diff --git a/registry/index.json b/registry/index.json index 8fcc5cce..afcf1ca5 100644 --- a/registry/index.json +++ b/registry/index.json @@ -1,6 +1,6 @@ { "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "package_count": 1, "packages": [ { @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index bcd03d4d..08fe1de7 100644 --- a/registry/packages/yao-meta-skill.json +++ b/registry/packages/yao-meta-skill.json @@ -16,8 +16,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -48,10 +48,10 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" } diff --git a/reports/adaptation_proposals.json b/reports/adaptation_proposals.json index a8b6c7f9..20bb712e 100644 --- a/reports/adaptation_proposals.json +++ b/reports/adaptation_proposals.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-15T20:47:47Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, diff --git a/reports/adaptation_proposals.md b/reports/adaptation_proposals.md index bd03a988..5f2a60e3 100644 --- a/reports/adaptation_proposals.md +++ b/reports/adaptation_proposals.md @@ -1,6 +1,6 @@ # Adaptation Proposals -- Generated at: `2026-06-16` +- Generated at: `2026-06-15T20:47:47Z` - Pattern report: `reports/user_patterns.json` - Proposal only: `true` - Writes repository files: `false` diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index a1c933cc..73c2722c 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T20:34:53Z", + "generated_at": "2026-06-15T20:47:47Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 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": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 1, - "accepted": 1, + "adoption_events": 0, + "accepted": 0, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 100.0 + "adoption_rate": 0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "skill_activation", + "event": "review_event", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "explicit", - "outcome": "accepted", + "activation_type": "manual", + "outcome": "reviewed", "failure_type": "none", - "timestamp": "2026-06-13T10:00:00Z" + "timestamp": "2026-06-13T12:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", + "events_jsonl": "reports/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 206372c9..91b31983 100644 --- a/reports/adoption_drift_report.md +++ b/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: `1` -- Activation events: `1` -- Adoption rate: `100.0` +- Adoption samples: `0` +- Activation events: `0` +- Adoption rate: `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 | 1 | 1 | 0 | 0 | 0 | 100.0 | +| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` +- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index a54a6733..1d179a08 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,13 +1,13 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "python_file_count": 181, - "script_file_count": 115, - "test_file_count": 66, - "internal_module_count": 34, + "python_file_count": 183, + "script_file_count": 116, + "test_file_count": 67, + "internal_module_count": 35, "cli_script_count": 83, "command_handler_count": 66, "entrypoint_command_handler_count": 18, diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index 6a552a1a..f0084e06 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,14 +1,14 @@ # Architecture Maintainability -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary - decision: `pass` -- python files: `181` -- scripts: `115` -- tests: `66` -- internal modules: `34` +- python files: `183` +- scripts: `116` +- tests: `67` +- internal modules: `35` - CLI scripts: `83` - Yao CLI command handlers: `66` - entrypoint command handlers: `18` diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index a4099e20..69f37eaf 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,23 +3,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 69, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adaptation_proposals.json", + " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json" + ], "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": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -34,29 +47,30 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, "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)", - "world-class source checks are not all accepted (7/13 pass, 6 blocked)" + "world-class source checks are not all accepted (6/13 pass, 7 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "ready": false, + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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": 25, "missing_count": 0, "missing_paths": [], - "sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4" + "sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -137,8 +151,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "f9487c444b2f9dfba3ce0dd9d22a828c23d9a52d772a9017265ca898c9ef2b75" + "bytes": 7967, + "sha256": "c1f94258e640e449eca383be009ff54d883f44bace9738d7717392043b1d3e71" }, { "label": "blind_review", @@ -172,64 +186,64 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 113207, - "sha256": "ba3b69b8eb33e907fb14a4e86c70bc6dd05d666baa6b8dbce787a03a156663a7" + "bytes": 113805, + "sha256": "47c789ac5ff9404eaeb16fa762a805ea8d12c923dd54c74f97d1f3ccb312a556" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 23905, - "sha256": "01aa970d0d213f0561787dbae628cc92df9085e1c5fb57f62ecae9cfabceae31" + "bytes": 24156, + "sha256": "9392cf6f3c9042044ddd5e2467e4e81f7d9e31587265d906359d4ca80c9e0958" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "979fb0ac2207d6cf8cb41ec68fd13da8007f0033cf29b07404cfae1d1c20b9d8" + "sha256": "462d39d38d11e4f885ba965a320a61dbf0d4ad9b8bd6fe909ee0c039b3058f08" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "e46eaa920aca5a6394897610f743372bcc3e81fc17f1e3cd9eb552ddb6ed4945" + "sha256": "bd6b8467def56d3667aa931c5ace75227dc9f4345e0ab02632d1d99e5aeac91a" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "4d071571c537ad2f43d3f1c8ad3a0928417ec9d9137a704f2baec95e5a2307a2" + "bytes": 8604, + "sha256": "1ad04c50c23ff7c76115b7218d22c4c86ea10bf2bcefb34d4b2d6d10122f350b" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "f881e979b36e4d98cf7b737589e39d308568e033ecc8d5125a964c64b70683ec" + "sha256": "e7d9819e12a79f97a0e708f6401db7ede878deff3a9b2aa3fe2f5aba09fdb15e" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 19940, - "sha256": "b408af112c784fdc3e96ea9ecf374990b9f58a0ebfa4df18394ccd9e93dc5545" + "sha256": "76a3f8e2b12b9ace575f3465bcee7697ddffb3440eed7ca3c3bb0becc61e1ab7" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 21277, - "sha256": "63d7aaedf72503c21577928da46783e0ec55b0e92af326cb92ab1e01289db9f5" + "bytes": 21280, + "sha256": "1cb74eaa978b8a4aee3a95c4459bffb4092f2de8476fd18acce4b943687481b6" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 18865, - "sha256": "2fbecc603d8dc6382fde6c61869aaf4b56fc9d1be5afcd07b345c419dce6d55a" + "sha256": "99a0ba234d59c0329d4645064bd67508c3057cbcc684016437bd0c7f4d9c3b2a" }, { "label": "world_class_evidence_preflight", @@ -242,36 +256,36 @@ "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 13550, - "sha256": "ab20b288f47f2a739ec7862fa8a04985584a729d588a32dca3d71ba64d8de2fc" + "bytes": 13553, + "sha256": "b8317119e9cd19044bac24f9ff5f5ea7def5f7c782b0bb93b9ba4aa554d6fee6" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 23957, - "sha256": "b4640688026ef9199e96f80bd2d9971aaca3ec6d092d8ecd052a5debc0aa94c7" + "bytes": 24021, + "sha256": "f5ca32d5ea8bae74fccd5a574d6bbd3cad46d0950b73d522e66b0a439a433860" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 15025, - "sha256": "3a916ac568377d8df7d612426f7358283eddfa2ab5fedb7ed12db0097a8b3c48" + "bytes": 15080, + "sha256": "260d5e03c52edefd8640c2bb2a0d8ee2c4f6d4e964f925128d4ffdd5563db4ec" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 20969, - "sha256": "886b915da0f27fb46f4d8cebb6211ab5066a9fd44e1ec2e3206487d9a8abfff2" + "bytes": 21030, + "sha256": "04cc091b113f018072d07a1d71ad142773c415a49e633493689903e7b399b5e6" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18218, - "sha256": "926bf86d54c2c3d09078e9cff5821e170c9fc398723d9c99bd89cdcf60e29691" + "sha256": "7359ad2ef09dc0863014aab541a92a1f3e55f18f0c0446816c1c7333cba256e9" } ], "missing_artifacts": [], diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 2809e362..105bbdc1 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,29 +1,29 @@ # Benchmark Reproducibility Generated at: `2026-06-16` -Commit: `3ea32f51a55aec572e423c7c0d3f66edf8f64bd0` -Working tree dirty at generation: `false` -Evidence bundle SHA256: `3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4` +Commit: `3677dd4664b0777391fb82ab9987a7b6ea975af5` +Working tree dirty at generation: `true` +Evidence bundle SHA256: `8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c` ## Summary - reproducibility ready: `true` -- release lock ready: `true` +- release lock ready: `false` - methodology complete: `true` - required artifacts: `25` - missing artifacts: `0` -- source contract sha256: `b6abceeea0f2` -- archive sha256: `7e55b9259f9a` +- source contract sha256: `7de584946cac` +- archive sha256: `1d4626e5f8a2` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `23` - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- world-class source checks: `7` pass / `13` total; `6` blocked +- 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: `69` 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. @@ -35,22 +35,23 @@ 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) | -| world-class source checks are not all accepted (7/13 pass, 6 blocked) | +| world-class source checks are not all accepted (6/13 pass, 7 blocked) | ## 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: `25` / `25` -- sha256: `3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4` +- sha256: `8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c` ## Methodology Sections @@ -72,26 +73,26 @@ 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 | `f9487c444b2f` | +| output_execution | `reports/output_execution_runs.json` | present | `c1f94258e640` | | 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 | `97f9ba949c23` | -| trust_report | `reports/security_trust_report.json` | present | `ba3b69b8eb33` | -| python_compatibility | `reports/python_compatibility.json` | present | `01aa970d0d21` | -| registry_audit | `reports/registry_audit.json` | present | `979fb0ac2207` | -| package_verification | `reports/package_verification.json` | present | `e46eaa920aca` | -| install_simulation | `reports/install_simulation.json` | present | `4d071571c537` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `f881e979b36e` | -| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `b408af112c78` | -| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `63d7aaedf725` | -| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `2fbecc603d8d` | +| trust_report | `reports/security_trust_report.json` | present | `47c789ac5ff9` | +| python_compatibility | `reports/python_compatibility.json` | present | `9392cf6f3c90` | +| registry_audit | `reports/registry_audit.json` | present | `462d39d38d11` | +| package_verification | `reports/package_verification.json` | present | `bd6b8467def5` | +| install_simulation | `reports/install_simulation.json` | present | `1ad04c50c23f` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e7d9819e12a7` | +| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `76a3f8e2b12b` | +| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `1cb74eaa978b` | +| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `99a0ba234d59` | | world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `412186c14ddd` | -| world_class_submission_review | `reports/world_class_submission_review.json` | present | `ab20b288f47f` | -| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `b4640688026e` | -| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `3a916ac56837` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `886b915da0f2` | -| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `926bf86d54c2` | +| world_class_submission_review | `reports/world_class_submission_review.json` | present | `b8317119e9cd` | +| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `f5ca32d5ea8b` | +| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `260d5e03c52e` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `04cc091b113f` | +| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `7359ad2ef09d` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 6287c4d6..8032bb49 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "target_count": 5, diff --git a/reports/context_budget.json b/reports/context_budget.json index e932d8b4..f97c8e3c 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -5,22 +5,22 @@ "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, - "skill_body_tokens": 767, - "other_text_tokens": 1001355, - "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1002122, - "deferred_resource_tokens": 461032, + "skill_body_tokens": 797, + "other_text_tokens": 1007838, + "estimated_initial_load_tokens": 990, + "estimated_total_text_tokens": 1008635, + "deferred_resource_tokens": 464021, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115 + "estimated_tokens": 414241, + "file_count": 116 }, { "path": "references", - "estimated_tokens": 27376, - "file_count": 34 + "estimated_tokens": 27945, + "file_count": 35 }, { "path": "evals", @@ -31,8 +31,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115 + "estimated_tokens": 414241, + "file_count": 116 } ], "deferred_resource_governance": { @@ -54,16 +54,16 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115, + "estimated_tokens": 414241, + "file_count": 116, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 570, + "relevant_file_count": 609, "unused_resource_dirs": [], "quality_signal_points": 130, - "quality_density": 135.4 + "quality_density": 131.3 } } diff --git a/reports/context_budget.md b/reports/context_budget.md index d58edfaf..aefa46e8 100644 --- a/reports/context_budget.md +++ b/reports/context_budget.md @@ -2,7 +2,7 @@ | Target | Path | Tier | Limit | Initial | SKILL | Deferred | Resource Governance | Large Deferred Dirs | Quality Density | Unused Dirs | Status | | --- | --- | --- | ---: | ---: | ---: | ---: | --- | --- | ---: | --- | --- | -| root | `.` | `production` | 1000 | 960 | 767 | 461032 | `governed` | scripts:411821 | 135.4 | - | ok | +| root | `.` | `production` | 1000 | 990 | 797 | 464021 | `governed` | scripts:414241 | 131.3 | - | ok | | complex-release-orchestrator | `examples/complex-release-orchestrator/generated-skill` | `production` | 1000 | 790 | 718 | 1657 | `not-required` | - | 164.6 | - | ok | | governed-incident-command | `examples/governed-incident-command/generated-skill` | `production` | 1000 | 760 | 658 | 1030 | `not-required` | - | 171.1 | - | ok | diff --git a/reports/context_budget_summary.json b/reports/context_budget_summary.json index 4d0a791e..81032723 100644 --- a/reports/context_budget_summary.json +++ b/reports/context_budget_summary.json @@ -6,14 +6,14 @@ "path": ".", "budget_tier": "production", "budget_limit": 1000, - "initial_tokens": 960, - "skill_body_tokens": 767, - "deferred_resource_tokens": 461032, + "initial_tokens": 990, + "skill_body_tokens": 797, + "deferred_resource_tokens": 464021, "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115 + "estimated_tokens": 414241, + "file_count": 116 } ], "deferred_resource_governance": { @@ -35,14 +35,14 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115, + "estimated_tokens": 414241, + "file_count": 116, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "quality_density": 135.4, + "quality_density": 131.3, "unused_resource_dirs": [], "ok": true, "warnings": [] diff --git a/reports/evidence_consistency.json b/reports/evidence_consistency.json index 50f3e3d0..b9c2fca0 100644 --- a/reports/evidence_consistency.json +++ b/reports/evidence_consistency.json @@ -184,12 +184,12 @@ "status": "pass", "expected": { "status": "pass", - "detail": "initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4", + "detail": "initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "actual": { "status": "pass", - "detail": "initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4", + "detail": "initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json" }, "paths": [ @@ -202,8 +202,8 @@ "key": "benchmark-release-lock-self-consistency", "label": "Benchmark release lock matches git dirty state", "status": "pass", - "expected": true, - "actual": true, + "expected": false, + "actual": false, "paths": [ "reports/benchmark_reproducibility.json" ], @@ -243,8 +243,8 @@ "key": "overview-benchmark-commit", "label": "overview embeds the benchmark commit", "status": "pass", - "expected": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", - "actual": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "expected": "3677dd4664b0777391fb82ab9987a7b6ea975af5", + "actual": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-overview.json" @@ -256,30 +256,30 @@ "label": "overview embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -293,13 +293,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -307,13 +307,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -336,8 +336,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -348,8 +348,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -369,7 +369,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "actual": { "ready": false, @@ -377,7 +377,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -389,8 +389,8 @@ "key": "interpretation-benchmark-commit", "label": "interpretation embeds the benchmark commit", "status": "pass", - "expected": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", - "actual": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "expected": "3677dd4664b0777391fb82ab9987a7b6ea975af5", + "actual": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "paths": [ "reports/benchmark_reproducibility.json", "reports/skill-interpretation.json" @@ -402,30 +402,30 @@ "label": "interpretation embeds benchmark summary fields", "status": "pass", "expected": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "actual": { - "release_lock_ready": true, + "release_lock_ready": false, "required_artifact_count": 25, "missing_artifact_count": 0, - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false, - "public_claim_blocker_count": 4 + "public_claim_blocker_count": 5 }, "paths": [ "reports/benchmark_reproducibility.json", @@ -439,13 +439,13 @@ "status": "pass", "expected": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -453,13 +453,13 @@ }, "actual": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, + "adoption_rate": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "source_types": { "manual": 1 @@ -482,8 +482,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -494,8 +494,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "decision": "evidence-pending" }, @@ -515,7 +515,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "actual": { "ready": false, @@ -523,7 +523,7 @@ "pending_count": 4, "accepted_count": 0, "source_check_count": 13, - "source_pass_count": 7 + "source_pass_count": 6 }, "paths": [ "reports/world_class_evidence_ledger.json", @@ -572,7 +572,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -593,7 +593,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -636,7 +636,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -657,7 +657,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -889,7 +889,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -937,7 +937,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -1012,7 +1012,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -1171,7 +1171,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -1322,7 +1322,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1381,7 +1381,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1395,7 +1396,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1454,7 +1455,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1499,13 +1501,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -1517,10 +1519,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -1541,11 +1543,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -1553,7 +1555,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -1587,13 +1589,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -1605,10 +1607,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -1629,11 +1631,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -1641,7 +1643,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -1804,15 +1806,15 @@ "expected": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false }, "actual": { "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "world_class_source_pass_count": 6, + "world_class_source_blocked_count": 7, "public_claim_ready": false }, "paths": [ @@ -1828,8 +1830,8 @@ "expected": { "pending_count": 4, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1837,8 +1839,8 @@ "actual": { "pending_count": 4, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "preflight_counts_as_evidence": false, "credential_value_exposed": false @@ -1972,8 +1974,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2121,8 +2123,8 @@ "human_pending_count": 1, "external_pending_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "plan_keys": [ "human-adjudication", "native-client-telemetry", @@ -2277,16 +2279,16 @@ "score `91`", "`16` gates", "`3` warnings", - "`31` declared internal modules", - "`84 / 84` CLI help smoke checks passing across `115` scripts", - "`630` zip entries", - "archive with `630` entries", + "`32` declared internal modules", + "`84 / 84` CLI help smoke checks passing across `116` scripts", + "`634` zip entries", + "archive with `634` entries", "`12` installer permission checks enforced", "`0` permission failures", "`25` required artifacts", "`23` reproduction commands", - "initial load `960/1000`", - "target count is `78`" + "initial load `990/1000`", + "target count is `79`" ], "actual": "all present", "paths": [ diff --git a/reports/install_simulation.json b/reports/install_simulation.json index 6c1bff83..6dbc3d4e 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,14 +1,14 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", - "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", + "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", "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -26,7 +26,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" + "detail": "Package archive exists: dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -272,9 +272,9 @@ "failures": [], "warnings": [], "artifacts": { - "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" + "archive": "dist/yao-meta-skill.zip", + "package_manifest": "dist/manifest.json", + "json": "reports/install_simulation.json", + "markdown": "reports/install_simulation.md" } } diff --git a/reports/install_simulation.md b/reports/install_simulation.md index b0d16dae..6750e007 100644 --- a/reports/install_simulation.md +++ b/reports/install_simulation.md @@ -1,7 +1,7 @@ # Install Simulation - OK: `True` -- Package directory: `tests/tmp_review_studio/dist` +- Package directory: `dist` - Archive extracted: `True` - Entrypoint loaded: `True` - Manifest loaded: `True` @@ -16,7 +16,7 @@ | Check | Status | Detail | | --- | --- | --- | -| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip | +| `archive-present` | `pass` | Package archive exists: 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 | diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 98cf7158..2aa5cd77 100644 --- a/reports/output_execution_runs.json +++ b/reports/output_execution_runs.json @@ -34,7 +34,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.97, + "duration_ms": 26.41, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.0, + "duration_ms": 26.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.96, + "duration_ms": 26.02, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.66, + "duration_ms": 26.01, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.56, + "duration_ms": 25.98, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.61, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.27, + "duration_ms": 26.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.29, + "duration_ms": 26.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.96, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.68, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 551a753f..eaa78bc0 100644 --- a/reports/output_execution_runs.md +++ b/reports/output_execution_runs.md @@ -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 | 45.97 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 38.0 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 35.96 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 35.66 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 32.56 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 31.61 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 32.27 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 32.29 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 34.96 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 31.68 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 26.41 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 26.38 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 26.02 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.01 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 25.98 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.24 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.23 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.52 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 26.24 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.24 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index d8d2a1d8..253f9202 100644 --- a/reports/package_verification.json +++ b/reports/package_verification.json @@ -8,8 +8,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index f7c5884f..0d3d405c 100644 --- a/reports/package_verification.md +++ b/reports/package_verification.md @@ -4,7 +4,7 @@ - Package directory: `dist` - Targets: `4 / 4` adapters present - Archive present: `True` -- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed` +- Archive SHA256: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35` - Failures: `0` - Warnings: `0` diff --git a/reports/prompt-quality-profile.json b/reports/prompt-quality-profile.json index 8af0544b..6e095e43 100644 --- a/reports/prompt-quality-profile.json +++ b/reports/prompt-quality-profile.json @@ -1,6 +1,6 @@ { "skill_name": "yao-meta-skill", - "relevance": "prompt-heavy", + "relevance": "prompt-aware", "primary_task_family": { "key": "execution_operation", "label": "Execution operation", @@ -46,15 +46,15 @@ "format_guidance": "Return options with rationale, selection criteria, and refinement paths." }, { - "key": "prompt_engineering", - "label": "Prompt engineering", + "key": "analytical_reasoning", + "label": "Analytical reasoning", "score": 1, "matched_keywords": [ - "prompt" + "decision" ], - "role_guidance": "Use a prompt engineer role only when role design materially improves execution.", - "task_guidance": "Map Role, Task, and Format into skill behavior rather than copying a large prompt template.", - "format_guidance": "Return a compact prompt contract plus tests, quality matrix, and usage notes." + "role_guidance": "Use an analyst role that separates evidence, inference, uncertainty, and recommendation.", + "task_guidance": "State assumptions, compare alternatives, and make the decision path inspectable.", + "format_guidance": "Return findings, evidence, tradeoffs, recommendation, and residual risks." } ], "complexity": { diff --git a/reports/prompt-quality-profile.md b/reports/prompt-quality-profile.md index a0611304..a501dbc5 100644 --- a/reports/prompt-quality-profile.md +++ b/reports/prompt-quality-profile.md @@ -1,7 +1,7 @@ # Prompt Quality Profile Skill: `yao-meta-skill` -Relevance: `prompt-heavy` +Relevance: `prompt-aware` Overall quality score: `89.0/100` ## Primary Task Family @@ -74,12 +74,12 @@ Overall quality score: `89.0/100` - Task: Generate variants, explain selection logic, and preserve the user's distinctive constraints. - Format: Return options with rationale, selection criteria, and refinement paths. -### Prompt engineering +### Analytical reasoning - Score: `1` -- Keywords: prompt -- Role: Use a prompt engineer role only when role design materially improves execution. -- Task: Map Role, Task, and Format into skill behavior rather than copying a large prompt template. -- Format: Return a compact prompt contract plus tests, quality matrix, and usage notes. +- Keywords: decision +- Role: Use an analyst role that separates evidence, inference, uncertainty, and recommendation. +- Task: State assumptions, compare alternatives, and make the decision path inspectable. +- Format: Return findings, evidence, tradeoffs, recommendation, and residual risks. ## Self-Repair Checks diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index e326221c..d7b89493 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,11 +1,11 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "root": ".", "summary": { "target_python": "3.11", - "file_count": 184, + "file_count": 186, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -610,6 +610,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/skillops_opportunity.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/summarize_user_signals.py", "ok": true, @@ -1036,6 +1042,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_skillops_opportunity.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_system_model.py", "ok": true, diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index a0719a7d..fef92c23 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,12 +1,12 @@ # Python Compatibility -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary - decision: `pass` - target python: `3.11` -- files scanned: `184` +- files scanned: `186` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index bda0cabc..1a4767c9 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -53,16 +53,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "package_count": 1, "packages": [ { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 49dbb1d9..c4c4aa34 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083` -- Archive SHA256: `7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed` +- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7` +- Archive SHA256: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index 71610a99..c587bfe0 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -676,22 +676,22 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

