
||||
"pass_count": 20,
|
||||
"warn_count": 0,
|
||||
"missing_count": 0,
|
||||
"extension_track_count": 2,
|
||||
"extension_partial_count": 1,
|
||||
"extension_planned_count": 1,
|
||||
"extension_covered_count": 0,
|
||||
"adaptive_extension_ready": false,
|
||||
"local_blueprint_ready": true,
|
||||
"public_world_class_ready": false,
|
||||
"world_class_evidence_pending_count": 4,
|
||||
@@ -20,6 +25,10 @@
|
||||
"warn": 0,
|
||||
"missing": 0
|
||||
},
|
||||
"extension_status_counts": {
|
||||
"partial": 1,
|
||||
"planned": 1
|
||||
},
|
||||
"modules": [
|
||||
{
|
||||
"key": "skill-ir",
|
||||
@@ -600,14 +609,105 @@
|
||||
"next_action": "Keep this item covered as the implementation evolves."
|
||||
}
|
||||
],
|
||||
"reference_extension_tracks": [
|
||||
{
|
||||
"key": "skill-interpretation-report",
|
||||
"label": "Skill Interpretation Report",
|
||||
"status": "partial",
|
||||
"objective": "User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.",
|
||||
"current": "Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.",
|
||||
"target": "Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.",
|
||||
"evidence": [
|
||||
{
|
||||
"path": "reports/skill-overview.html",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/skill-overview.json",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_skill_overview.py",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "scripts/render_skill_interpretation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "schemas/skill-interpretation.schema.json",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_skill_interpretation.py",
|
||||
"exists": false
|
||||
}
|
||||
],
|
||||
"next_action": "Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests."
|
||||
},
|
||||
{
|
||||
"key": "adaptive-self-iteration",
|
||||
"label": "Adaptive Self-Iteration",
|
||||
"status": "planned",
|
||||
"objective": "Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.",
|
||||
"current": "The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.",
|
||||
"target": "Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.",
|
||||
"evidence": [
|
||||
{
|
||||
"path": "references/autonomous-adaptation.md",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "references/user-memory-policy.md",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "schemas/adaptation-proposal.schema.json",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/summarize_user_signals.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/propose_adaptation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "scripts/apply_adaptation.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "tests/verify_adaptation_safety.py",
|
||||
"exists": false
|
||||
},
|
||||
{
|
||||
"path": "reports/iteration-directions.md",
|
||||
"exists": true
|
||||
},
|
||||
{
|
||||
"path": "reports/adoption_drift_report.md",
|
||||
"exists": true
|
||||
}
|
||||
],
|
||||
"next_action": "Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path."
|
||||
}
|
||||
],
|
||||
"next_highest_leverage": [
|
||||
"Close the four world-class evidence ledger entries with accepted human or external evidence.",
|
||||
"Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.",
|
||||
"Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.",
|
||||
"Keep the blueprint coverage report in CI so 2.0 plan drift is visible."
|
||||
],
|
||||
"source_blueprint": {
|
||||
"title": "Skill Overview / Skill OS 2.0 upgrade plan",
|
||||
"core_module_count": 8,
|
||||
"recommended_pr_count": 12
|
||||
"recommended_pr_count": 12,
|
||||
"reference_extension_count": 2,
|
||||
"reference_extensions": [
|
||||
"Skill interpretation report",
|
||||
"Adaptive self-iteration with local preference memory and approval gates"
|
||||
]
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skill_os2_coverage.json",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Skill OS 2.0 Blueprint Coverage
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -10,6 +10,10 @@ Generated at: `2026-06-15`
|
||||
- pass: `20` / `20`
|
||||
- missing: `0`
|
||||
- warn: `0`
|
||||
- reference extensions: `2`
|
||||
- extension partial: `1`
|
||||
- extension planned: `1`
|
||||
- adaptive extension ready: `false`
|
||||
- world-class evidence pending: `4`
|
||||
|
||||
This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, commands, and tests. It does not count pending human review, provider runs, metadata fallbacks, or planned work as public world-class evidence.
|
||||
@@ -44,9 +48,20 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
| Review Studio 2.0 | `pass` | 16 review gates | `make ci-test` | `tests/verify_review_studio.py` |
|
||||
| Migration V2 Docs | `pass` | migration guide present | `make ci-test` | `docs review` |
|
||||
|
||||
## Reference Extension Tracks
|
||||
|
||||
| Track | Status | Current | Target | Next action |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| Skill Interpretation Report | `partial` | Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet. | Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests. | Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests. |
|
||||
| Adaptive Self-Iteration | `planned` | The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy. | Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan. | Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. |
|
||||
|
||||
These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution.
|
||||
|
||||
## Next Highest-Leverage Moves
|
||||
|
||||
- Close the four world-class evidence ledger entries with accepted human or external evidence.
