diff --git a/.gitignore b/.gitignore index 3a814aa8..bc323ba0 100644 --- a/.gitignore +++ b/.gitignore @@ -24,6 +24,7 @@ tests/tmp_baseline_compare.* reports/release_snapshots/ reports/telemetry_events.jsonl .yao/ +evidence/world_class/submission-kit/ evidence/world_class/submissions/ # Local business-skill experiments belong outside this meta-skill repo unless promoted intentionally. diff --git a/README.md b/README.md index 5cb45c2f..5951cfb5 100644 --- a/README.md +++ b/README.md @@ -143,6 +143,7 @@ python3 scripts/yao.py package-verify . --package-dir dist --require-zip python3 scripts/yao.py install-simulate . --package-dir dist python3 scripts/yao.py upgrade-check . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json python3 scripts/yao.py world-class-evidence . +python3 scripts/yao.py world-class-submission-kit . --output-dir /tmp/yao-world-class-submission-kit python3 scripts/yao.py world-class-ledger . python3 scripts/yao.py world-class-intake . python3 scripts/yao.py world-class-claim-guard . diff --git a/evidence/world_class/README.md b/evidence/world_class/README.md index 7417cb8d..642a2790 100644 --- a/evidence/world_class/README.md +++ b/evidence/world_class/README.md @@ -7,6 +7,7 @@ The templates in `templates/` are review aids only. They do not count as accepte Run: ```bash +python3 scripts/yao.py world-class-submission-kit . --output-dir /tmp/yao-world-class-submission-kit python3 scripts/yao.py world-class-intake . ``` @@ -20,4 +21,6 @@ The intake validator checks: The generated intake report also includes an `operator_checklist` for each pending evidence item. Use it to find the template path, target submission path, preparation command, validation command, required provenance, success checks, and privacy boundary before asking a reviewer or external operator to submit evidence. +The submission kit command creates editable JSON drafts plus a local README for an external operator or human reviewer. Those drafts keep `template_only: true` and do not count as evidence until the real run or review exists, the packet is edited truthfully, and `world-class-intake` validates it. + Accepted intake means "ready for ledger review", not "world-class complete". The ledger remains the source of truth for `ready_to_claim_world_class`. diff --git a/registry/index.json b/registry/index.json index 450c60d6..ce5e8972 100644 --- a/registry/index.json +++ b/registry/index.json @@ -1,6 +1,6 @@ { "schema_version": "2.0", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_sha256": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index b7ae3900..32f86700 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": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9", - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "package_sha256": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, "compatibility": { "openai": "pass", @@ -48,10 +48,10 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-14" + "generated_at": "2026-06-13" } diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index ac177722..125e304b 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": "2026-06-13T22:00:20Z", + "generated_at": "2026-06-13T22:21:26Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -25,14 +25,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -41,7 +41,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -53,31 +53,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } diff --git a/reports/adoption_drift_report.md b/reports/adoption_drift_report.md index 91b31983..206372c9 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: `0` -- Activation events: `0` -- Adoption rate: `0` +- Adoption samples: `1` +- Activation events: `1` +- Adoption rate: `100.0` - Missed trigger signals: `0` - Bad output signals: `0` - Script error signals: `0` @@ -25,7 +25,7 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, | Skill | Events | Adoption Samples | Accepted | Edited | Rejected | Missed | Adoption Rate | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | -| `yao-meta-skill` | 1 | 0 | 0 | 0 | 0 | 0 | 0 | +| `yao-meta-skill` | 1 | 1 | 1 | 0 | 0 | 0 | 100.0 | ## Next Iteration Candidates @@ -33,4 +33,4 @@ Local-first, metadata-only telemetry for skill operations. Raw prompts, outputs, ## Recent Metadata Events -- `2026-06-13T12:00:00Z` `yao-meta-skill` event=`review_event` source=`manual` command=`unknown` activation=`manual` outcome=`reviewed` failure=`none` +- `2026-06-13T10:00:00Z` `yao-meta-skill` event=`skill_activation` source=`manual` command=`unknown` activation=`explicit` outcome=`accepted` failure=`none` diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 112742d9..ca779cc8 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -1,14 +1,14 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { - "python_file_count": 146, - "script_file_count": 90, + "python_file_count": 147, + "script_file_count": 91, "test_file_count": 56, "internal_module_count": 19, - "cli_script_count": 72, + "cli_script_count": 73, "command_handler_count": 33, "warn_line_threshold": 900, "block_line_threshold": 1500, @@ -27,14 +27,14 @@ }, { "path": "tests/verify_yao_cli.py", - "lines": 850, + "lines": 871, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, { "path": "scripts/yao.py", - "lines": 839, + "lines": 840, "kind": "cli-script", "severity": "pass", "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator." @@ -69,7 +69,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 692, + "lines": 703, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index fba3b0ed..9b9540ec 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -1,15 +1,15 @@ # Architecture Maintainability -Generated at: `2026-06-14` +Generated at: `2026-06-13` ## Summary - decision: `pass` -- python files: `146` -- scripts: `90` +- python files: `147` +- scripts: `91` - tests: `56` - internal modules: `19` -- CLI scripts: `72` +- CLI scripts: `73` - Yao CLI command handlers: `33` - largest file lines: `899` - hotspots: `0` @@ -26,13 +26,13 @@ No file-size hotspots found. | File | Lines | Kind | Severity | | --- | ---: | --- | --- | | `scripts/render_review_studio.py` | `899` | `cli-script` | `pass` | -| `tests/verify_yao_cli.py` | `850` | `test` | `pass` | -| `scripts/yao.py` | `839` | `cli-script` | `pass` | +| `tests/verify_yao_cli.py` | `871` | `test` | `pass` | +| `scripts/yao.py` | `840` | `cli-script` | `pass` | | `scripts/skill_report_model.py` | `782` | `internal-module` | `pass` | | `scripts/compile_skill.py` | `734` | `cli-script` | `pass` | | `scripts/optimize_description.py` | `723` | `cli-script` | `pass` | | `scripts/trust_check.py` | `714` | `internal-module` | `pass` | -| `scripts/yao_cli_parser.py` | `692` | `internal-module` | `pass` | +| `scripts/yao_cli_parser.py` | `703` | `internal-module` | `pass` | | `scripts/render_review_viewer.py` | `685` | `cli-script` | `pass` | | `scripts/build_skill_atlas.py` | `674` | `cli-script` | `pass` | | `scripts/skill_report_layout.py` | `653` | `internal-module` | `pass` | diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 4987604d..02ae36b5 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,12 +3,15 @@ "ok": true, "generated_at": "2026-06-14", "skill_dir": ".", - "commit": "c5e7b05faae8536b420c5120c1d3a59456c96e51", + "commit": "b540f580b373cb9c0f575b687fb82c5a16748a5d", "git_status": { "available": true, "dirty": true, - "changed_file_count": 30, + "changed_file_count": 48, "sample": [ + " M .gitignore", + " M README.md", + " M evidence/world_class/README.md", " M registry/index.json", " M registry/packages/yao-meta-skill.json", " M reports/adoption_drift_report.json", @@ -16,11 +19,8 @@ " M reports/architecture_maintainability.md", " M reports/benchmark_reproducibility.json", " M reports/benchmark_reproducibility.md", - " M reports/context_budget.json", - " M reports/output_execution_runs.json", - " M reports/output_execution_runs.md", - " M reports/package_verification.json", - " M reports/package_verification.md" + " M reports/compiled_targets.json", + " M reports/context_budget.json" ] }, "summary": { @@ -42,7 +42,7 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 48 }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -115,8 +115,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7965, - "sha256": "917751088ebd5af0581461f73cf28c4b192a91bb1352d7c981b2e3bdb12ce48f" + "bytes": 7966, + "sha256": "9456b0729b322d3f9fdf6f0929c0010d649df94eccc9597f4e0f67115dc8ea1b" }, { "label": "blind_review", @@ -150,43 +150,43 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 92549, - "sha256": "5680f911b5b589d63c8e83ef2c2edabdff004d6634bc6d475f2efd76256071ab" + "bytes": 93677, + "sha256": "2aa9f4b0a7e2ca36d7f8e87e76bbc224bb23f9962f86d2c0f2b3cefd7deca221" }, { "label": "python_compatibility", "path": "reports/python_compatibility.json", "exists": true, - "bytes": 19427, - "sha256": "809d07d66de33719b160b1a20d3bc86c546b3a69051cc662c840e5d16e10f5b8" + "bytes": 19564, + "sha256": "bbab01ebaa5b6986b0a3bfcf9825b15efdea5b98377a126fb0708e9fa67d2acb" }, { "label": "registry_audit", "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9934a175c3db29c7e2d182cdd68aa3b04da28d0dff7606c98dc8bc5cb209425b" + "sha256": "69f9f9f4663e291275c0c50caa86aac68d2579f9e02abf3f6dc9e03b64a77557" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19325, - "sha256": "51a8e785a233726c2988004db5437c5678e58ed36f4b5ab312942245e385cf11" + "sha256": "c8ab851a6f715e866a7b5fca04de075692027d77bc81d4d68e425c5d2dd2a7de" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, - "bytes": 8557, - "sha256": "5e6e501706588c0eb431d71af38c4789c40991acca4531f667acb6a0610a70c3" + "bytes": 8758, + "sha256": "a88a496f58a591e3f81f552347de64e56dd9269bb775121e6bf0fafab795707f" }, { "label": "skill_os2_audit", "path": "reports/skill_os2_audit.json", "exists": true, "bytes": 13946, - "sha256": "ed1be043898a5550be37c93b3d8723dbaf2d537af3005a8a6476ec6d0d266318" + "sha256": "91945bad2dcd8f6a165b1c896932a61ee64f43bfc9cca2091f3a921ef7817c0c" }, { "label": "world_class_evidence_plan", @@ -206,8 +206,8 @@ "label": "world_class_evidence_intake", "path": "reports/world_class_evidence_intake.json", "exists": true, - "bytes": 12523, - "sha256": "6eae947a6e2f3721a8c616b58795554fe6cd778be62c6e6c34833563582a505d" + "bytes": 12369, + "sha256": "465f8d915a869ad536c2d71ba26dc536b82ba64e6e98013e8dbd0efd1bb92883" }, { "label": "world_class_claim_guard", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index fc7334e4..76ac7179 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,7 +1,7 @@ # Benchmark Reproducibility Generated at: `2026-06-14` -Commit: `c5e7b05faae8536b420c5120c1d3a59456c96e51` +Commit: `b540f580b373cb9c0f575b687fb82c5a16748a5d` Working tree dirty at generation: `true` ## Summary @@ -16,7 +16,7 @@ Working tree dirty at generation: `true` - provider evidence complete: `false` - human review complete: `false` - world-class ready: `false` -- changed files at generation: `30` +- changed files at generation: `48` This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. @@ -40,20 +40,20 @@ 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 | `917751088ebd` | +| output_execution | `reports/output_execution_runs.json` | present | `9456b0729b32` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `5765254c4309` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` | -| trust_report | `reports/security_trust_report.json` | present | `5680f911b5b5` | -| python_compatibility | `reports/python_compatibility.json` | present | `809d07d66de3` | -| registry_audit | `reports/registry_audit.json` | present | `9934a175c3db` | -| package_verification | `reports/package_verification.json` | present | `51a8e785a233` | -| install_simulation | `reports/install_simulation.json` | present | `5e6e50170658` | -| skill_os2_audit | `reports/skill_os2_audit.json` | present | `ed1be043898a` | +| trust_report | `reports/security_trust_report.json` | present | `2aa9f4b0a7e2` | +| python_compatibility | `reports/python_compatibility.json` | present | `bbab01ebaa5b` | +| registry_audit | `reports/registry_audit.json` | present | `69f9f9f4663e` | +| package_verification | `reports/package_verification.json` | present | `c8ab851a6f71` | +| install_simulation | `reports/install_simulation.json` | present | `a88a496f58a5` | +| skill_os2_audit | `reports/skill_os2_audit.json` | present | `91945bad2dcd` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `ed1274b7c18c` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `e6dfdb22dc9f` | -| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `6eae947a6e2f` | +| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `465f8d915a86` | | world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `608c954d1af9` | ## Reproduction Commands diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 5d67f6ff..32468651 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -1,7 +1,7 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "target_count": 5, @@ -166,6 +166,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -223,8 +224,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -383,7 +383,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -399,6 +399,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -483,14 +484,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -512,7 +513,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -625,7 +626,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -641,6 +642,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -725,14 +727,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -752,7 +754,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -1007,6 +1009,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -1064,8 +1067,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -1224,7 +1226,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1240,6 +1242,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -1324,14 +1327,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1353,7 +1356,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -1466,7 +1469,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -1482,6 +1485,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -1566,14 +1570,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1593,7 +1597,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -1848,6 +1852,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -1905,8 +1910,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -2065,7 +2069,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2081,6 +2085,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -2165,14 +2170,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2194,7 +2199,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -2300,7 +2305,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2316,6 +2321,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -2400,14 +2406,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2427,7 +2433,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -2673,6 +2679,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -2730,8 +2737,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -2890,7 +2896,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -2906,6 +2912,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -2990,14 +2997,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3019,7 +3026,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -3125,7 +3132,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3141,6 +3148,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -3225,14 +3233,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3252,7 +3260,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -3498,6 +3506,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -3555,8 +3564,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -3715,7 +3723,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3731,6 +3739,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -3815,14 +3824,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3844,7 +3853,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -3954,7 +3963,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -3970,6 +3979,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -4054,14 +4064,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4081,7 +4091,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, diff --git a/reports/context_budget.json b/reports/context_budget.json index 82da791d..af17c449 100644 --- a/reports/context_budget.json +++ b/reports/context_budget.json @@ -6,10 +6,10 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 1113302, + "other_text_tokens": 1117887, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 1114053, - "relevant_file_count": 479, + "estimated_total_text_tokens": 1118638, + "relevant_file_count": 480, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 137.7 diff --git a/reports/install_simulation.json b/reports/install_simulation.json index 67ca2c32..bed46a8e 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -1,14 +1,14 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", - "package_dir": "dist", - "install_root": "[temporary-install-root]", - "installed_skill_dir": "[temporary-install-root]/yao-meta-skill", + "package_dir": "tests/tmp_review_studio/dist", + "install_root": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill", + "installed_skill_dir": "tests/tmp_review_studio/install-root/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 558, + "archive_entry_count": 559, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -18,7 +18,7 @@ "installer_permission_failure_count": 0, "permission_target_count": 4, "permission_capability_count": 3, - "install_root_is_temp": true, + "install_root_is_temp": false, "failure_count": 0, "warning_count": 0 }, @@ -26,7 +26,7 @@ { "id": "archive-present", "status": "pass", - "detail": "Package archive exists: dist/yao-meta-skill.zip" + "detail": "Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip" }, { "id": "archive-safe-paths", @@ -272,9 +272,9 @@ "failures": [], "warnings": [], "artifacts": { - "archive": "dist/yao-meta-skill.zip", - "package_manifest": "dist/manifest.json", - "json": "reports/install_simulation.json", - "markdown": "reports/install_simulation.md" + "archive": "tests/tmp_review_studio/dist/yao-meta-skill.zip", + "package_manifest": "tests/tmp_review_studio/dist/manifest.json", + "json": "tests/tmp_review_studio/install_simulation.json", + "markdown": "tests/tmp_review_studio/install_simulation.md" } } diff --git a/reports/install_simulation.md b/reports/install_simulation.md index 6750e007..b0d16dae 100644 --- a/reports/install_simulation.md +++ b/reports/install_simulation.md @@ -1,7 +1,7 @@ # Install Simulation - OK: `True` -- Package directory: `dist` +- Package directory: `tests/tmp_review_studio/dist` - Archive extracted: `True` - Entrypoint loaded: `True` - Manifest loaded: `True` @@ -16,7 +16,7 @@ | Check | Status | Detail | | --- | --- | --- | -| `archive-present` | `pass` | Package archive exists: dist/yao-meta-skill.zip | +| `archive-present` | `pass` | Package archive exists: tests/tmp_review_studio/dist/yao-meta-skill.zip | | `archive-safe-paths` | `pass` | Archive has no absolute or parent-traversal entries | | `single-top-level` | `pass` | Archive top-level directory is yao-meta-skill | | `entrypoint-load` | `pass` | Installed SKILL.md frontmatter is readable | diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 916d1145..3b13f25b 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": 29.8, + "duration_ms": 32.47, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.94, + "duration_ms": 33.17, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.0, + "duration_ms": 32.51, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 39.86, + "duration_ms": 31.11, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.86, + "duration_ms": 32.82, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.43, + "duration_ms": 29.65, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.14, + "duration_ms": 27.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.46, + "duration_ms": 28.12, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -237,7 +237,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.25, + "duration_ms": 28.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.63, + "duration_ms": 28.07, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index 6f176b24..f1aee64f 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 | 29.8 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 28.94 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 29.0 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 39.86 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 32.86 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.43 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 30.14 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 29.46 | 65 | 100.0 | pass | -| file-backed-governed-package | baseline | command | local-output-eval-runner | 31.25 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 29.63 | 98 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 32.47 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 33.17 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 32.51 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.11 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 32.82 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 29.65 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.97 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.12 | 65 | 100.0 | pass | +| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.34 | 37 | 0.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.07 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 6a72c521..41a7d3dd 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": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", - "archive_entry_count": 558, + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", + "archive_entry_count": 559, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index 37e11571..4e3d0424 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: `934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d` +- Archive SHA256: `fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index b1c9b327..0f566454 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -1,11 +1,11 @@ { "schema_version": "1.0", "ok": true, - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "root": ".", "summary": { "target_python": "3.11", - "file_count": 149, + "file_count": 150, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -166,6 +166,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/probe_runtime_permissions.py", "ok": true, diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index 38fb4b1a..b64a2501 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -1,12 +1,12 @@ # Python Compatibility -Generated at: `2026-06-14` +Generated at: `2026-06-13` ## Summary - decision: `pass` - target python: `3.11` -- files scanned: `149` +- files scanned: `150` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 843bba40..79cc0a3d 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9", - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "package_sha256": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, "compatibility": { "openai": "pass", @@ -53,16 +53,16 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" }, - "generated_at": "2026-06-14" + "generated_at": "2026-06-13" }, "index": { "schema_version": "2.0", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "package_count": 1, "packages": [ { @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_sha256": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index 40ffcd14..7cc916c0 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9` -- Archive SHA256: `934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d` +- Package SHA256: `4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75` +- Archive SHA256: `fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e` - Install simulated: `True` ## Compatibility diff --git a/reports/review-studio.html b/reports/review-studio.html index a54b1087..1e71e484 100644 --- a/reports/review-studio.html +++ b/reports/review-studio.html @@ -434,12 +434,12 @@