4 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

115 scripts scanned; secrets found

Py Compat0

184 files scanned for Python 3.11

Arch Debt0

899 largest lines; 11 watchlist; 66 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

178 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

630 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

+
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review Kit0/5

pending 5; answer key hidden

Review A/B0/5

adjudication decisions; pending 5

Public Claimblocked

5 blockers; local reproducible true

Blueprint21/21

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

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native; 4 installer-enforced

Trust0

116 scripts scanned; secrets found

Py Compat0

186 files scanned for Python 3.11

Arch Debt0

899 largest lines; 11 watchlist; 66 CLI handlers; 18 in entrypoint

Atlas5

12 scanned skills; route collisions

Driftlow

1 metadata events; 0 missed triggers

Waivers0

0 gates covered; human risk decisions

Intake4/4

0 valid submissions; 0 invalid

Claim Guard0

178 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

634 zip entries; package verification

Installpass

4 adapters; 12 permissions enforced; 0 permission failures

Upgrademinor

declared minor; 0 breaking changes

审查闸门

-
通过

意图画布

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

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 115 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 184 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

181 Python files; 0 hotspots; 11 watchlist files; 0 blockers; largest 899 lines; 66 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

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

意图画布

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

reports/intent-confidence.json 证据
通过

触发实验

13 trigger cases; 0 misroutes; 0 ambiguous

reports/route_scorecard.json 证据
关注

输出实验

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

reports/output_quality_scorecard.json 证据
通过

上下文

initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3

reports/context_budget.json 证据
通过

运行矩阵

5 / 5 targets pass

reports/conformance_matrix.json 证据
通过

信任报告

0 secrets; 116 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 186 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