|
||||
- Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.
|
||||
- Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.
|
||||
- Keep the blueprint coverage report in CI so 2.0 plan drift is visible.
|
||||
|
||||
## Evidence Detail
|
||||
@@ -190,3 +205,19 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
|
||||
- status: `pass`
|
||||
- existing evidence: `docs/migration-v2.md`, `reports/skill-os-2-review.md`, `README.md`
|
||||
- next action: Keep this item covered as the implementation evolves.
|
||||
|
||||
### Skill Interpretation Report
|
||||
|
||||
- objective: User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.
|
||||
- status: `partial`
|
||||
- existing evidence: `reports/skill-overview.html`, `reports/skill-overview.json`, `scripts/render_skill_overview.py`
|
||||
- missing evidence: `scripts/render_skill_interpretation.py`, `schemas/skill-interpretation.schema.json`, `tests/verify_skill_interpretation.py`
|
||||
- next action: Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests.
|
||||
|
||||
### Adaptive Self-Iteration
|
||||
|
||||
- objective: Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.
|
||||
- status: `planned`
|
||||
- existing evidence: `reports/iteration-directions.md`, `reports/adoption_drift_report.md`
|
||||
- missing evidence: `references/autonomous-adaptation.md`, `references/user-memory-policy.md`, `schemas/adaptation-proposal.schema.json`, `scripts/summarize_user_signals.py`, `scripts/propose_adaptation.py`, `scripts/apply_adaptation.py`, `tests/verify_adaptation_safety.py`
|
||||
- next action: Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path.
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"ok": true,
|
||||
"schema_version": "2.0",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"previous": {
|
||||
"name": "yao-meta-skill",
|
||||
"version": "1.0.0",
|
||||
@@ -75,7 +75,7 @@
|
||||
{
|
||||
"field": "package_sha256",
|
||||
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
||||
"to": "0a4768c86c9af215719c0b76036499fc1b2324a0045914d54f3df1e2860fb822"
|
||||
"to": "fe193ec81d0e9ce9e1eeed5ea6d8aa0dcf63506ce4f3e92b93da93536644c4f5"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -90,7 +90,7 @@
|
||||
"artifacts": {
|
||||
"previous_package": "registry/examples/yao-meta-skill-1.0.0.json",
|
||||
"current_package": "reports/registry_audit.json",
|
||||
"json": "reports/upgrade_check.json",
|
||||
"markdown": "reports/upgrade_check.md"
|
||||
"json": "tests/tmp_review_studio/upgrade_check.json",
|
||||
"markdown": "tests/tmp_review_studio/upgrade_check.md"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"ledger_ready_to_claim_world_class": false,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Claim Guard
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"schema_present": true,
|
||||
@@ -307,7 +307,7 @@
|
||||
"source_accepted": false,
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Intake
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"ledger_entry_count": 4,
|
||||
@@ -14,8 +14,8 @@
|
||||
"missing_submission_count": 4,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"submitted_but_pending_count": 0,
|
||||
"source_accepted_without_valid_submission_count": 0,
|
||||
"overclaim_guard_active": true,
|
||||
@@ -351,7 +351,7 @@
|
||||
"status": "pending",
|
||||
"source_status": "external_required",
|
||||
"source_accepted": false,
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -388,7 +388,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -409,8 +409,8 @@
|
||||
"label": "Adoption sample",
|
||||
"field": "adoption_sample_count",
|
||||
"expected": ">0",
|
||||
"actual": 0,
|
||||
"status": "blocked",
|
||||
"actual": 1,
|
||||
"status": "pass",
|
||||
"source_accepted": false,
|
||||
"next_action": "Telemetry must include adoption outcome evidence."
|
||||
},
|
||||
@@ -426,8 +426,8 @@
|
||||
}
|
||||
],
|
||||
"source_check_count": 3,
|
||||
"source_pass_count": 1,
|
||||
"source_blocked_count": 2,
|
||||
"source_pass_count": 2,
|
||||
"source_blocked_count": 1,
|
||||
"submission_state": {
|
||||
"status": "missing",
|
||||
"path": "evidence/world_class/submissions/native-client-telemetry.json",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Ledger
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -8,8 +8,8 @@ Generated at: `2026-06-15`
|
||||
- ready to claim world-class: `false`
|
||||
- entries: `4`
|
||||
- source accepted: `0`
|
||||
- source checks: `6` pass / `13` total
|
||||
- source blocked: `7`
|
||||
- source checks: `7` pass / `13` total
|
||||
- source blocked: `6`
|
||||
- accepted: `0`
|
||||
- pending: `4`
|
||||
- human pending: `1`
|
||||
@@ -29,7 +29,7 @@ This ledger records the current evidence state. It requires both passing source
|
||||
| `provider-holdout` | `pending` | `missing` | `external` | model-executed 0; token-observed 0 | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
|
||||
| `human-adjudication` | `pending` | `missing` | `human` | 0/5 decisions; pending 5 | Record real A/B choices in the decision template, then regenerate adjudication. |
|
||||
| `native-permission-enforcement` | `pending` | `missing` | `external` | native-enforced targets 0; installer-enforced targets 4 | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. |
|
||||
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. |
|
||||
| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. |
|
||||
|
||||
## Provider Holdout
|
||||
|
||||
@@ -167,8 +167,8 @@ This ledger records the current evidence state. It requires both passing source
|
||||
|
||||
- objective: Import production metadata-only events from a real external client into the local drift loop.