核心指标

-
Skill IR2.0.0

5 targets in platform-neutral contract

Compiler5/5

target contracts compiled from Skill IR

Output Delta100.0

5 cases; 1 file-backed

Exec Runs10

command 10; model 0; recorded 0

Blind A/B5

review pairs hide baseline vs with-skill labels

Review A/B0/5

adjudication decisions; pending 5

Blueprint20/20

2.0 coverage; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native enforcement targets

Trust0

90 scripts scanned; secrets found

Py Compat0

149 files scanned for Python 3.11

Arch Debt0

899 largest lines; 33 CLI handlers

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

68 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

558 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 A/B0/5

adjudication decisions; pending 5

Blueprint20/20

2.0 coverage; evidence pending 4

Runtime5/5

target conformance pass rate

Perm Probe4/4

0 native enforcement targets

Trust0

91 scripts scanned; secrets found

Py Compat0

150 files scanned for Python 3.11

Arch Debt0

899 largest lines; 33 CLI handlers

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

68 public surfaces scanned

Notes0/0

0 open blocker annotations

Registry1.1.0

5 targets; MIT license

Archivepass

559 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 944/1000; quality density 137.7

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; 90 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 149 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

146 Python files; 0 hotspots; 0 blockers; largest 899 lines; 33 CLI handlers

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; 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; 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 944/1000; quality density 137.7

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; 91 scripts; 3 network-capable scripts; 0 help smoke failures

reports/security_trust_report.json 证据
通过

Python 兼容

Python 3.11; 150 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards

reports/python_compatibility.json 证据
通过

架构维护

147 Python files; 0 hotspots; 0 blockers; largest 899 lines; 33 CLI handlers

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; 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; 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

@@ -506,12 +506,12 @@
-

信任报告

Secret
0
脚本数
90
网络脚本
3
Help 失败
0
包体哈希
0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9
+

信任报告

Secret
0
脚本数
91
网络脚本
3
Help 失败
0
包体哈希
d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac

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
149
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
150
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。

@@ -531,8 +531,8 @@
-

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
+

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
@@ -543,13 +543,13 @@

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

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.
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

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_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.
待补证 · external

Native Permission Enforcement

Prove at least one target or installer enforces approved high-permission capabilities at runtime.

负责人
target client or installer integrator
当前状态
native-enforced targets 0
下一步
Integrate a real client or installer runtime guard before claiming native permission enforcement.
观测值
native_enforcement_count: 0; metadata_fallback_count: 4; 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

完成定义

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • 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
  • 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.
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

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.
+
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

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.
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

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_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.
待补证 · external

Native Permission Enforcement

Prove at least one target or installer enforces approved high-permission capabilities at runtime.