183 Python files; 0 hotspots; 11 watchlist files; 0 blockers; largest 899 lines; 66 CLI handlers; 18 in entrypoint

reports/architecture_maintainability.json 证据
通过

权限批准

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

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

权限探针

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

reports/runtime_permission_probes.json 证据
通过

组合治理

12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues

reports/skill_atlas.json 证据
通过

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

reports/adoption_drift_report.json 证据
关注

人工批准

0 active waivers; 1 warning gates still need reviewer decision

reports/review_waivers.json 证据
关注

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

reports/world_class_evidence_ledger.json 证据
通过

注册审计

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

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

发布路线

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

阻断事项

无。

-

关注事项

+

关注事项

修复动作

-
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

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

人工批准

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

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

世界证据

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

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

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 1

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
1 blocked / 2 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
+
关注

输出实验

补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。

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

人工批准

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

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

世界证据

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

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

证据采集

以下条目仍需真实外部或人工证据；提交文件、校验命令和阻断检查必须同时闭环。

pending · external

Provider Holdout

model-executed 0; token-observed 0

提交
evidence/world_class/submissions/provider-holdout.json
模板
evidence/world_class/templates/provider-holdout.intake.json
阻断
2 blocked / 1 pass
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
阻断检查
  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  2. python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  3. Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
pending · human

Human Adjudication

0/5 decisions; pending 5

提交
evidence/world_class/submissions/human-adjudication.json
模板
evidence/world_class/templates/human-adjudication.intake.json
阻断
2 blocked / 2 pass
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
阻断检查
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/yao.py output-review-kit --write-template
  2. Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  3. python3 scripts/adjudicate_output_review.py --write-template
pending · external

Native Permission Enforcement

native-enforced targets 0; installer-enforced targets 4

提交
evidence/world_class/submissions/native-permission-enforcement.json
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
阻断
1 blocked / 2 pass
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
阻断检查
  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  2. Update the generated target adapter only when the guard is actually enforced by that target.
  3. python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
pending · external

Native Client Telemetry

external source events 0; adoption samples 0

提交
evidence/world_class/submissions/native-client-telemetry.json
模板
evidence/world_class/templates/native-client-telemetry.intake.json
阻断
2 blocked / 1 pass
下一步
Install a real client against the native host and import production metadata-only events.
阻断检查
  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
操作命令
  • 准备提交python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • 校验入口python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • 审查提交python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions
  • 刷新台账python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions
首要步骤
  1. python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/
  2. Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.
  3. python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
@@ -743,17 +743,17 @@
-

上下文

initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4

+

上下文

initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3

编译证据

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

-

信任报告

Secret
0
脚本数
115
网络脚本
3
Help 失败
0
包体哈希
b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083
+

信任报告

Secret
0
脚本数
116
网络脚本
3
Help 失败
0
包体哈希
7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7

安全边界

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

-

Python 兼容

目标 Python
3.11
文件数
184
问题数
0
语法错误
0
F-string 3.11
0
+

Python 兼容

目标 Python
3.11
文件数
186
问题数
0
语法错误
0
F-string 3.11
0

解释器边界

CI 和发布审查以 Python 3.11 兼容为底线；本地更高版本允许的新语法不能绕过兼容门禁。

@@ -773,8 +773,8 @@
-

运营回路

1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low

-

漂移信号

事件数
1
采用率
100
漏触发
0
Bad Output Count
0
风险带
low
+

运营回路

1 metadata events; adoption 0; missed 0; bad-output 0; risk low

+

漂移信号

事件数
1
采用率
0
漏触发
0
Bad Output Count
0
风险带
low
@@ -785,13 +785,13 @@

批准台账

Waiver Count
0
Active Count
0
Expired Count
0
Invalid Count
0
覆盖 Gate
0

批准候选

-
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令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
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
无
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .
+
可批准 · needs-reviewer-decision

Output Lab

review pending 5; model-executed 0; output failures 0

Gate
output-lab
证据
reports/output_review_adjudication.md
选项
accepted-risk, false-positive, temporary-exception
边界
Does not count as provider, human, or public world-class completion evidence.

审查条件

  • Reviewer confirms this release does not claim provider-backed or human-adjudicated output superiority.
  • Reviewer names the release scope and expiry date.
  • Reviewer links output_review_adjudication or output_execution evidence.
建议命令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 2027-06-16 --evidence reports/output_review_adjudication.md
不可批准 · cannot-waive

World-Class Evidence

4 pending evidence entries; 1 human pending; 3 external pending

Gate
world-class-evidence
证据
reports/world_class_evidence_ledger.md
选项
无
边界
Non-waivable completion boundary.

审查条件

  • Do not use a waiver to claim public world-class readiness.
  • Either submit accepted ledger evidence or state that this release does not claim world-class completion.
  • Keep claim guard active until ledger summary.ready_to_claim_world_class is true.
建议命令python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions && python3 scripts/yao.py world-class-claim-guard .

世界证据

这里列出每个 world-class 证据项的当前状态、完成定义、证据来源、隐私约束和下一步；计划、metadata fallback、待评审和本地命令不会被当成完成证据。

-
待补证 · external

Provider Holdout

Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.

负责人
operator with provider credentials
当前状态
model-executed 0; token-observed 0
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
观测值
model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass

证据来源

  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.

源证据检查

  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
待补证 · human

Human Adjudication

Record real blind A/B reviewer decisions before claiming human output review completion.

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
观测值
pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • python3 scripts/yao.py output-review-kit --write-template
  • Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  • python3 scripts/adjudicate_output_review.py --write-template
  • Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.
  • python3 scripts/yao.py output-review
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_review_adjudication.json summary.pending_count == 0
  • reports/output_review_adjudication.json summary.judgment_count == summary.pair_count
  • reports/output_review_adjudication.json summary.invalid_decision_count == 0
  • reports/skill_os2_audit.json item human-adjudication status becomes pass

证据来源

  • reports/output_blind_review_pack.md
  • reports/output_review_kit.md
  • reports/output_review_decisions.json
  • reports/output_review_adjudication.json
  • reports/output_review_adjudication.md
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/human-adjudication.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Reviewer decisions should not include raw user data or private customer detail.
  • Keep the answer key separate until after decisions are recorded.

源证据检查

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: 0 / ==0Fix malformed winner/confidence entries.
待补证 · external

Native Permission Enforcement

Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.

负责人
target client or installer integrator
当前状态
native-enforced targets 0; installer-enforced targets 4
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
观测值
native_enforcement_count: 0; metadata_fallback_count: 4; installer_enforcement_pass_count: 4; installer_permission_failure_count: 0; installer_enforcement_ready: True; residual_risk_count: 4; failure_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  • Update the generated target adapter only when the guard is actually enforced by that target.
  • python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
  • python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation
  • python3 scripts/yao.py runtime-permissions . --package-dir dist
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass

证据来源

  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
  • security/permission_policy.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-permission-enforcement.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.

源证据检查

  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: 0 / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
待补证 · external

Native Client Telemetry

Import production metadata-only events from a real external client into the local drift loop.

负责人
Browser/Chrome/IDE/provider client integrator
当前状态
external source events 0; adoption samples 1
下一步
Install a real client against the native host and import production metadata-only events.
观测值
external_source_events: 0; adoption_sample_count: 1; raw_content_allowed: False; risk_band: low; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • 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.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

证据来源

  • reports/adoption_drift_report.json
  • reports/adoption_drift_report.md
  • reports/telemetry_hook_recipes.json
  • scripts/telemetry_native_host.py
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-client-telemetry.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.

源证据检查

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 1 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
+
待补证 · external

Provider Holdout

Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.

负责人
operator with provider credentials
当前状态
model-executed 0; token-observed 0
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.
观测值
model_executed_count: 0; timing_observed_count: 10; token_observed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/provider-holdout.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_execution_runs.json summary.model_executed_count > 0
  • reports/output_execution_runs.json summary.timing_observed_count > 0
  • reports/output_execution_runs.json summary.token_observed_count > 0
  • reports/skill_os2_audit.json item provider-holdout status becomes pass

证据来源

  • reports/output_execution_runs.json
  • reports/output_execution_runs.md
  • reports/skill_os2_audit.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/provider-holdout.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Do not commit provider credentials or environment dumps.
  • The output execution report records output hashes and aggregate run metadata, not raw provider prompts.

源证据检查

  • Provider model runmodel_executed_count: 0 / >0Run provider-backed output-exec with real credentials.
  • Timing observedtiming_observed_count: 10 / >0Provider execution should record timing metadata.
  • Token usage observedtoken_observed_count: 0 / >0Provider execution should return non-estimated token usage.
待补证 · human

Human Adjudication

Record real blind A/B reviewer decisions before claiming human output review completion.

负责人
human reviewer
当前状态
0/5 decisions; pending 5
下一步
Record real A/B choices in the decision template, then regenerate adjudication.
观测值
pair_count: 5; judgment_count: 0; pending_count: 5; invalid_decision_count: 0; answer_revealed_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/human-adjudication.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • python3 scripts/yao.py output-review-kit --write-template
  • Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.
  • python3 scripts/adjudicate_output_review.py --write-template
  • Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.
  • python3 scripts/yao.py output-review
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/output_review_adjudication.json summary.pending_count == 0
  • reports/output_review_adjudication.json summary.judgment_count == summary.pair_count
  • reports/output_review_adjudication.json summary.invalid_decision_count == 0
  • reports/skill_os2_audit.json item human-adjudication status becomes pass

证据来源

  • reports/output_blind_review_pack.md
  • reports/output_review_kit.md
  • reports/output_review_decisions.json
  • reports/output_review_adjudication.json
  • reports/output_review_adjudication.md
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/human-adjudication.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Reviewer decisions should not include raw user data or private customer detail.
  • Keep the answer key separate until after decisions are recorded.

源证据检查

  • Review pairs existpair_count: 5 / >0Generate the blind A/B review pack.
  • No pending decisionspending_count: 5 / ==0Record a reviewer choice for every pair.
  • Judgments completejudgment_count: 0 / ==pair_countEvery pair needs one valid human judgment.
  • No invalid decisionsinvalid_decision_count: 0 / ==0Fix malformed winner/confidence entries.
待补证 · external

Native Permission Enforcement

Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.

负责人
target client or installer integrator
当前状态
native-enforced targets 0; installer-enforced targets 4
下一步
Integrate a real target-client or external installer runtime guard before claiming native permission enforcement.
观测值
native_enforcement_count: 0; metadata_fallback_count: 4; installer_enforcement_pass_count: 4; installer_permission_failure_count: 0; installer_enforcement_ready: True; residual_risk_count: 4; failure_count: 0; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-permission-enforcement.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.
  • Update the generated target adapter only when the guard is actually enforced by that target.
  • python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip
  • python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation
  • python3 scripts/yao.py runtime-permissions . --package-dir dist
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass

证据来源

  • dist/targets/*/adapter.json
  • reports/runtime_permission_probes.json
  • reports/runtime_permission_probes.md
  • reports/install_simulation.json
  • reports/install_simulation.md
  • security/permission_policy.json
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-permission-enforcement.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Do not mark native_enforcement true for metadata-only fallbacks.
  • Keep residual risks visible for targets that still rely on operator enforcement.

源证据检查

  • Native enforcementnative_enforcement_count: 0 / >0Collect real target-client or external runtime guard proof.
  • Probe failuresfailure_count: 0 / ==0Runtime permission probes must stay clean.
  • Installer supportinstaller_enforcement_ready: True / trueInstaller enforcement is supporting evidence, not native proof.
待补证 · external

Native Client Telemetry

Import production metadata-only events from a real external client into the local drift loop.

负责人
Browser/Chrome/IDE/provider client integrator
当前状态
external source events 0; adoption samples 0
下一步
Install a real client against the native host and import production metadata-only events.
观测值
external_source_events: 0; adoption_sample_count: 0; raw_content_allowed: False; risk_band: low; accepted: False
提交态
status: missing; path: evidence/world_class/submissions/native-client-telemetry.json; attested_real_evidence: False; privacy_contract_satisfied: False

执行步骤

  • 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.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • 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.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions

完成定义

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

证据来源

  • reports/adoption_drift_report.json
  • reports/adoption_drift_report.md
  • reports/telemetry_hook_recipes.json
  • scripts/telemetry_native_host.py
  • evidence/world_class/intake.schema.json
  • evidence/world_class/templates/native-client-telemetry.intake.json
  • reports/world_class_evidence_intake.json
  • reports/world_class_evidence_intake.md

隐私约束

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.