|
||||
- source status: `external_required`
|
||||
- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
|
||||
- source checks: `1` pass / `3` total
|
||||
- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}`
|
||||
- source checks: `2` pass / `3` total
|
||||
- submission state: `{"status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", "artifact_ref_count": 0, "attested_real_evidence": false, "privacy_contract_satisfied": false, "ledger_counts_as_completion": false}`
|
||||
|
||||
### Provenance Requirements
|
||||
@@ -192,7 +192,7 @@ This ledger records the current evidence state. It requires both passing source
|
||||
| Check | Current | Expected | Status |
|
||||
| --- | --- | --- | --- |
|
||||
| External events | `0` | `>0` | `blocked` |
|
||||
| Adoption sample | `0` | `>0` | `blocked` |
|
||||
| Adoption sample | `1` | `>0` | `pass` |
|
||||
| Raw content blocked | `False` | `false` | `pass` |
|
||||
|
||||
### Completion Assertions
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"audit_decision": "continue-iteration",
|
||||
@@ -141,7 +141,7 @@
|
||||
"status": "external_required",
|
||||
"category": "external",
|
||||
"owner": "Browser/Chrome/IDE/provider client integrator",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
@@ -299,7 +299,7 @@
|
||||
"status": "external_required",
|
||||
"category": "external",
|
||||
"owner": "Browser/Chrome/IDE/provider client integrator",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Evidence Plan
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -22,7 +22,7 @@ This report is an execution plan for the remaining world-class evidence gaps. It
|
||||
| `provider-holdout` | `external_required` | `external` | operator with provider credentials | model-executed 0; token-observed 0 |
|
||||
| `human-adjudication` | `human_required` | `human` | human reviewer | 0/5 decisions; pending 5 |
|
||||
| `native-permission-enforcement` | `external_required` | `external` | target client or installer integrator | native-enforced targets 0; installer-enforced targets 4 |
|
||||
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 |
|
||||
| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 |
|
||||
|
||||
## Provider Holdout
|
||||
|
||||
|
||||
@@ -57,7 +57,7 @@
|
||||
<span class="eyebrow">Evidence Operations</span>
|
||||
<h1>World-Class Operator Runbook</h1>
|
||||
<p class="lede">A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.</p>
|
||||
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>6/13</strong></article><article><span>Blocked</span><strong>7</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
|
||||
<div class="stats"><article><span>Pending</span><strong>4</strong></article><article><span>Awaiting</span><strong>4</strong></article><article><span>Ready</span><strong>0</strong></article><article><span>Source</span><strong>7/13</strong></article><article><span>Blocked</span><strong>6</strong></article><article><span>Invalid</span><strong>0</strong></article></div>
|
||||
</section>
|
||||
<section class="section panel" id="fast-path"><h2>Fast Path</h2><ol><li>Run the real external or human work for one evidence item.</li><li>Generate and fill the matching submission draft.</li><li>Validate intake and inspect the submission review queue.</li><li>Refresh the ledger and run the claim guard before making any completion claim.</li></ol></section>
|
||||
<section class="section" id="items"><h2>Evidence Items</h2><div class="item-grid"><article class="item-card awaiting-submission">
|
||||
@@ -120,7 +120,7 @@
|
||||
<dl>
|
||||
<dt>Owner</dt><dd>Browser/Chrome/IDE/provider client integrator</dd>
|
||||
<dt>Ledger</dt><dd><code>pending</code></dd>
|
||||
<dt>Blocked</dt><dd><code>2</code></dd>
|
||||
<dt>Blocked</dt><dd><code>1</code></dd>
|
||||
<dt>Submission</dt><dd><code>evidence/world_class/submissions/native-client-telemetry.json</code></dd>
|
||||
</dl>
|
||||
<section class="source-panel"><h4>Source Runbook</h4><ul><li>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>/</li><li>Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.</li><li>python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl</li><li>python3 scripts/yao.py skill-atlas --workspace-root .</li><li>python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD></li><li>Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.</li><li>python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions</li></ul></section>
|
||||
@@ -130,8 +130,8 @@
|
||||
<section><h4>Success Checks</h4><ul><li>reports/adoption_drift_report.json summary.source_types.external > 0</li><li>reports/adoption_drift_report.json summary.adoption_sample_count > 0</li><li>reports/skill_os2_audit.json item native-client-telemetry status becomes pass</li></ul></section>
|
||||
<section><h4>Privacy</h4><ul><li>Telemetry must remain metadata-only and local-first.</li><li>Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.</li></ul></section>
|
||||
</div>
|
||||