负责人
target client or installer integrator
当前状态
native-enforced targets 0
下一步
Integrate a real client or installer runtime guard before claiming native permission enforcement.
观测值
native_enforcement_count: 0; metadata_fallback_count: 4; 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

完成定义

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • 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
  • 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.
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

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.

提交清单

每张卡片给出模板、提交文件、准备命令、校验命令、收集要求、通过条件和隐私边界；只有真实 provider、真人、原生权限或真实客户端证据通过 intake 后，才进入 ledger review。

-
awaiting-submission · external

Provider Holdout

No real evidence submission has been provided yet.

负责人
operator with provider credentials
模板
evidence/world_class/templates/provider-holdout.intake.json
提交
evidence/world_class/submissions/provider-holdout.json
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.

操作命令

  • prepare_submissionmkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/provider-holdout.intake.json evidence/world_class/submissions/provider-holdout.json
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • provider-backed model run
  • observed timing
  • observed token metadata

通过条件

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

隐私边界

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

Human Adjudication

No real evidence submission has been provided yet.

负责人
human reviewer
模板
evidence/world_class/templates/human-adjudication.intake.json
提交
evidence/world_class/submissions/human-adjudication.json
下一步
Record real A/B choices in the decision template, then regenerate adjudication.

操作命令

  • prepare_submissionmkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/human-adjudication.intake.json evidence/world_class/submissions/human-adjudication.json
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist

通过条件

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

隐私边界

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

Native Permission Enforcement

No real evidence submission has been provided yet.

负责人
target client or installer integrator
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
提交
evidence/world_class/submissions/native-permission-enforcement.json
下一步
Integrate a real client or installer runtime guard before claiming native permission enforcement.

操作命令

  • prepare_submissionmkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-permission-enforcement.intake.json evidence/world_class/submissions/native-permission-enforcement.json
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real target or installer guard
  • native enforcement flag
  • residual risk retained for fallback targets

通过条件

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass

隐私边界

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

Native Client Telemetry

No real evidence submission has been provided yet.

负责人
Browser/Chrome/IDE/provider client integrator
模板
evidence/world_class/templates/native-client-telemetry.intake.json
提交
evidence/world_class/submissions/native-client-telemetry.json
下一步
Install a real client against the native host and import production metadata-only events.

操作命令

  • prepare_submissionmkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-client-telemetry.intake.json evidence/world_class/submissions/native-client-telemetry.json
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real external client source
  • metadata-only event
  • local-first import path

通过条件

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

隐私边界

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

Provider Holdout

No real evidence submission has been provided yet.

负责人
operator with provider credentials
模板
evidence/world_class/templates/provider-holdout.intake.json
提交
evidence/world_class/submissions/provider-holdout.json
下一步
Run provider-backed holdout cases with real credentials and commit only aggregate evidence.

操作命令

  • prepare_submissionpython3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • provider-backed model run
  • observed timing
  • observed token metadata

通过条件

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

隐私边界

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

Human Adjudication

No real evidence submission has been provided yet.

负责人
human reviewer
模板
evidence/world_class/templates/human-adjudication.intake.json
提交
evidence/world_class/submissions/human-adjudication.json
下一步
Record real A/B choices in the decision template, then regenerate adjudication.

操作命令

  • prepare_submissionpython3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real reviewer identity
  • blind A/B decisions
  • answer key unopened until decisions exist

通过条件

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

隐私边界

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

Native Permission Enforcement

No real evidence submission has been provided yet.

负责人
target client or installer integrator
模板
evidence/world_class/templates/native-permission-enforcement.intake.json
提交
evidence/world_class/submissions/native-permission-enforcement.json
下一步
Integrate a real client or installer runtime guard before claiming native permission enforcement.

操作命令

  • prepare_submissionpython3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real target or installer guard
  • native enforcement flag
  • residual risk retained for fallback targets

通过条件

  • reports/runtime_permission_probes.json summary.native_enforcement_count > 0
  • reports/runtime_permission_probes.json summary.failure_count == 0
  • reports/skill_os2_audit.json item native-permission-enforcement status becomes pass

隐私边界

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

Native Client Telemetry

No real evidence submission has been provided yet.

负责人
Browser/Chrome/IDE/provider client integrator
模板
evidence/world_class/templates/native-client-telemetry.intake.json
提交
evidence/world_class/submissions/native-client-telemetry.json
下一步
Install a real client against the native host and import production metadata-only events.