源证据检查

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
@@ -806,12 +806,12 @@
-

公开声明

本地复现
是
发布锁
是
可公开声明
否
声明阻断
4
Provider 证据
否
人审完成
否
世界级就绪
否
-

声明阻断

+

公开声明

本地复现
是
发布锁
否
可公开声明
否
声明阻断
5
Provider 证据
否
人审完成
否
世界级就绪
否
+

声明阻断

-

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true

+

世界证据

4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true

证据台账

Ledger Entry Count
4
Accepted Count
0
待审
4
Human Pending Count
1
External Pending Count
3
Overclaim Guard Active
是
Ready To Claim World Class
否
@@ -827,12 +827,12 @@

注册审计

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

-

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed
+

包体元数据

名称
yao-meta-skill
版本
1.1.0
Maturity
governed
Owner
Yao Team
License
MIT
信任级别
local
目标平台
openai, claude, generic, agent-skills-compatible, vscode
兼容通过
6/6
归档哈希
1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35

发布路线

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

-

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
630
失败数
0
警告数
0
归档哈希
7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
634
失败数
0
警告数
0
归档哈希
1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35
diff --git a/reports/review-studio.json b/reports/review-studio.json index 911672fd..c6eece8a 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -43,7 +43,7 @@ "key": "context-budget", "label": "上下文", "status": "pass", - "detail": "initial load 960/1000; deferred 461032/120000; top deferred scripts 411821; resource governance governed; quality density 135.4", + "detail": "initial load 990/1000; deferred 464021/120000; top deferred scripts 414241; resource governance governed; quality density 131.3", "evidence": "reports/context_budget.json", "link": "context_budget.md" }, @@ -59,7 +59,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 115 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 116 scripts; 3 network-capable scripts; 0 help smoke failures", "evidence": "reports/security_trust_report.json", "link": "security_trust_report.md" }, @@ -67,7 +67,7 @@ "key": "python-compat", "label": "Python 兼容", "status": "pass", - "detail": "Python 3.11; 184 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 186 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", "evidence": "reports/python_compatibility.json", "link": "python_compatibility.md" }, @@ -75,7 +75,7 @@ "key": "architecture-maintainability", "label": "架构维护", "status": "pass", - "detail": "181 Python files; 0 hotspots; 11 watchlist files; 0 blockers; largest 899 lines; 66 CLI handlers; 18 in entrypoint", + "detail": "183 Python files; 0 hotspots; 11 watchlist files; 0 blockers; largest 899 lines; 66 CLI handlers; 18 in entrypoint", "evidence": "reports/architecture_maintainability.json", "link": "architecture_maintainability.md" }, @@ -107,7 +107,7 @@ "key": "operations-loop", "label": "运营回路", "status": "pass", - "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low", + "detail": "1 metadata events; adoption 0; missed 0; bad-output 0; risk low", "evidence": "reports/adoption_drift_report.json", "link": "adoption_drift_report.md" }, @@ -123,7 +123,7 @@ "key": "world-class-evidence", "label": "世界证据", "status": "warn", - "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true", "evidence": "reports/world_class_evidence_ledger.json", "link": "world_class_evidence_ledger.md" }, @@ -166,7 +166,7 @@ "key": "world-class-evidence", "label": "世界证据", "status": "warn", - "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 7/13 pass; 6 blocked; overclaim guard true", + "detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true", "evidence": "reports/world_class_evidence_ledger.json", "link": "world_class_evidence_ledger.md" } @@ -579,12 +579,12 @@ "category": "external", "status": "pending", "readiness": "awaiting-submission", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "next_action": "Install a real client against the native host and import production metadata-only events.", "submission_path": "evidence/world_class/submissions/native-client-telemetry.json", "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json", - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "blocked_checks": [ { "label": "External events", @@ -593,6 +593,14 @@ "expected": ">0", "status": "blocked", "next_action": "Import at least one metadata-only event from a real client." + }, + { + "label": "Adoption sample", + "field": "adoption_sample_count", + "actual": 0, + "expected": ">0", + "status": "blocked", + "next_action": "Telemetry must include adoption outcome evidence." } ], "commands": [ @@ -754,7 +762,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -775,7 +783,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -879,7 +887,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -944,7 +952,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -1085,7 +1093,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -1144,7 +1152,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -1179,13 +1188,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -1197,10 +1206,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -1221,11 +1230,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -1233,7 +1242,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -1349,13 +1358,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -1367,7 +1376,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], "strengths": [ @@ -1669,13 +1678,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1690,14 +1699,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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.", @@ -1781,9 +1790,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1801,8 +1810,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "skill_atlas": { "skill_count": 12, @@ -1840,8 +1849,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -1872,12 +1881,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1888,8 +1897,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, @@ -1900,7 +1909,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1967,12 +1976,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -1989,14 +1998,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -2005,7 +2014,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -2227,7 +2236,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -2279,8 +2288,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -2616,7 +2625,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -2653,7 +2662,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2674,8 +2683,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2691,8 +2700,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -4339,7 +4348,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 45.97, + "duration_ms": 26.41, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4367,7 +4376,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 38.0, + "duration_ms": 26.38, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4390,7 +4399,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.96, + "duration_ms": 26.02, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4418,7 +4427,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 35.66, + "duration_ms": 26.01, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4441,7 +4450,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.56, + "duration_ms": 25.98, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4469,7 +4478,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.61, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4492,7 +4501,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.27, + "duration_ms": 26.23, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4519,7 +4528,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.29, + "duration_ms": 26.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4542,7 +4551,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 34.96, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4571,7 +4580,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.68, + "duration_ms": 26.24, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -5292,23 +5301,36 @@ "ok": true, "generated_at": "2026-06-16", "skill_dir": ".", - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "git_status": { "available": true, - "dirty": false, - "changed_file_count": 0, - "sample": [], + "dirty": true, + "changed_file_count": 69, + "sample": [ + " M registry/index.json", + " M registry/packages/yao-meta-skill.json", + " M reports/adaptation_proposals.json", + " M reports/adaptation_proposals.md", + " M reports/adoption_drift_report.json", + " M reports/adoption_drift_report.md", + " M reports/architecture_maintainability.json", + " M reports/architecture_maintainability.md", + " M reports/benchmark_reproducibility.json", + " M reports/benchmark_reproducibility.md", + " M reports/compiled_targets.json", + " M reports/context_budget.json" + ], "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": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -5323,29 +5345,30 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, "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)", - "world-class source checks are not all accepted (7/13 pass, 6 blocked)" + "world-class source checks are not all accepted (6/13 pass, 7 blocked)" ], "policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, accepted world-class evidence, and complete source checks." }, "release_lock": { - "ready": true, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "ready": false, + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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)", @@ -5353,7 +5376,7 @@ "existing_count": 25, "missing_count": 0, "missing_paths": [], - "sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4" + "sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -5426,8 +5449,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7966, - "sha256": "f9487c444b2f9dfba3ce0dd9d22a828c23d9a52d772a9017265ca898c9ef2b75" + "bytes": 7967, + "sha256": "c1f94258e640e449eca383be009ff54d883f44bace9738d7717392043b1d3e71" }, { "label": "blind_review", @@ -5461,64 +5484,64 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 113207, - "sha256": "ba3b69b8eb33e907fb14a4e86c70bc6dd05d666baa6b8dbce787a03a156663a7" + "bytes": 113805, + "sha256": "47c789ac5ff9404eaeb16fa762a805ea8d12c923dd54c74f97d1f3ccb312a556" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 23905, - "sha256": "01aa970d0d213f0561787dbae628cc92df9085e1c5fb57f62ecae9cfabceae31" + "bytes": 24156, + "sha256": "9392cf6f3c9042044ddd5e2467e4e81f7d9e31587265d906359d4ca80c9e0958" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "979fb0ac2207d6cf8cb41ec68fd13da8007f0033cf29b07404cfae1d1c20b9d8" + "sha256": "462d39d38d11e4f885ba965a320a61dbf0d4ad9b8bd6fe909ee0c039b3058f08" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19338, - "sha256": "e46eaa920aca5a6394897610f743372bcc3e81fc17f1e3cd9eb552ddb6ed4945" + "sha256": "bd6b8467def56d3667aa931c5ace75227dc9f4345e0ab02632d1d99e5aeac91a" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8758, - "sha256": "4d071571c537ad2f43d3f1c8ad3a0928417ec9d9137a704f2baec95e5a2307a2" + "bytes": 8604, + "sha256": "1ad04c50c23ff7c76115b7218d22c4c86ea10bf2bcefb34d4b2d6d10122f350b" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 14310, - "sha256": "f881e979b36e4d98cf7b737589e39d308568e033ecc8d5125a964c64b70683ec" + "sha256": "e7d9819e12a79f97a0e708f6401db7ede878deff3a9b2aa3fe2f5aba09fdb15e" }, { "label": "world_class_evidence_plan", "path": "reports/world_class_evidence_plan.json", "exists": true, "bytes": 19940, - "sha256": "b408af112c784fdc3e96ea9ecf374990b9f58a0ebfa4df18394ccd9e93dc5545" + "sha256": "76a3f8e2b12b9ace575f3465bcee7697ddffb3440eed7ca3c3bb0becc61e1ab7" }, { "label": "world_class_evidence_ledger", "path": "reports/world_class_evidence_ledger.json", "exists": true, - "bytes": 21277, - "sha256": "63d7aaedf72503c21577928da46783e0ec55b0e92af326cb92ab1e01289db9f5" + "bytes": 21280, + "sha256": "1cb74eaa978b8a4aee3a95c4459bffb4092f2de8476fd18acce4b943687481b6" }, { "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, "bytes": 18865, - "sha256": "2fbecc603d8dc6382fde6c61869aaf4b56fc9d1be5afcd07b345c419dce6d55a" + "sha256": "99a0ba234d59c0329d4645064bd67508c3057cbcc684016437bd0c7f4d9c3b2a" }, { "label": "world_class_evidence_preflight", @@ -5531,36 +5554,36 @@ "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 13550, - "sha256": "ab20b288f47f2a739ec7862fa8a04985584a729d588a32dca3d71ba64d8de2fc" + "bytes": 13553, + "sha256": "b8317119e9cd19044bac24f9ff5f5ea7def5f7c782b0bb93b9ba4aa554d6fee6" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 23957, - "sha256": "b4640688026ef9199e96f80bd2d9971aaca3ec6d092d8ecd052a5debc0aa94c7" + "bytes": 24021, + "sha256": "f5ca32d5ea8bae74fccd5a574d6bbd3cad46d0950b73d522e66b0a439a433860" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 15025, - "sha256": "3a916ac568377d8df7d612426f7358283eddfa2ab5fedb7ed12db0097a8b3c48" + "bytes": 15080, + "sha256": "260d5e03c52edefd8640c2bb2a0d8ee2c4f6d4e964f925128d4ffdd5563db4ec" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 20969, - "sha256": "886b915da0f27fb46f4d8cebb6211ab5066a9fd44e1ec2e3206487d9a8abfff2" + "bytes": 21030, + "sha256": "04cc091b113f018072d07a1d71ad142773c415a49e633493689903e7b399b5e6" }, { "label": "world_class_claim_guard", "path": "reports/world_class_claim_guard.json", "exists": true, "bytes": 18218, - "sha256": "926bf86d54c2c3d09078e9cff5821e170c9fc398723d9c99bd89cdcf60e29691" + "sha256": "7359ad2ef09dc0863014aab541a92a1f3e55f18f0c0446816c1c7333cba256e9" } ], "missing_artifacts": [], @@ -5700,7 +5723,7 @@ "skill_os2_coverage": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "item_count": 21, @@ -5829,7 +5852,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "115 scripts; secrets 0; help failures 0", + "current": "116 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -5903,7 +5926,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 630; install failures 0", + "current": "archive entries 634; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ @@ -6484,7 +6507,7 @@ "compiled_targets": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "target_count": 5, @@ -11223,7 +11246,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -11263,7 +11286,7 @@ { "target": "openai", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", + "adapter": "dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11360,7 +11383,7 @@ { "target": "claude", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", + "adapter": "dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11442,7 +11465,7 @@ { "target": "generic", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", + "adapter": "dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11524,7 +11547,7 @@ { "target": "vscode", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", + "adapter": "dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -11614,9 +11637,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -11634,8 +11657,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "failures": [], "warnings": [], @@ -12988,6 +13011,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/skillops_opportunity.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by render_daily_skillops_report.py to score SkillOps opportunities without writing files.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/summarize_user_signals.py", "interface": "cli", @@ -13303,7 +13340,7 @@ "checked_count": 84, "passed_count": 84, "failed_count": 0, - "skipped_count": 31, + "skipped_count": 32, "failed_scripts": [], "results": [ { @@ -14228,6 +14265,10 @@ "path": "scripts/skill_report_world_class.py", "reason": "internal module" }, + { + "path": "scripts/skillops_opportunity.py", + "reason": "internal module" + }, { "path": "scripts/world_class_evidence_contract.py", "reason": "internal module" @@ -14461,11 +14502,11 @@ "python_compatibility": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "root": ".", "summary": { "target_python": "3.11", - "file_count": 184, + "file_count": 186, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -15070,6 +15111,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/skillops_opportunity.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/summarize_user_signals.py", "ok": true, @@ -15496,6 +15543,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_skillops_opportunity.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_system_model.py", "ok": true, @@ -15596,13 +15649,13 @@ "architecture_maintainability": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "python_file_count": 181, - "script_file_count": 115, - "test_file_count": 66, - "internal_module_count": 34, + "python_file_count": 183, + "script_file_count": 116, + "test_file_count": 67, + "internal_module_count": 35, "cli_script_count": 83, "command_handler_count": 66, "entrypoint_command_handler_count": 18, @@ -15795,22 +15848,22 @@ "stats": { "context_budget_tier": "production", "context_budget_limit": 1000, - "skill_body_tokens": 767, - "other_text_tokens": 1001355, - "estimated_initial_load_tokens": 960, - "estimated_total_text_tokens": 1002122, - "deferred_resource_tokens": 461032, + "skill_body_tokens": 797, + "other_text_tokens": 1007838, + "estimated_initial_load_tokens": 990, + "estimated_total_text_tokens": 1008635, + "deferred_resource_tokens": 464021, "deferred_resource_warn_threshold": 120000, "deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115 + "estimated_tokens": 414241, + "file_count": 116 }, { "path": "references", - "estimated_tokens": 27376, - "file_count": 34 + "estimated_tokens": 27945, + "file_count": 35 }, { "path": "evals", @@ -15821,8 +15874,8 @@ "large_deferred_resource_dirs": [ { "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115 + "estimated_tokens": 414241, + "file_count": 116 } ], "deferred_resource_governance": { @@ -15844,17 +15897,17 @@ ], "missing": [], "path": "scripts", - "estimated_tokens": 411821, - "file_count": 115, + "estimated_tokens": 414241, + "file_count": 116, "rationale": "Script resources are deterministic deferred tools, not initial-load prompt context." } ], "summary": "Large deferred resources are indexed and backed by evidence." }, - "relevant_file_count": 570, + "relevant_file_count": 609, "unused_resource_dirs": [], "quality_signal_points": 130, - "quality_density": 135.4 + "quality_density": 131.3 } }, "promotion": { @@ -16695,7 +16748,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skills": [ { "name": "yao-meta-skill", @@ -16810,6 +16863,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/skill_report_world_class.py", + "scripts/skillops_opportunity.py", "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", @@ -16860,6 +16914,7 @@ "references/skill-atlas-method.md", "references/skill-engineering-method.md", "references/skill-ir-method.md", + "references/skillops-decision-policy.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", "references/trust-security-method.md", @@ -16895,8 +16950,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, @@ -17559,7 +17614,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 74, + "age_days": 77, "allowed_days": 31, "actionable": false, "scope": "example" @@ -17727,7 +17782,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T20:34:53Z", + "generated_at": "2026-06-15T20:47:47Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -17751,14 +17806,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -17767,7 +17822,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -17779,31 +17834,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 1, - "accepted": 1, + "adoption_events": 0, + "accepted": 0, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 100.0 + "adoption_rate": 0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "skill_activation", + "event": "review_event", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "explicit", - "outcome": "accepted", + "activation_type": "manual", + "outcome": "reviewed", "failure_type": "none", - "timestamp": "2026-06-13T10:00:00Z" + "timestamp": "2026-06-13T12:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", + "events_jsonl": "reports/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } @@ -17812,7 +17867,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "summary": { "waiver_count": 0, "active_count": 0, @@ -17862,7 +17917,7 @@ "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 \"\" --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", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -17892,7 +17947,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "tests/tmp_review_studio/empty_review_annotations_input.json", + "source": "reports/review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, @@ -17915,7 +17970,7 @@ "adaptation_proposals": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-16", + "generated_at": "2026-06-15T20:47:47Z", "skill_dir": ".", "source_patterns": "reports/user_patterns.json", "pattern_count": 5, @@ -18313,7 +18368,7 @@ "world_class_evidence_ledger": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -18327,8 +18382,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -18343,8 +18398,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -18705,7 +18760,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -18742,7 +18797,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -18763,8 +18818,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -18780,8 +18835,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -18819,7 +18874,7 @@ "world_class_evidence_intake": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "schema_present": true, @@ -19125,7 +19180,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -19196,7 +19251,7 @@ "world_class_submission_review": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -19209,8 +19264,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -19222,8 +19277,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -19496,7 +19551,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -19517,8 +19572,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -19534,8 +19589,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", @@ -19561,7 +19616,7 @@ "world_class_operator_runbook": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "evidence_item_count": 4, @@ -19572,8 +19627,8 @@ "valid_packet_source_incomplete_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "runbook_counts_as_completion": false, "decision": "collect-evidence" @@ -19954,7 +20009,7 @@ "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 1", + "current": "external source events 0; adoption samples 0", "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:///", "Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.", @@ -20002,7 +20057,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -20023,8 +20078,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -20039,9 +20094,10 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 1, + "blocked_source_check_count": 2, "next_source_actions": [ - "Import at least one metadata-only event from a real client." + "Import at least one metadata-only event from a real client.", + "Telemetry must include adoption outcome evidence." ], "submission_state": { "status": "missing", @@ -20074,7 +20130,7 @@ "world_class_claim_guard": { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, @@ -20861,8 +20917,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -20893,16 +20949,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "package_count": 1, "packages": [ { @@ -20918,7 +20974,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -20941,8 +20997,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, @@ -21600,14 +21656,14 @@ "install_simulation": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", - "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", + "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", "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -21625,7 +21681,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" + "detail": "Package archive exists: dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -21871,16 +21927,16 @@ "failures": [], "warnings": [], "artifacts": { - "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" + "archive": "dist/yao-meta-skill.zip", + "package_manifest": "dist/manifest.json", + "json": "reports/install_simulation.json", + "markdown": "reports/install_simulation.md" } }, "upgrade_check": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -21949,12 +22005,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -21969,8 +22025,8 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "tests/tmp_review_studio/upgrade_check.json", - "markdown": "tests/tmp_review_studio/upgrade_check.md" + "json": "reports/upgrade_check.json", + "markdown": "reports/upgrade_check.md" } }, "manifest": { diff --git a/reports/review-viewer.html b/reports/review-viewer.html index e79a876f..89834f47 100644 --- a/reports/review-viewer.html +++ b/reports/review-viewer.html @@ -283,7 +283,7 @@