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li><li>Telemetry must include adoption outcome evidence.</li></ul></section>
|
||||
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / >0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check blocked'><span>Adoption sample</span><code>adoption_sample_count: 0 / >0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
|
||||
<section class="source-panel"><h4>Next Source Actions</h4><ul><li>Import at least one metadata-only event from a real client.</li></ul></section>
|
||||
<section class="source-panel"><h4>Source Evidence Snapshot</h4><ul class='source-checks'><li class='source-check blocked'><span>External events</span><code>external_source_events: 0 / >0</code><small>Import at least one metadata-only event from a real client.</small></li><li class='source-check pass'><span>Adoption sample</span><code>adoption_sample_count: 1 / >0</code><small>Telemetry must include adoption outcome evidence.</small></li><li class='source-check pass'><span>Raw content blocked</span><code>raw_content_allowed: False / false</code><small>Telemetry must stay metadata-only.</small></li></ul></section>
|
||||
</article></div></section>
|
||||
<section class="section panel" id="boundary"><h2>Boundary</h2><ul><li>Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.</li><li>Valid intake means ready for submission review; ledger review still requires passing source evidence.</li><li>The world-class ledger and claim guard remain the source of truth.</li></ul></section>
|
||||
</main>
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"evidence_item_count": 4,
|
||||
@@ -12,8 +12,8 @@
|
||||
"valid_packet_source_incomplete_count": 0,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"ready_to_claim_world_class": false,
|
||||
"runbook_counts_as_completion": false,
|
||||
"decision": "collect-evidence"
|
||||
@@ -394,7 +394,7 @@
|
||||
"review_state": "awaiting-submission",
|
||||
"source_accepted": false,
|
||||
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
||||
"current": "external source events 0; adoption samples 0",
|
||||
"current": "external source events 0; adoption samples 1",
|
||||
"execution_runbook": [
|
||||
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
||||
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
||||
@@ -442,7 +442,7 @@
|
||||
],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -463,8 +463,8 @@
|
||||
"label": "Adoption sample",
|
||||
"field": "adoption_sample_count",
|
||||
"expected": ">0",
|
||||
"actual": 0,
|
||||
"status": "blocked",
|
||||
"actual": 1,
|
||||
"status": "pass",
|
||||
"source_accepted": false,
|
||||
"next_action": "Telemetry must include adoption outcome evidence."
|
||||
},
|
||||
@@ -479,10 +479,9 @@
|
||||
"next_action": "Telemetry must stay metadata-only."
|
||||
}
|
||||
],
|
||||
"blocked_source_check_count": 2,
|
||||
"blocked_source_check_count": 1,
|
||||
"next_source_actions": [
|
||||
"Import at least one metadata-only event from a real client.",
|
||||
"Telemetry must include adoption outcome evidence."
|
||||
"Import at least one metadata-only event from a real client."
|
||||
],
|
||||
"submission_state": {
|
||||
"status": "missing",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Operator Runbook
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -28,7 +28,7 @@ This runbook coordinates evidence collection only. It does not accept submission
|
||||
| `provider-holdout` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Run provider-backed output-exec with real credentials. | operator with provider credentials |
|
||||
| `human-adjudication` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Record a reviewer choice for every pair. | human reviewer |
|
||||
| `native-permission-enforcement` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Collect real target-client or external runtime guard proof. | target client or installer integrator |
|
||||
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `2` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
|
||||
| `native-client-telemetry` | `pending` | `awaiting-submission` | `awaiting-submission` | `1` | Import at least one metadata-only event from a real client. | Browser/Chrome/IDE/provider client integrator |
|
||||
|
||||
## Provider Holdout
|
||||
|
||||
@@ -239,7 +239,7 @@ This runbook coordinates evidence collection only. It does not accept submission
|
||||
|
||||
- objective: Import production metadata-only events from a real external client into the local drift loop.
|
||||
- blocking reason: No evidence packet has been submitted for review.
|
||||
- blocked source checks: `2`
|
||||
- blocked source checks: `1`
|
||||
- submission: `evidence/world_class/submissions/native-client-telemetry.json`
|
||||
- template: `evidence/world_class/templates/native-client-telemetry.intake.json`
|
||||
|
||||
@@ -292,14 +292,13 @@ This runbook coordinates evidence collection only. It does not accept submission
|
||||
### Next Source Actions
|
||||
|
||||
- Import at least one metadata-only event from a real client.
|
||||
- Telemetry must include adoption outcome evidence.
|
||||
|
||||
### Source Evidence Snapshot
|
||||
|
||||
| Check | Current | Expected | Status | Next action |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. |
|
||||
| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. |
|
||||
| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. |
|
||||
| Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. |
|
||||
|
||||
## Boundary
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"schema_version": "1.0",
|
||||
"ok": true,
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skill_dir": ".",
|
||||
"summary": {
|
||||
"review_item_count": 4,
|
||||
@@ -13,8 +13,8 @@
|
||||
"unmatched_submission_count": 0,
|
||||
"invalid_submission_count": 0,
|
||||
"source_check_count": 13,
|
||||
"source_pass_count": 6,
|
||||
"source_blocked_count": 7,
|
||||
"source_pass_count": 7,
|
||||
"source_blocked_count": 6,
|
||||
"ready_to_claim_world_class": false,
|
||||
"review_counts_submission_as_completion": false,
|
||||
"decision": "awaiting-submissions"
|
||||
@@ -265,7 +265,7 @@
|
||||
"intake_errors": [],
|
||||
"observed_state": {
|
||||
"external_source_events": 0,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"raw_content_allowed": false,
|
||||
"risk_band": "low",
|
||||
"accepted": false
|
||||
@@ -286,8 +286,8 @@
|
||||
"label": "Adoption sample",
|
||||
"field": "adoption_sample_count",
|
||||
"expected": ">0",
|
||||
"actual": 0,
|
||||
"status": "blocked",
|
||||
"actual": 1,
|
||||
"status": "pass",
|
||||
"source_accepted": false,
|
||||
"next_action": "Telemetry must include adoption outcome evidence."
|
||||
},
|
||||
@@ -303,8 +303,8 @@
|
||||
}
|
||||
],
|
||||
"source_check_count": 3,
|
||||
"source_pass_count": 1,
|
||||
"source_blocked_count": 2,
|
||||
"source_pass_count": 2,
|
||||
"source_blocked_count": 1,
|
||||
"success_checks": [
|
||||
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
||||
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# World-Class Submission Review
|
||||
|
||||
Generated at: `2026-06-15`
|
||||
Generated at: `2026-06-13`
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -138,7 +138,7 @@ This report is a read-only reviewer queue. It does not accept evidence or make w
|
||||
#### Source Checks
|
||||
|
||||
- External events: 0 / >0 => blocked
|
||||
- Adoption sample: 0 / >0 => blocked
|
||||
- Adoption sample: 1 / >0 => pass
|
||||
- Raw content blocked: False / false => pass
|
||||
|
||||
#### Completion Assertions
|
||||
|
||||
@@ -247,6 +247,10 @@ def render_html(report: dict[str, Any]) -> str:
|
||||
"pass_count",
|
||||
"warn_count",
|
||||
"missing_count",
|
||||
"extension_track_count",
|
||||
"extension_partial_count",
|
||||
"extension_planned_count",
|
||||
"adaptive_extension_ready",
|
||||
"local_blueprint_ready",
|
||||
"public_world_class_ready",
|
||||
"world_class_evidence_pending_count",
|
||||
|
||||
@@ -86,6 +86,30 @@ def build_item(
|
||||
}
|
||||
|
||||
|
||||
def build_extension_track(
|
||||
*,
|
||||
key: str,
|
||||
label: str,
|
||||
status: str,
|
||||
objective: str,
|
||||
current: str,
|
||||
target: str,
|
||||
artifact_paths: list[str],
|
||||
next_action: str,
|
||||
skill_dir: Path,
|
||||
) -> dict[str, Any]:
|
||||
return {
|
||||
"key": key,
|
||||
"label": label,
|
||||
"status": status,
|
||||
"objective": objective,
|
||||
"current": current,
|
||||
"target": target,
|
||||
"evidence": evidence(skill_dir, artifact_paths),
|
||||
"next_action": next_action,
|
||||
}
|
||||
|
||||
|
||||
def summary_value(payload: dict[str, Any], key: str, default: Any = 0) -> Any:
|
||||
summary = payload.get("summary", {})
|
||||
return summary.get(key, default) if isinstance(summary, dict) else default
|
||||
@@ -273,6 +297,51 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
for key, path_a, path_b, path_c, condition, current in recommended_prs
|
||||
]
|
||||
|
||||
extension_tracks = [
|
||||
build_extension_track(
|
||||
key="skill-interpretation-report",
|
||||
label="Skill Interpretation Report",
|
||||
status="partial",
|
||||
objective="User-facing deep interpretation report explains use cases, triggers, inputs, outputs, workflow, principles, boundaries, quality gates, examples, and next iterations.",
|
||||