Prompt quality profile

-

Relevance: prompt-heavy · score 89.0 / 100 · complexity expert

+

Relevance: prompt-aware · score 89.0 / 100 · complexity expert

  • Completeness · 100 / 100
    Name missing inputs, outputs, constraints, or success standards before deepening the package.
  • Clarity · 85 / 100
    Replace broad verbs with observable actions and define what done means.
  • Consistency · 90 / 100
    Check that role, task, format, exclusions, and examples do not contradict each other.
  • Practicality · 90 / 100
    Add runnable steps, examples, or verification cues instead of abstract advice.
  • Specificity · 80 / 100
    Anchor wording in the user's audience, domain nouns, and target outcome.
diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 5ecacbd8..bc69acf7 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -81,7 +81,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -206,7 +206,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -271,7 +271,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -412,7 +412,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,7 +471,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -506,13 +507,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -524,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -548,11 +549,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -560,7 +561,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -676,13 +677,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -694,7 +695,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], "strengths": [ @@ -996,13 +997,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1017,14 +1018,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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.", @@ -1108,9 +1109,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1128,8 +1129,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "skill_atlas": { "skill_count": 12, @@ -1167,8 +1168,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -1199,12 +1200,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1215,8 +1216,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, @@ -1227,7 +1228,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1294,12 +1295,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -1316,14 +1317,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1332,7 +1333,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1554,7 +1555,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1606,8 +1607,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -1943,7 +1944,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1980,7 +1981,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2001,8 +2002,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2018,8 +2019,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", @@ -14387,7 +14388,7 @@ }, "prompt_quality": { "skill_name": "yao-meta-skill", - "relevance": "prompt-heavy", + "relevance": "prompt-aware", "primary_task_family": { "key": "execution_operation", "label": "Execution operation", @@ -14433,15 +14434,15 @@ "format_guidance": "Return options with rationale, selection criteria, and refinement paths." }, { - "key": "prompt_engineering", - "label": "Prompt engineering", + "key": "analytical_reasoning", + "label": "Analytical reasoning", "score": 1, "matched_keywords": [ - "prompt" + "decision" ], - "role_guidance": "Use a prompt engineer role only when role design materially improves execution.", - "task_guidance": "Map Role, Task, and Format into skill behavior rather than copying a large prompt template.", - "format_guidance": "Return a compact prompt contract plus tests, quality matrix, and usage notes." + "role_guidance": "Use an analyst role that separates evidence, inference, uncertainty, and recommendation.", + "task_guidance": "State assumptions, compare alternatives, and make the decision path inspectable.", + "format_guidance": "Return findings, evidence, tradeoffs, recommendation, and residual risks." } ], "complexity": { diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 66f2b1d9..76fadc1f 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "tests/tmp_review_studio/empty_review_annotations_input.json", + "source": "reports/review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 07eeccbc..aa2558e7 100644 --- a/reports/review_waivers.json +++ b/reports/review_waivers.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "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 \"\" --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", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { diff --git a/reports/review_waivers.md b/reports/review_waivers.md index dbc942d1..6c8d594c 100644 --- a/reports/review_waivers.md +++ b/reports/review_waivers.md @@ -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 "" --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` +- verification: `python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer "" --reason "Output Lab has pending human/provider evidence; accepted only for this bounded review scope." --expires-at 2027-06-16 --evidence reports/output_review_adjudication.md` - world-class boundary: Does not count as provider, human, or public world-class completion evidence. #### Required Review diff --git a/reports/runtime_permission_probes.json b/reports/runtime_permission_probes.json index 59c9a1a4..9c2ffd6e 100644 --- a/reports/runtime_permission_probes.json +++ b/reports/runtime_permission_probes.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "tests/tmp_review_studio/dist", + "package_dir": "dist", "expected_capabilities": [ "file_write", "network", @@ -42,7 +42,7 @@ { "target": "openai", "status": "pass", - "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", + "adapter": "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": "tests/tmp_review_studio/dist/targets/claude/adapter.json", + "adapter": "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": "tests/tmp_review_studio/dist/targets/generic/adapter.json", + "adapter": "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": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", + "adapter": "dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 2394d2c5..1f60be0f 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,9 +2,9 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -22,8 +22,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "failures": [], "warnings": [], @@ -1376,6 +1376,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/skillops_opportunity.py", + "interface": "internal-module", + "interface_declared": true, + "interface_reason": "Imported by render_daily_skillops_report.py to score SkillOps opportunities without writing files.", + "has_argparse": false, + "has_main_guard": false, + "uses_input": false, + "uses_network": false, + "uses_file_write": false, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/summarize_user_signals.py", "interface": "cli", @@ -1691,7 +1705,7 @@ "checked_count": 84, "passed_count": 84, "failed_count": 0, - "skipped_count": 31, + "skipped_count": 32, "failed_scripts": [], "results": [ { @@ -2616,6 +2630,10 @@ "path": "scripts/skill_report_world_class.py", "reason": "internal module" }, + { + "path": "scripts/skillops_opportunity.py", + "reason": "internal module" + }, { "path": "scripts/world_class_evidence_contract.py", "reason": "internal module" diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index a835f0df..b630a008 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,9 +1,9 @@ # Security Trust Report - OK: `True` -- Scanned files: `202` -- Scripts: `115` -- Internal script modules: `31` +- Scanned files: `204` +- Scripts: `116` +- Internal script modules: `32` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` @@ -15,8 +15,8 @@ - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `202` -- Package SHA256: `b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083` +- Package hash files: `204` +- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7` ## Failures @@ -157,6 +157,7 @@ | scripts/skill_report_metrics.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to calculate overview report metrics. | | scripts/skill_report_model.py | internal-module | True | False | False | False | False | False | False | Imported by render_skill_overview.py to build the v2 report data model. | | scripts/skill_report_world_class.py | internal-module | True | False | False | False | False | False | False | Imported by skill_report_model.py to summarize world-class evidence readiness and roadmap actions. | +| scripts/skillops_opportunity.py | internal-module | True | False | False | False | False | False | False | Imported by render_daily_skillops_report.py to score SkillOps opportunities without writing files. | | scripts/summarize_user_signals.py | cli | True | True | True | False | False | True | False | Scans an explicit local source file and summarizes redacted repeated user preference signals. | | scripts/sync_local_install.py | cli | False | True | True | False | False | True | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/telemetry_native_host.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | diff --git a/reports/skill-interpretation.html b/reports/skill-interpretation.html index 722d87d6..f7f54c2b 100644 --- a/reports/skill-interpretation.html +++ b/reports/skill-interpretation.html @@ -764,7 +764,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-interpretation.html，再继续扩展包体。After creation, open reports/skill-interpretation.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 16388.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.纳入下一轮修复Fix next
@@ -915,11 +915,11 @@
- +
风险Risk信号Signal应对Response
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
-