current="Skill Overview v2 already covers much of the explainer experience, but dedicated skill-interpretation JSON/MD/HTML artifacts are not first-class yet.",
|
||||
target="Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests.",
|
||||
artifact_paths=[
|
||||
"reports/skill-overview.html",
|
||||
"reports/skill-overview.json",
|
||||
"scripts/render_skill_overview.py",
|
||||
"scripts/render_skill_interpretation.py",
|
||||
"schemas/skill-interpretation.schema.json",
|
||||
"tests/verify_skill_interpretation.py",
|
||||
],
|
||||
next_action="Decide whether overview v2 is the canonical interpretation surface; if not, add a dedicated schema, renderer, and CJK/path-safety tests.",
|
||||
skill_dir=skill_dir,
|
||||
),
|
||||
build_extension_track(
|
||||
key="adaptive-self-iteration",
|
||||
label="Adaptive Self-Iteration",
|
||||
status="planned",
|
||||
objective="Local-first preference memory, repeated-signal extraction, adaptation proposals, approval, patch application, regression evidence, and rollback.",
|
||||
current="The repo has feedback, iteration, telemetry, and review artifacts, but no adapt-scan/adapt-propose/adapt-apply approval loop and no user-memory policy.",
|
||||
target="Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan.",
|
||||
artifact_paths=[
|
||||
"references/autonomous-adaptation.md",
|
||||
"references/user-memory-policy.md",
|
||||
"schemas/adaptation-proposal.schema.json",
|
||||
"scripts/summarize_user_signals.py",
|
||||
"scripts/propose_adaptation.py",
|
||||
"scripts/apply_adaptation.py",
|
||||
"tests/verify_adaptation_safety.py",
|
||||
"reports/iteration-directions.md",
|
||||
"reports/adoption_drift_report.md",
|
||||
],
|
||||
next_action="Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path.",
|
||||
skill_dir=skill_dir,
|
||||
),
|
||||
]
|
||||
extension_counts: dict[str, int] = {}
|
||||
for item in extension_tracks:
|
||||
extension_counts[item["status"]] = extension_counts.get(item["status"], 0) + 1
|
||||
|
||||
items = modules + pr_items
|
||||
counts: dict[str, int] = {"pass": 0, "warn": 0, "missing": 0}
|
||||
for item in items:
|
||||
@@ -287,6 +356,11 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
"pass_count": counts.get("pass", 0),
|
||||
"warn_count": counts.get("warn", 0),
|
||||
"missing_count": counts.get("missing", 0),
|
||||
"extension_track_count": len(extension_tracks),
|
||||
"extension_partial_count": extension_counts.get("partial", 0),
|
||||
"extension_planned_count": extension_counts.get("planned", 0),
|
||||
"extension_covered_count": extension_counts.get("covered", 0),
|
||||
"adaptive_extension_ready": extension_counts.get("planned", 0) == 0,
|
||||
"local_blueprint_ready": local_ready,
|
||||
"public_world_class_ready": public_ready,
|
||||
"world_class_evidence_pending_count": pending_world_class,
|
||||
@@ -299,16 +373,25 @@ def build_coverage(skill_dir: Path, generated_at: str) -> dict[str, Any]:
|
||||
"skill_dir": rel_path(skill_dir, ROOT),
|
||||
"summary": summary,
|
||||
"status_counts": counts,
|
||||
"extension_status_counts": extension_counts,
|
||||
"modules": modules,
|
||||
"recommended_prs": pr_items,
|
||||
"reference_extension_tracks": extension_tracks,
|
||||
"next_highest_leverage": [
|
||||
"Close the four world-class evidence ledger entries with accepted human or external evidence.",
|
||||
"Clarify whether Skill Overview v2 is the canonical interpretation report or split a dedicated skill-interpretation renderer.",
|
||||
"Start adaptive self-iteration as explicit-source, proposal-only, approval-gated work; do not scan private logs by default.",
|
||||
"Keep the blueprint coverage report in CI so 2.0 plan drift is visible.",
|
||||
],
|
||||
"source_blueprint": {
|
||||
"title": "Skill Overview / Skill OS 2.0 upgrade plan",
|
||||
"core_module_count": 8,
|
||||
"recommended_pr_count": 12,
|
||||
"reference_extension_count": len(extension_tracks),
|
||||
"reference_extensions": [
|
||||
"Skill interpretation report",
|
||||
"Adaptive self-iteration with local preference memory and approval gates",
|
||||
],
|
||||
},
|
||||
"artifacts": {
|
||||
"json": "reports/skill_os2_coverage.json",
|
||||
@@ -351,6 +434,10 @@ def render_markdown(report: dict[str, Any]) -> str:
|
||||
f"- pass: `{summary['pass_count']}` / `{summary['item_count']}`",
|
||||