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks7 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
@@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution409项409 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution413项413 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-interpretation.json b/reports/skill-interpretation.json index 9c15a0cd..11def85e 100644 --- a/reports/skill-interpretation.json +++ b/reports/skill-interpretation.json @@ -81,7 +81,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -102,7 +102,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -206,7 +206,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -271,7 +271,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -412,7 +412,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -471,7 +471,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -506,13 +507,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -524,10 +525,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -548,11 +549,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -560,7 +561,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -680,13 +681,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -698,7 +699,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], "strengths": [ @@ -1000,13 +1001,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1021,14 +1022,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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.", @@ -1112,9 +1113,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1132,8 +1133,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "skill_atlas": { "skill_count": 12, @@ -1171,8 +1172,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -1203,12 +1204,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1219,8 +1220,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, @@ -1231,7 +1232,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1298,12 +1299,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -1320,14 +1321,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1336,7 +1337,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1558,7 +1559,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1610,8 +1611,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -1947,7 +1948,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1984,7 +1985,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2005,8 +2006,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2022,8 +2023,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index bb9e4786..94763334 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -114,13 +114,13 @@ Next move: add real client or installer permission enforcement integration. | Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden | | Runtime Conformance | `5 / 5` targets passing | | Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts | -| Trust | `0` secret findings, `1` pinned dependency file, `31` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `84 / 84` CLI help smoke checks passing across `115` scripts, source-contract hash scope explicit | +| Trust | `0` secret findings, `1` pinned dependency file, `32` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `84 / 84` CLI help smoke checks passing across `116` scripts, source-contract hash scope explicit | | Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired | | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | | Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix | -| Package Verification | `4 / 4` target adapters present, archive verified, `630` zip entries, `0` failures, `0` warnings | -| Install Simulation | archive with `630` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | +| Package Verification | `4 / 4` target adapters present, archive verified, `634` zip entries, `0` failures, `0` warnings | +| Install Simulation | archive with `634` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | | Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | @@ -132,8 +132,8 @@ Next move: add real client or installer permission enforcement integration. | World-Class Evidence Ledger | `4` evidence entries remain pending: `1` human-required and `3` external-required; anti-overclaim guards block planned work, metadata fallbacks, pending review, and local command runners from counting as completion | | Benchmark Reproducibility | local reproducibility ready with `25` required artifacts, `0` missing artifacts, `23` reproduction commands, and `3` disclosed failure cases; provider and human evidence remain explicit limitations | | IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable | -| Context Budget | initial load `960/1000`, under the production budget | -| CI | `make ci-test` target count is `78` after the Daily SkillOps gate update | +| Context Budget | initial load `990/1000`, under the production budget | +| CI | `make ci-test` target count is `79` after the SkillOps opportunity scoring gate update | ## Next Highest-Leverage Moves diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 36504f04..2f3d3ddc 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -764,7 +764,7 @@
  • 把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。Turn one-off experience into a reusable, evaluable, and portable skill package.
  • Skill 作者、复用团队和后续 reviewer。Skill authors, reuse teams, and later reviewers.
  • 创建完成后建议先打开 reports/skill-overview.html，再继续扩展包体。After creation, open reports/skill-overview.html before expanding the package further.
-
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
+
完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
上下文成本Context cost42入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
@@ -800,10 +800,10 @@
评分雷达Rating Radar完整度Completeness触发清晰Trigger clarity证据充分Evidence depth可维护性Maintainability可迁移性Portability
评分雷达展示结构完整度、触发边界、证据、维护和迁移的相对强弱。The radar chart compares completeness, trigger clarity, evidence, maintainability, and portability.

成熟度条Maturity Bar

-
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
+
  1. 稳定Stable完整度Completeness100SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  2. 稳定Stable触发清晰Trigger clarity100frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  3. 稳定Stable证据充分Evidence depth100已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  4. 稳定Stable可维护性Maintainability100SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  5. 稳定Stable可迁移性Portability100agents/interface.yaml 已存在。agents/interface.yaml exists.
  6. 关注Watch上下文成本Context cost42入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
-
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 356 个词/字，references 约 16388 个词/字。Entrypoint is about 356 words/characters; references are about 16388.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
+
完整度Completeness100
  • SKILL.md 已存在，是 Skill 的入口。SKILL.md exists and acts as the skill entrypoint.
  • README.md 已存在，便于人工阅读。README.md exists for human-readable usage.
  • agents/interface.yaml 已存在，便于跨平台适配。agents/interface.yaml exists for cross-platform adaptation.
触发清晰Trigger clarity100
  • frontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.
  • description 有足够长度说明任务边界。The description is long enough to explain the task boundary.
  • description 已包含使用场景或排除边界信号。The description includes usage-scenario or exclusion-boundary signals.
证据充分Evidence depth100
  • 已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.
  • skill-ir.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
  • compiled_targets.json 已存在。Skill-specific source text is authored in Chinese; switch to Simplified Chinese for the exact wording.
可维护性Maintainability100
  • SKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.
  • 入口文件保持克制，可维护性较好。The entrypoint stays restrained, which supports maintainability.
  • references/ 已承载扩展指导。references/ carries extended guidance.
可迁移性Portability100
  • agents/interface.yaml 已存在。agents/interface.yaml exists.
  • manifest.json 已存在。manifest.json exists.
  • 目标平台或 adapter target 已声明。Target platforms or adapter targets are declared.
上下文成本Context cost42
  • 入口约 360 个词/字，references 约 16740 个词/字。Entrypoint is about 360 words/characters; references are about 16740.
  • 分数越高代表上下文成本越低。A higher score means lower context cost.
  • 上下文成本偏高，建议压缩入口或拆分 references。Context cost is high; compress the entrypoint or split references further.
@@ -878,7 +878,7 @@
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder
- +
类型Type证据Evidence建议Action
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。Context cost needs improvement: Entrypoint is about 356 words/characters; references are about 16388.纳入下一轮修复Fix next
强项Strength触发面保持精简，并锚定在 frontmatter description。The trigger surface stays lean and anchored in the frontmatter description.保留并复用Keep
强项Strength已生成 Skill IR，核心语义可先于平台打包被审查和迁移。Skill IR is generated so core semantics can be reviewed and migrated before platform packaging.保留并复用Keep
强项Strength已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。Target compilation evidence is generated to review how IR maps to OpenAI, Claude, generic, and other target contracts.保留并复用Keep
缺口Gap上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。Context cost needs improvement: Entrypoint is about 360 words/characters; references are about 16740.纳入下一轮修复Fix next
@@ -915,11 +915,11 @@
- +
风险Risk信号Signal应对Response
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 356 个词/字。SKILL.md is about 356 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
误触发风险Trigger riskfrontmatter description 已存在，具备基础路由面。The frontmatter description exists, giving the skill a basic routing surface.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
输出漂移风险Output drift risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
证据不足风险Evidence gap risk已生成 20 / 20 类报告证据。Generated 20 / 20 evidence report types.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
包体膨胀风险Package bloat riskSKILL.md 约 360 个词/字。SKILL.md is about 360 words/characters.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
跨平台迁移风险Portability riskagents/interface.yaml 已存在。agents/interface.yaml exists.先补证据和边界，再增加包体复杂度。Improve evidence and boundaries before adding package complexity.
-

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks7 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
+

世界证据World Evidence

世界级证据尚未完成：4 项待补，0 项已接受。World-class evidence is not complete: 4 pending, 0 accepted.

证据待补Evidence pending
待补证据Pending4仍需外部或人工证据接受。External or human evidence still needs acceptance.
已接受Accepted0已通过 source check 与提交契约。Passed source checks and submission contract.
源检查Source Checks6 / 13通过数 / 总检查数。Passed checks / total checks.
外部证据External evidence

提供商留出Provider Holdout

缺少真实 provider 模型运行和 token metadata。Missing a real provider model run and token metadata.

阻塞检查Blocked Checks
  • 提供商实跑Provider model run
  • Token 用量Token usage observed
人工证据Human evidence

人工盲评Human Adjudication

盲评 pair 仍待真实 reviewer 决策。Blind-review pairs still need real reviewer decisions.

阻塞检查Blocked Checks
  • 无待判定No pending decisions
  • 盲评完成Judgments complete
外部证据External evidence

原生权限Native Permission

原生 runtime enforcement 仍待目标客户端或外部安装器证明。Native runtime enforcement still needs target-client or external-installer proof.

阻塞检查Blocked Checks
  • 原生执行Native enforcement
外部证据External evidence

原生遥测Native Telemetry

真实外部客户端 metadata-only 事件仍未导入。Real external-client metadata-only events have not been imported yet.

阻塞检查Blocked Checks
  • 外部事件External events
  • 采用样本Adoption sample
@@ -930,7 +930,7 @@

让 reviewer 快速确认关键文件、目录和资产分布。Lets reviewers confirm key files, directories, and asset distribution quickly.

-
资产分布Asset Distribution409项409 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
+
资产分布Asset Distribution413项413 itemsSKILL.mdSKILL.mdREADME.mdREADME.mdagents/interface.yamlagents/interface.yamlmanifest.jsonmanifest.jsonreferencesreferencesscriptsscripts
资产分布图展示当前包体的文件和目录重心。The asset distribution chart shows where files and directories are concentrated.
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 456e85cd..a13891d8 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -80,7 +80,7 @@ "label": "可维护性", "score": 100, "reasons": [ - "SKILL.md 约 356 个词/字。", + "SKILL.md 约 360 个词/字。", "入口文件保持克制，可维护性较好。", "references/ 已承载扩展指导。", "scripts/ 已承载确定性逻辑。", @@ -101,7 +101,7 @@ "label": "上下文成本", "score": 42, "reasons": [ - "入口约 356 个词/字，references 约 16388 个词/字。", + "入口约 360 个词/字，references 约 16740 个词/字。", "分数越高代表上下文成本越低。", "上下文成本偏高，建议压缩入口或拆分 references。" ] @@ -205,7 +205,7 @@ "已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。" ], "gaps": [ - "上下文成本需要补强：入口约 356 个词/字，references 约 16388 个词/字。" + "上下文成本需要补强：入口约 360 个词/字，references 约 16740 个词/字。" ], "recommendations": [ "先改触发边界，再扩展工作流。", @@ -270,7 +270,7 @@ "name": "包体膨胀风险", "impact": 2, "probability": 1, - "signal": "SKILL.md 约 356 个词/字。", + "signal": "SKILL.md 约 360 个词/字。", "response": "先补证据和边界，再增加包体复杂度。" }, { @@ -411,7 +411,7 @@ "external_pending_count": 3, "human_pending_count": 1, "source_check_count": 13, - "source_pass_count": 7, + "source_pass_count": 6, "conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。", "conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.", "entries": [ @@ -470,7 +470,8 @@ "summary_zh": "真实外部客户端 metadata-only 事件仍未导入。", "summary_en": "Real external-client metadata-only events have not been imported yet.", "blocked_checks": [ - "External events" + "External events", + "Adoption sample" ] } ] @@ -505,13 +506,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -523,10 +524,10 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], - "file_count": 409, + "file_count": 413, "folder_count": 4, "distribution": [ { @@ -547,11 +548,11 @@ }, { "label": "references", - "value": 34 + "value": 35 }, { "label": "scripts", - "value": 115 + "value": 116 }, { "label": "evals", @@ -559,7 +560,7 @@ }, { "label": "reports", - "value": 227 + "value": 229 } ] }, @@ -675,13 +676,13 @@ "path": "references", "label": "Extended guidance and reusable notes", "kind": "folder", - "file_count": 34 + "file_count": 35 }, { "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 115 + "file_count": 116 }, { "path": "evals", @@ -693,7 +694,7 @@ "path": "reports", "label": "Generated evidence and overview artifacts", "kind": "folder", - "file_count": 227 + "file_count": 229 } ], "strengths": [ @@ -995,13 +996,13 @@ "ok": true, "summary": { "reproducibility_ready": true, - "release_lock_ready": true, + "release_lock_ready": false, "methodology_complete": true, "required_artifact_count": 25, "missing_artifact_count": 0, - "evidence_bundle_sha256": "3a7d57917032305aa9e1374c8e659e37e7cee771b82238848ba4b21479ddd6c4", - "source_contract_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "evidence_bundle_sha256": "8eaf9f0bedd393943fce51d00f80191be7cb6a92b62aab3d6e7f341bd6bdd31c", + "source_contract_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 23, @@ -1016,14 +1017,14 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "world_class_source_check_count": 13, - "world_class_source_pass_count": 7, - "world_class_source_blocked_count": 6, + "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": 69 }, - "commit": "3ea32f51a55aec572e423c7c0d3f66edf8f64bd0", + "commit": "3677dd4664b0777391fb82ab9987a7b6ea975af5", "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.", @@ -1107,9 +1108,9 @@ "failures": [] }, "trust_security": { - "scanned_files": 202, - "script_count": 115, - "internal_module_count": 31, + "scanned_files": 204, + "script_count": 116, + "internal_module_count": 32, "secret_findings": 0, "dependency_files": [ "requirements-ci.txt" @@ -1127,8 +1128,8 @@ "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 202, - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "package_hash_file_count": 204, + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" }, "skill_atlas": { "skill_count": 12, @@ -1166,8 +1167,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083", - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, "compatibility": { "openai": "pass", @@ -1198,12 +1199,12 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-13" + "generated_at": "2026-06-16" }, "failures": [], "warnings": [] @@ -1214,8 +1215,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed", - "archive_entry_count": 630, + "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_entry_count": 634, "failure_count": 0, "warning_count": 0 }, @@ -1226,7 +1227,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 630, + "archive_entry_count": 634, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1293,12 +1294,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -1315,14 +1316,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 1, - "activation_count": 1, - "accepted_count": 1, + "adoption_sample_count": 0, + "activation_count": 0, + "accepted_count": 0, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 100.0, + "adoption_rate": 0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1331,7 +1332,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "skill_activation": 1 + "review_event": 1 }, "failure_types": {}, "source_types": { @@ -1553,7 +1554,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1605,8 +1606,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -1942,7 +1943,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -1979,7 +1980,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -2000,8 +2001,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -2017,8 +2018,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index a7e76ce2..55c53b1e 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -44,7 +44,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skills": [ { "name": "yao-meta-skill", @@ -159,6 +159,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/skill_report_world_class.py", + "scripts/skillops_opportunity.py", "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", @@ -209,6 +210,7 @@ "references/skill-atlas-method.md", "references/skill-engineering-method.md", "references/skill-ir-method.md", + "references/skillops-decision-policy.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", "references/trust-security-method.md", @@ -244,8 +246,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, @@ -908,7 +910,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 74, + "age_days": 77, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 91211d40..452ce92f 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "item_count": 15, @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 115; help failures 0", + "current": "secrets 0; scripts 116; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { @@ -285,7 +285,7 @@ "key": "registry-distribution", "label": "Registry Distribution", "status": "pass", - "current": "zip entries 630; install failures 0; permission failures 0", + "current": "zip entries 634; install failures 0; permission failures 0", "target": "Package metadata, archive checksum, package verification, and install simulation pass", "evidence": [ { @@ -351,7 +351,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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 1", + "current": "external source events 0; adoption samples 0", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 2ced448a..78d02ff4 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Audit -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary @@ -23,14 +23,14 @@ Generated at: `2026-06-13` | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. | | Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. | | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. | -| Trust Security | pass | secrets 0; scripts 115; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | +| Trust Security | pass | secrets 0; scripts 116; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | -| Registry Distribution | pass | zip entries 630; 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. | +| Registry Distribution | pass | zip entries 634; 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 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. | +| 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. | ## Open Highest-Leverage Gaps diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 83370704..c7a35e63 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "item_count": 21, @@ -130,7 +130,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "115 scripts; secrets 0; help failures 0", + "current": "116 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -204,7 +204,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 630; install failures 0", + "current": "archive entries 634; install failures 0", "command": "python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .", "test": "python3 tests/verify_registry_audit.py", "evidence": [ diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 469e9215..99090853 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Blueprint Coverage -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary @@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` | | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` | | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | -| Trust Security | `pass` | 115 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 116 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | | Skill Atlas | `pass` | 12 scanned skills; actionable collisions 0 | `python3 scripts/yao.py skill-atlas --workspace-root .` | `python3 tests/verify_skill_atlas.py` | -| Registry Distribution | `pass` | archive entries 630; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | +| Registry Distribution | `pass` | archive entries 634; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | | Review Studio | `pass` | 16 gates; decision review; warnings 3 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` | | Telemetry Drift | `pass` | events 1; recipes 5; risk low | `python3 scripts/yao.py telemetry-hooks . && python3 scripts/yao.py adoption-drift .` | `python3 tests/verify_telemetry_hooks.py` | diff --git a/reports/skillops/daily/2026-06-16.json b/reports/skillops/daily/2026-06-16.json index 86e11d71..a35cbc88 100644 --- a/reports/skillops/daily/2026-06-16.json +++ b/reports/skillops/daily/2026-06-16.json @@ -268,6 +268,208 @@ ] } ], + "opportunity_summary": { + "opportunity_count": 5, + "top_score": 88, + "ready_for_approval_review_count": 1, + "proposal_review_count": 4, + "observe_more_evidence_count": 0, + "report_only_count": 0, + "action_type_counts": { + "patch_existing_skill": 3, + "agents_update": 1, + "add_eval": 1 + }, + "decision_counts": { + "ready_for_approval_review": 1, + "proposal_review": 4 + } + }, + "opportunities": [ + { + "opportunity_id": "skillops-4ad91c18dd", + "proposal_id": "adapt-fbfe921ba5", + "pattern_id": "report_ui", + "title": "Improve report layout, visual hierarchy, and chart readability", + "opportunity_type": "artifact-quality", + "action_type": "patch_existing_skill", + "decision": "ready_for_approval_review", + "priority": "medium", + "score": 88, + "score_reasons": [ + "support_count=5", + "confidence=0.95", + "risk=medium", + "target_files_present", + "verification_present", + "approval_required" + ], + "policy_reason": "Repeated report layout feedback maps to existing renderer and design doctrine changes.", + "risk_level": "medium", + "requires_approval": true, + "write_allowed_without_approval": false, + "evidence_count": 5, + "target_files": [ + "scripts/render_skill_overview.py", + "references/artifact-design-doctrine.md", + "tests/verify_skill_overview.py" + ], + "verification_commands": [ + "python3 tests/verify_skill_overview.py", + "python3 tests/verify_skill_report_charts.py" + ] + }, + { + "opportunity_id": "skillops-531e13c1c6", + "proposal_id": "adapt-59d219a1fb", + "pattern_id": "approval_safety", + "title": "Keep adaptive iteration approval-gated", + "opportunity_type": "governance", + "action_type": "agents_update", + "decision": "proposal_review", + "priority": "medium", + "score": 82, + "score_reasons": [ + "support_count=2", + "confidence=0.79", + "risk=low", + "target_files_present", + "verification_present", + "approval_required" + ], + "policy_reason": "Repeated privacy and approval signals should tighten durable operating guidance.", + "risk_level": "low", + "requires_approval": true, + "write_allowed_without_approval": false, + "evidence_count": 2, + "target_files": [ + "references/user-memory-policy.md", + "references/autonomous-adaptation.md", + "schemas/adaptation-proposal.schema.json" + ], + "verification_commands": [ + "python3 tests/verify_adaptation_safety.py" + ] + }, + { + "opportunity_id": "skillops-709ef884f3", + "proposal_id": "adapt-18c7517f3d", + "pattern_id": "language_default", + "title": "Keep reports Chinese-first with optional English", + "opportunity_type": "report-experience", + "action_type": "patch_existing_skill", + "decision": "proposal_review", + "priority": "medium", + "score": 82, + "score_reasons": [ + "support_count=2", + "confidence=0.79", + "risk=low", + "target_files_present", + "verification_present", + "approval_required" + ], + "policy_reason": "Repeated language preferences can improve existing report templates after approval.", + "risk_level": "low", + "requires_approval": true, + "write_allowed_without_approval": false, + "evidence_count": 2, + "target_files": [ + "scripts/render_skill_overview.py", + "references/artifact-design-doctrine.md" + ], + "verification_commands": [ + "python3 tests/verify_skill_overview.py" + ] + }, + { + "opportunity_id": "skillops-f9e43237aa", + "proposal_id": "adapt-457baca160", + "pattern_id": "delivery_format", + "title": "Make generated artifact paths explicit in CLI output", + "opportunity_type": "artifact-discoverability", + "action_type": "patch_existing_skill", + "decision": "proposal_review", + "priority": "medium", + "score": 82, + "score_reasons": [ + "support_count=2", + "confidence=0.79", + "risk=low", + "target_files_present", + "verification_present", + "approval_required" + ], + "policy_reason": "Repeated delivery-path requests can improve CLI and README artifact discoverability.", + "risk_level": "low", + "requires_approval": true, + "write_allowed_without_approval": false, + "evidence_count": 2, + "target_files": [ + "scripts/yao.py", + "README.md" + ], + "verification_commands": [ + "python3 tests/verify_yao_cli.py" + ] + }, + { + "opportunity_id": "skillops-0a3a2de7c3", + "proposal_id": "adapt-abfee25d3a", + "pattern_id": "evidence_testing", + "title": "Attach tests and evidence refresh to each upgrade", + "opportunity_type": "quality-gate", + "action_type": "add_eval", + "decision": "proposal_review", + "priority": "medium", + "score": 74, + "score_reasons": [ + "support_count=2", + "confidence=0.79", + "risk=medium", + "target_files_present", + "verification_present", + "approval_required" + ], + "policy_reason": "Repeated verification and evidence requests should become focused checks.", + "risk_level": "medium", + "requires_approval": true, + "write_allowed_without_approval": false, + "evidence_count": 2, + "target_files": [ + "tests/verify_adaptation_safety.py", + "scripts/render_skill_os2_coverage.py", + "reports/skill_os2_coverage.json" + ], + "verification_commands": [ + "python3 tests/verify_adaptation_safety.py", + "python3 tests/verify_skill_os2_coverage.py" + ] + } + ], + "decision_policy": { + "schema_version": "1.0", + "contract": "skillops-opportunity-scoring", + "score_range": [ + 0, + 100 + ], + "score_bands": { + "85-100": "ready_for_approval_review", + "70-84": "proposal_review", + "50-69": "observe_more_evidence", + "0-49": "report_only_or_no_action" + }, + "action_types": [ + "add_eval", + "agents_update", + "patch_existing_skill", + "report_only" + ], + "writes_source_files": false, + "auto_patch_enabled": false, + "approval_required_for_writes": true + }, "approval": { "approval_count": 0, "pending_review_count": 0, diff --git a/reports/skillops/daily/2026-06-16.md b/reports/skillops/daily/2026-06-16.md index 326369b7..105c41c3 100644 --- a/reports/skillops/daily/2026-06-16.md +++ b/reports/skillops/daily/2026-06-16.md @@ -36,6 +36,52 @@ This report is an operations cockpit for explicit-source SkillOps. It does not s - `high` Review proposal-only adaptation items before preparing any approval ledger entry. - `high` Collect accepted external or human evidence for the pending world-class ledger entries. +## Opportunities + +- count: `5` +- top score: `88` +- ready for approval review: `1` +### Improve report layout, visual hierarchy, and chart readability + +- ID: `skillops-4ad91c18dd` +- Action: `patch_existing_skill` +- Decision: `ready_for_approval_review` +- Score: `88` +- Risk: `medium` +- Policy: Repeated report layout feedback maps to existing renderer and design doctrine changes. +### Keep adaptive iteration approval-gated + +- ID: `skillops-531e13c1c6` +- Action: `agents_update` +- Decision: `proposal_review` +- Score: `82` +- Risk: `low` +- Policy: Repeated privacy and approval signals should tighten durable operating guidance. +### Keep reports Chinese-first with optional English + +- ID: `skillops-709ef884f3` +- Action: `patch_existing_skill` +- Decision: `proposal_review` +- Score: `82` +- Risk: `low` +- Policy: Repeated language preferences can improve existing report templates after approval. +### Make generated artifact paths explicit in CLI output + +- ID: `skillops-f9e43237aa` +- Action: `patch_existing_skill` +- Decision: `proposal_review` +- Score: `82` +- Risk: `low` +- Policy: Repeated delivery-path requests can improve CLI and README artifact discoverability. +### Attach tests and evidence refresh to each upgrade + +- ID: `skillops-0a3a2de7c3` +- Action: `add_eval` +- Decision: `proposal_review` +- Score: `74` +- Risk: `medium` +- Policy: Repeated verification and evidence requests should become focused checks. + ## Patterns - `language_default`: Default language preference (support `2`, confidence `0.79`) diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index 41d8914e..fbecf450 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "7e55b9259f9a93d8590effddc92463882fe4d4f14696f54af5af10b0587fc0ed" + "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "b6abceeea0f2329299123b8e295469602f9e742298f729e60d9b56ef49b48083" + "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" } ] }, @@ -90,7 +90,7 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "tests/tmp_review_studio/upgrade_check.json", - "markdown": "tests/tmp_review_studio/upgrade_check.md" + "json": "reports/upgrade_check.json", + "markdown": "reports/upgrade_check.md" } } diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index e578865f..a4f2f9c3 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "ledger_ready_to_claim_world_class": false, diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index 01cef197..ee6c3083 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -1,6 +1,6 @@ # World-Class Claim Guard -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index ed002e84..396b0c9a 100644 --- a/reports/world_class_evidence_intake.json +++ b/reports/world_class_evidence_intake.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "summary": { "schema_present": true, @@ -307,7 +307,7 @@ "source_accepted": false, "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index 62c2d7ed..33297ad1 100644 --- a/reports/world_class_evidence_intake.md +++ b/reports/world_class_evidence_intake.md @@ -1,6 +1,6 @@ # World-Class Evidence Intake -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index 58110595..7c395391 100644 --- a/reports/world_class_evidence_ledger.json +++ b/reports/world_class_evidence_ledger.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "decision": "evidence-pending", "ready_to_claim_world_class": false, @@ -15,8 +15,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -31,8 +31,8 @@ "missing_submission_count": 4, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "submitted_but_pending_count": 0, "source_accepted_without_valid_submission_count": 0, "overclaim_guard_active": true, @@ -393,7 +393,7 @@ "status": "pending", "source_status": "external_required", "source_accepted": false, - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -430,7 +430,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -451,8 +451,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -468,8 +468,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "submission_state": { "status": "missing", "path": "evidence/world_class/submissions/native-client-telemetry.json", diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index 8ec440ff..9f5a3944 100644 --- a/reports/world_class_evidence_ledger.md +++ b/reports/world_class_evidence_ledger.md @@ -1,6 +1,6 @@ # World-Class Evidence Ledger -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## Summary @@ -8,8 +8,8 @@ Generated at: `2026-06-13` - ready to claim world-class: `false` - entries: `4` - source accepted: `0` -- source checks: `7` pass / `13` total -- source blocked: `6` +- source checks: `6` pass / `13` total +- source blocked: `7` - 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 1 | 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 0 | 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": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` -- source checks: `2` pass / `3` total +- 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 - 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 | `1` | `>0` | `pass` | +| Adoption sample | `0` | `>0` | `blocked` | | Raw content blocked | `False` | `false` | `pass` | ### Completion Assertions diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index 236c40fe..afaae4db 100644 --- a/reports/world_class_evidence_plan.json +++ b/reports/world_class_evidence_plan.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "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 1", + "current": "external source events 0; adoption samples 0", "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:///", @@ -299,7 +299,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 1", + "current": "external source events 0; adoption samples 0", "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:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index c0db846d..e97adc90 100644 --- a/reports/world_class_evidence_plan.md +++ b/reports/world_class_evidence_plan.md @@ -1,6 +1,6 @@ # World-Class Evidence Plan -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## 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 1 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | ## Provider Holdout diff --git a/reports/world_class_evidence_preflight.html b/reports/world_class_evidence_preflight.html index 73e1f07b..6a0a8f10 100644 --- a/reports/world_class_evidence_preflight.html +++ b/reports/world_class_evidence_preflight.html @@ -59,7 +59,7 @@ Evidence Collection