f"- missing: `{summary['missing_count']}`",
|
||||
f"- warn: `{summary['warn_count']}`",
|
||||
f"- reference extensions: `{summary['extension_track_count']}`",
|
||||
f"- extension partial: `{summary['extension_partial_count']}`",
|
||||
f"- extension planned: `{summary['extension_planned_count']}`",
|
||||
f"- adaptive extension ready: `{str(summary['adaptive_extension_ready']).lower()}`",
|
||||
f"- world-class evidence pending: `{summary['world_class_evidence_pending_count']}`",
|
||||
"",
|
||||
"This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, commands, and tests. It does not count pending human review, provider runs, metadata fallbacks, or planned work as public world-class evidence.",
|
||||
@@ -363,12 +450,37 @@ def render_markdown(report: dict[str, Any]) -> str:
|
||||
"",
|
||||
*render_table(report["recommended_prs"]),
|
||||
"",
|
||||
"## Reference Extension Tracks",
|
||||
"",
|
||||
"| Track | Status | Current | Target | Next action |",
|
||||
"| --- | --- | --- | --- | --- |",
|
||||
]
|
||||
for item in report["reference_extension_tracks"]:
|
||||
lines.append(
|
||||
"| "
|
||||
+ " | ".join(
|
||||
[
|
||||
item["label"].replace("|", "\\|"),
|
||||
f"`{item['status']}`",
|
||||
item["current"].replace("|", "\\|"),
|
||||
item["target"].replace("|", "\\|"),
|
||||
item["next_action"].replace("|", "\\|"),
|
||||
]
|
||||
)
|
||||
+ " |"
|
||||
)
|
||||
lines.extend(
|
||||
[
|
||||
"",
|
||||
"These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution.",
|
||||
"",
|
||||
"## Next Highest-Leverage Moves",
|
||||
"",
|
||||
]
|
||||
]
|
||||
)
|
||||
lines.extend(f"- {item}" for item in report["next_highest_leverage"])
|
||||
lines.extend(["", "## Evidence Detail", ""])
|
||||
for item in report["modules"] + report["recommended_prs"]:
|
||||
for item in report["modules"] + report["recommended_prs"] + report["reference_extension_tracks"]:
|
||||
existing = [entry["path"] for entry in item["evidence"] if entry["exists"]]
|
||||
missing = [entry["path"] for entry in item["evidence"] if not entry["exists"]]
|
||||
lines.append(f"### {item['label']}")
|
||||
|
||||
@@ -147,6 +147,8 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
|
||||
output_review = data["output_review_adjudication"].get("summary", {})
|
||||
benchmark = data["benchmark_reproducibility"].get("summary", {})
|
||||
blueprint = data["skill_os2_coverage"].get("summary", {})
|
||||
extension_partial = int(blueprint.get("extension_partial_count", 0) or 0)
|
||||
extension_planned = int(blueprint.get("extension_planned_count", 0) or 0)
|
||||
compiled = data["compiled_targets"].get("summary", {})
|
||||
conformance = data["conformance"].get("summary", {})
|
||||
runtime_permissions = data["runtime_permissions"].get("summary", {})
|
||||
@@ -211,7 +213,10 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
|
||||
{
|
||||
"label": "Blueprint",
|
||||
"value": f"{blueprint.get('pass_count', 0)}/{blueprint.get('item_count', 0)}",
|
||||
"detail": f"2.0 coverage; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}",
|
||||
"detail": (
|
||||
f"2.0 coverage; extensions partial {extension_partial}, "
|
||||
f"planned {extension_planned}; evidence pending {blueprint.get('world_class_evidence_pending_count', 0)}"
|
||||
),
|
||||
},
|
||||
{
|
||||
"label": "Runtime",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"workspace_root": ".",
|
||||
"generated_at": "2026-06-15",
|
||||
"generated_at": "2026-06-13",
|
||||
"skills": [
|
||||
{
|
||||
"name": "yao-meta-skill",
|
||||
@@ -185,8 +185,8 @@
|
||||
"report": "reports/adoption_drift_report.json",
|
||||
"risk_band": "low",
|
||||
"event_count": 1,
|
||||
"adoption_sample_count": 0,
|
||||
"adoption_rate": 0,
|
||||
"adoption_sample_count": 1,
|
||||
"adoption_rate": 100.0,
|
||||
"candidate_count": 0
|
||||
}
|
||||
},
|
||||
|
||||
@@ -24,7 +24,7 @@
|
||||
"name": "incident-command-governor",
|
||||
"path": "examples/governed-incident-command/generated-skill",
|
||||
"reason": "review overdue by cadence monthly",
|
||||
"age_days": 76,
|
||||
"age_days": 74,
|
||||
"allowed_days": 31,
|
||||
"actionable": false,
|
||||
"scope": "example"
|
||||
|
||||
@@ -537,6 +537,14 @@ def main() -> None:
|
||||
if full_payload["data"]["skill_os2_coverage"]:
|
||||
assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"]
|
||||
assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"]
|
||||
assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_track_count"] == 2, full_payload["data"]["skill_os2_coverage"]
|
||||
assert full_payload["data"]["skill_os2_coverage"]["summary"]["extension_planned_count"] == 1, full_payload["data"]["skill_os2_coverage"]
|
||||
extension_tracks = {
|
||||
item["key"]: item
|
||||
for item in full_payload["data"]["skill_os2_coverage"]["reference_extension_tracks"]
|
||||
}
|
||||
assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks
|
||||
assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks
|
||||
world_class_entries = full_payload["data"]["world_class_evidence_ledger"]["entries"]
|
||||
assert len(world_class_entries) == 4, world_class_entries
|
||||
assert {item["key"] for item in world_class_entries} == {
|
||||
@@ -644,6 +652,9 @@ def main() -> None:
|
||||
assert "model_executed_count: 0 / >0" in html, html
|
||||
assert "Token usage observed" in html, html
|
||||
assert "蓝图覆盖" in html, html
|
||||
assert "Extension Track Count" in html, html
|
||||
assert "Adaptive Extension Ready" in html, html
|
||||
assert "extensions partial 1, planned 1" in html, html
|
||||
assert "本地蓝图" in html, html
|
||||
assert "public world-class 仍以 world-class evidence ledger" in html, html
|
||||
assert "公开声明" in html, html
|
||||
|
||||
@@ -44,6 +44,10 @@ def main() -> None:
|
||||
assert summary["pass_count"] == 20, summary
|
||||
assert summary["warn_count"] == 0, summary
|
||||
assert summary["missing_count"] == 0, summary
|
||||
assert summary["extension_track_count"] == 2, summary
|
||||
assert summary["extension_partial_count"] == 1, summary
|
||||
assert summary["extension_planned_count"] == 1, summary
|
||||
assert summary["adaptive_extension_ready"] is False, summary
|
||||
assert summary["local_blueprint_ready"] is True, summary
|
||||
assert summary["public_world_class_ready"] is False, summary
|
||||
assert summary["world_class_evidence_pending_count"] == 4, summary
|
||||
@@ -81,13 +85,30 @@ def main() -> None:
|
||||
assert any(entry["path"] == "reports/benchmark_reproducibility.json" and entry["exists"] for entry in prs["benchmark-methodology"]["evidence"])
|
||||
assert payload["source_blueprint"]["core_module_count"] == 8, payload
|
||||
assert payload["source_blueprint"]["recommended_pr_count"] == 12, payload
|
||||
assert payload["source_blueprint"]["reference_extension_count"] == 2, payload
|
||||
extension_tracks = {item["key"]: item for item in payload["reference_extension_tracks"]}
|
||||
assert extension_tracks["skill-interpretation-report"]["status"] == "partial", extension_tracks
|
||||
assert extension_tracks["adaptive-self-iteration"]["status"] == "planned", extension_tracks
|
||||
assert any(
|
||||
entry["path"] == "reports/skill-overview.html" and entry["exists"]
|
||||
for entry in extension_tracks["skill-interpretation-report"]["evidence"]
|
||||
), extension_tracks["skill-interpretation-report"]
|
||||
assert any(
|
||||
entry["path"] == "scripts/summarize_user_signals.py" and not entry["exists"]
|
||||
for entry in extension_tracks["adaptive-self-iteration"]["evidence"]
|
||||
), extension_tracks["adaptive-self-iteration"]
|
||||
assert "Close the four world-class evidence ledger entries" in payload["next_highest_leverage"][0], payload
|
||||
assert "adaptive self-iteration" in " ".join(payload["next_highest_leverage"]), payload
|
||||
markdown = output_md.read_text(encoding="utf-8")
|
||||
assert "Skill OS 2.0 Blueprint Coverage" in markdown, markdown
|
||||
assert "local blueprint ready: `true`" in markdown, markdown
|
||||
assert "public world-class ready: `false`" in markdown, markdown
|
||||
assert "## Core Modules" in markdown, markdown
|
||||
assert "## Recommended PR Coverage" in markdown, markdown
|
||||
assert "## Reference Extension Tracks" in markdown, markdown
|
||||
assert "Skill Interpretation Report" in markdown, markdown
|
||||
assert "Adaptive Self-Iteration" in markdown, markdown
|
||||
assert "user-supplied 2.0 reference plan" in markdown, markdown
|
||||
assert "`agent-skills-conformance`" not in markdown, markdown
|
||||
assert "Agent Skills Conformance" in markdown, markdown
|
||||
print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
|
||||
|
||||
Reference in New Issue
Block a user