World-Class Evidence Preflight

This operator view shows which external and human evidence is still blocked, which commands prepare editable submission drafts, and why preflight never counts as accepted evidence.

-
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source7/13
+
Decisioncollection-preflight-blocked
Pending4
Ready1
Blocked3
Source6/13
@@ -495,15 +495,15 @@
-
+
adoption_sample_count Adoption sample
-
Current
1
+
Current
0
Expected
>0
-
Status
pass
+
Status
blocked
Action
Telemetry must include adoption outcome evidence.
diff --git a/reports/world_class_evidence_preflight.json b/reports/world_class_evidence_preflight.json index aa7c5816..74baff75 100644 --- a/reports/world_class_evidence_preflight.json +++ b/reports/world_class_evidence_preflight.json @@ -14,8 +14,8 @@ "collection_ready_count": 1, "collection_blocked_count": 3, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "pending_count": 4, "ready_to_claim_world_class": false, "credential_value_exposed": false, @@ -448,8 +448,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -768,8 +768,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, diff --git a/reports/world_class_evidence_preflight.md b/reports/world_class_evidence_preflight.md index 40352893..ea962bc7 100644 --- a/reports/world_class_evidence_preflight.md +++ b/reports/world_class_evidence_preflight.md @@ -10,7 +10,7 @@ Generated at: `2026-06-16` - credential value exposed: `false` - collection ready: `1` - collection blocked: `3` -- source checks: `7` pass / `13` total +- source checks: `6` pass / `13` total This preflight report checks whether an operator can start collecting the remaining external or human evidence. It never accepts evidence, prints secret values, or changes the world-class ledger. @@ -132,7 +132,7 @@ Generate the submission kit after the real provider, human, native-permission, o | Check | Current | Expected | Status | Next action | | --- | --- | --- | --- | --- | | External events | `0` | `>0` | `blocked` | Import at least one metadata-only event from a real client. | -| Adoption sample | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_operator_runbook.html b/reports/world_class_operator_runbook.html index e239453a..be9f2679 100644 --- a/reports/world_class_operator_runbook.html +++ b/reports/world_class_operator_runbook.html @@ -57,7 +57,7 @@ Evidence Operations

World-Class Operator Runbook

A single operating page for collecting the remaining human and external evidence. It coordinates action, but does not accept evidence or change the ledger.

-
Pending4
Awaiting4
Ready0
Source7/13
Blocked6
Invalid0
+
Pending4
Awaiting4
Ready0
Source6/13
Blocked7
Invalid0

Fast Path

  1. Run the real external or human work for one evidence item.
  2. Generate and fill the matching submission draft.
  3. Validate intake and inspect the submission review queue.
  4. Refresh the ledger and run the claim guard before making any completion claim.

Evidence Items

@@ -120,7 +120,7 @@
Owner
Browser/Chrome/IDE/provider client integrator
Ledger
pending
-
Blocked
1
+
Blocked
2
Submission
evidence/world_class/submissions/native-client-telemetry.json

Source 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.
  • python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl
  • python3 scripts/yao.py skill-atlas --workspace-root .
  • python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>
  • 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.
  • python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
@@ -130,8 +130,8 @@

Success Checks

  • reports/adoption_drift_report.json summary.source_types.external > 0
  • reports/adoption_drift_report.json summary.adoption_sample_count > 0
  • reports/skill_os2_audit.json item native-client-telemetry status becomes pass

Privacy

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
-

Next Source Actions

  • Import at least one metadata-only event from a real client.
-

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 1 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.
+

Next Source Actions

  • Import at least one metadata-only event from a real client.
  • Telemetry must include adoption outcome evidence.
+

Source Evidence Snapshot

  • External eventsexternal_source_events: 0 / >0Import at least one metadata-only event from a real client.
  • Adoption sampleadoption_sample_count: 0 / >0Telemetry must include adoption outcome evidence.
  • Raw content blockedraw_content_allowed: False / falseTelemetry must stay metadata-only.

Boundary

  • Planned work, draft packets, metadata fallback, pending human decisions, and local command runners do not count as completion.
  • Valid intake means ready for submission review; ledger review still requires passing source evidence.
  • The world-class ledger and claim guard remain the source of truth.
diff --git a/reports/world_class_operator_runbook.json b/reports/world_class_operator_runbook.json index eb0e1857..1ad88b47 100644 --- a/reports/world_class_operator_runbook.json +++ b/reports/world_class_operator_runbook.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "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": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "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 1", + "current": "external source events 0; adoption samples 0", "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:///", "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": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -463,8 +463,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -479,9 +479,10 @@ "next_action": "Telemetry must stay metadata-only." } ], - "blocked_source_check_count": 1, + "blocked_source_check_count": 2, "next_source_actions": [ - "Import at least one metadata-only event from a real client." + "Import at least one metadata-only event from a real client.", + "Telemetry must include adoption outcome evidence." ], "submission_state": { "status": "missing", diff --git a/reports/world_class_operator_runbook.md b/reports/world_class_operator_runbook.md index bef6278b..715b410a 100644 --- a/reports/world_class_operator_runbook.md +++ b/reports/world_class_operator_runbook.md @@ -1,6 +1,6 @@ # World-Class Operator Runbook -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## 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` | `1` | 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` | `2` | 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: `1` +- blocked source checks: `2` - submission: `evidence/world_class/submissions/native-client-telemetry.json` - template: `evidence/world_class/templates/native-client-telemetry.intake.json` @@ -292,13 +292,14 @@ 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 | `1` | `>0` | `pass` | Telemetry must include adoption outcome evidence. | +| Adoption sample | `0` | `>0` | `blocked` | Telemetry must include adoption outcome evidence. | | Raw content blocked | `False` | `false` | `pass` | Telemetry must stay metadata-only. | ## Boundary diff --git a/reports/world_class_submission_review.json b/reports/world_class_submission_review.json index 9df3045c..867863f1 100644 --- a/reports/world_class_submission_review.json +++ b/reports/world_class_submission_review.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skill_dir": ".", "decision": "awaiting-submissions", "ready_to_claim_world_class": false, @@ -14,8 +14,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "review_counts_submission_as_completion": false, "summary": { "review_item_count": 4, @@ -27,8 +27,8 @@ "unmatched_submission_count": 0, "invalid_submission_count": 0, "source_check_count": 13, - "source_pass_count": 7, - "source_blocked_count": 6, + "source_pass_count": 6, + "source_blocked_count": 7, "ready_to_claim_world_class": false, "review_counts_submission_as_completion": false, "decision": "awaiting-submissions" @@ -301,7 +301,7 @@ "intake_errors": [], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 1, + "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -322,8 +322,8 @@ "label": "Adoption sample", "field": "adoption_sample_count", "expected": ">0", - "actual": 1, - "status": "pass", + "actual": 0, + "status": "blocked", "source_accepted": false, "next_action": "Telemetry must include adoption outcome evidence." }, @@ -339,8 +339,8 @@ } ], "source_check_count": 3, - "source_pass_count": 2, - "source_blocked_count": 1, + "source_pass_count": 1, + "source_blocked_count": 2, "success_checks": [ "reports/adoption_drift_report.json summary.source_types.external > 0", "reports/adoption_drift_report.json summary.adoption_sample_count > 0", diff --git a/reports/world_class_submission_review.md b/reports/world_class_submission_review.md index 7fe1e470..899b7aa1 100644 --- a/reports/world_class_submission_review.md +++ b/reports/world_class_submission_review.md @@ -1,6 +1,6 @@ # World-Class Submission Review -Generated at: `2026-06-13` +Generated at: `2026-06-16` ## 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: 1 / >0 => pass +- Adoption sample: 0 / >0 => blocked - Raw content blocked: False / false => pass #### Completion Assertions diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index fac24783..265edbc2 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -1,6 +1,6 @@ { "workspace_root": ".", - "generated_at": "2026-06-13", + "generated_at": "2026-06-16", "skills": [ { "name": "yao-meta-skill", @@ -115,6 +115,7 @@ "scripts/skill_report_metrics.py", "scripts/skill_report_model.py", "scripts/skill_report_world_class.py", + "scripts/skillops_opportunity.py", "scripts/summarize_user_signals.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", @@ -165,6 +166,7 @@ "references/skill-atlas-method.md", "references/skill-engineering-method.md", "references/skill-ir-method.md", + "references/skillops-decision-policy.md", "references/systems-thinking-doctrine.md", "references/telemetry-drift-method.md", "references/trust-security-method.md", @@ -200,8 +202,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 1, - "adoption_rate": 100.0, + "adoption_sample_count": 0, + "adoption_rate": 0, "candidate_count": 0 } }, diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json index 6602e829..b57d361d 100644 --- a/skill_atlas/stale_skills.json +++ b/skill_atlas/stale_skills.json @@ -24,7 +24,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 74, + "age_days": 77, "allowed_days": 31, "actionable": false, "scope": "example"
路径Path作用Role类型Type
SKILL.mdSkill 入口文件Skill entrypoint文件file
README.md人类可读使用说明Human-readable usage guide文件file
agents/interface.yaml跨平台接口元数据Neutral interface metadata文件file
manifest.json生命周期与打包元数据Lifecycle and portability metadata文件file
references扩展指导与复用资料Extended guidance and reusable notes目录folder
scripts确定性脚本或本地工具Deterministic helpers or local tooling目录folder
evals触发与质量检查Trigger and quality checks目录folder
reports生成的证据与总结报告Generated evidence and overview artifacts目录folder