操作命令

  • prepare_submissionpython3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions
  • validate_intakepython3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions
  • refresh_ledgerpython3 scripts/yao.py world-class-ledger .
  • guard_claimpython3 scripts/yao.py world-class-claim-guard .

收集要求

  • real external client source
  • metadata-only event
  • local-first import path

通过条件

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

隐私边界

  • Telemetry must remain metadata-only and local-first.
  • Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field.
@@ -574,12 +574,12 @@

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
934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d
+

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
fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e

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
558
失败数
0
警告数
0
归档哈希
934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d
+

包体验证

目标数
4
Adapter
4
归档存在
是
Zip 条目
559
失败数
0
警告数
0
归档哈希
fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e
diff --git a/reports/review-studio.json b/reports/review-studio.json index a4de8b91..2d8a527b 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -59,7 +59,7 @@ "key": "trust-report", "label": "信任报告", "status": "pass", - "detail": "0 secrets; 90 scripts; 3 network-capable scripts; 0 help smoke failures", + "detail": "0 secrets; 91 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; 149 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards", + "detail": "Python 3.11; 150 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": "146 Python files; 0 hotspots; 0 blockers; largest 899 lines; 33 CLI handlers", + "detail": "147 Python files; 0 hotspots; 0 blockers; largest 899 lines; 33 CLI handlers", "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 0; missed 0; bad-output 0; risk low", + "detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low", "evidence": "reports/adoption_drift_report.json", "link": "adoption_drift_report.md" }, @@ -837,7 +837,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 90 + "file_count": 91 }, { "path": "evals", @@ -852,7 +852,7 @@ "file_count": 195 } ], - "file_count": 349, + "file_count": 350, "folder_count": 4, "distribution": [ { @@ -877,7 +877,7 @@ }, { "label": "scripts", - "value": 90 + "value": 91 }, { "label": "evals", @@ -1006,7 +1006,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 90 + "file_count": 91 }, { "path": "evals", @@ -1310,9 +1310,9 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 54 }, - "commit": "c5e7b05faae8536b420c5120c1d3a59456c96e51", + "commit": "b540f580b373cb9c0f575b687fb82c5a16748a5d", "missing_artifacts": [], "limitations": [ "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.", @@ -1387,8 +1387,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 174, - "script_count": 90, + "scanned_files": 175, + "script_count": 91, "internal_module_count": 17, "secret_findings": 0, "dependency_files": [ @@ -1397,18 +1397,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 60, + "file_write_script_count": 61, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 73, + "help_smoke_checked_count": 74, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 174, - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_hash_file_count": 175, + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" }, "skill_atlas": { "skill_count": 12, @@ -1446,8 +1446,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9", - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, "compatibility": { "openai": "pass", @@ -1478,7 +1478,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1494,8 +1494,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", - "archive_entry_count": 558, + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", + "archive_entry_count": 559, "failure_count": 0, "warning_count": 0 }, @@ -1506,7 +1506,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 558, + "archive_entry_count": 559, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1516,7 +1516,7 @@ "installer_permission_failure_count": 0, "permission_target_count": 4, "permission_capability_count": 3, - "install_root_is_temp": true, + "install_root_is_temp": false, "failure_count": 0, "warning_count": 0 }, @@ -1573,12 +1573,12 @@ { "field": "archive_sha256", "from": "", - "to": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "to": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "to": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" } ] }, @@ -1595,14 +1595,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1611,7 +1611,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1824,7 +1824,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -2056,7 +2056,7 @@ "owner": "Browser/Chrome/IDE/provider client integrator", "status": "pending", "source_status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "provenance_requirements": [ "real external client source", @@ -2084,7 +2084,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -3734,7 +3734,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.8, + "duration_ms": 26.92, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3762,7 +3762,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 28.94, + "duration_ms": 26.93, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3785,7 +3785,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.0, + "duration_ms": 26.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3813,7 +3813,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 39.86, + "duration_ms": 29.94, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3836,7 +3836,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 32.86, + "duration_ms": 27.93, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3864,7 +3864,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.43, + "duration_ms": 26.69, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3887,7 +3887,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 30.14, + "duration_ms": 26.79, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3914,7 +3914,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.46, + "duration_ms": 27.09, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3937,7 +3937,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 31.25, + "duration_ms": 26.97, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -3966,7 +3966,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 29.63, + "duration_ms": 26.84, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -4533,7 +4533,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "90 scripts; secrets 0; help failures 0", + "current": "91 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -4607,7 +4607,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 558; install failures 0", + "current": "archive entries 559; 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": [ @@ -5193,6 +5193,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -5250,8 +5251,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -5410,7 +5410,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -5426,6 +5426,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -5510,14 +5511,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -5539,7 +5540,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -5652,7 +5653,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -5668,6 +5669,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -5752,14 +5754,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -5779,7 +5781,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -6034,6 +6036,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -6091,8 +6094,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -6251,7 +6253,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -6267,6 +6269,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -6351,14 +6354,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -6380,7 +6383,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -6493,7 +6496,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -6509,6 +6512,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -6593,14 +6597,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -6620,7 +6624,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -6875,6 +6879,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -6932,8 +6937,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -7092,7 +7096,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -7108,6 +7112,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -7192,14 +7197,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -7221,7 +7226,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -7327,7 +7332,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -7343,6 +7348,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -7427,14 +7433,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -7454,7 +7460,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -7700,6 +7706,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -7757,8 +7764,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -7917,7 +7923,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -7933,6 +7939,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -8017,14 +8024,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -8046,7 +8053,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -8152,7 +8159,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -8168,6 +8175,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -8252,14 +8260,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -8279,7 +8287,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -8525,6 +8533,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -8582,8 +8591,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", @@ -8742,7 +8750,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -8758,6 +8766,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -8842,14 +8851,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -8871,7 +8880,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -8981,7 +8990,7 @@ }, "file_write": { "required": true, - "script_count": 60, + "script_count": 61, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/build_confusion_matrix.py", @@ -8997,6 +9006,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -9081,14 +9091,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 73, + "checked_count": 74, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 60, + "file_write_script_count": 61, "subprocess_script_count": 9, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -9108,7 +9118,7 @@ ], "capability_counts": { "network": 3, - "file_write": 60, + "file_write": 61, "subprocess": 9, "interactive": 0 }, @@ -9457,7 +9467,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "package_dir": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -9477,7 +9487,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -9562,7 +9572,7 @@ { "target": "claude", "status": "pass", - "adapter": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -9632,7 +9642,7 @@ { "target": "generic", "status": "pass", - "adapter": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -9702,7 +9712,7 @@ { "target": "vscode", "status": "pass", - "adapter": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -9780,8 +9790,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 174, - "script_count": 90, + "scanned_files": 175, + "script_count": 91, "internal_module_count": 17, "secret_findings": 0, "dependency_files": [ @@ -9790,18 +9800,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 60, + "file_write_script_count": 61, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 73, + "help_smoke_checked_count": 74, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 174, - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_hash_file_count": 175, + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" }, "failures": [], "warnings": [], @@ -10110,6 +10120,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Prepares editable world-class evidence intake packets without counting drafts as accepted evidence.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/probe_runtime_permissions.py", "interface": "cli", @@ -11115,9 +11139,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 73, - "checked_count": 73, - "passed_count": 73, + "candidate_count": 74, + "checked_count": 74, + "passed_count": 74, "failed_count": 0, "skipped_count": 17, "failed_scripts": [], @@ -11332,6 +11356,16 @@ "stdout_excerpt": "usage: optimize_description.py [-h] --description-file DESCRIPTION_FILE\n [--baseline-description-file BASELINE_DESCRIPTION_FILE]\n --dev-cases DEV_CASES\n ", "stderr_excerpt": "" }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "command": "python3 scripts/prepare_world_class_submission_kit.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: prepare_world_class_submission_kit.py [-h] [--output-dir OUTPUT_DIR]\n [--evidence-key EVIDENCE_KEY]\n [--overwrite]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/probe_runtime_permissions.py", "command": "python3 scripts/probe_runtime_permissions.py --help", @@ -11990,6 +12024,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", @@ -12103,7 +12138,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 149, + "file_count": 150, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -12264,6 +12299,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/probe_runtime_permissions.py", "ok": true, @@ -13027,11 +13068,11 @@ "generated_at": "2026-06-14", "skill_dir": ".", "summary": { - "python_file_count": 146, - "script_file_count": 90, + "python_file_count": 147, + "script_file_count": 91, "test_file_count": 56, "internal_module_count": 19, - "cli_script_count": 72, + "cli_script_count": 73, "command_handler_count": 33, "warn_line_threshold": 900, "block_line_threshold": 1500, @@ -13050,14 +13091,14 @@ }, { "path": "tests/verify_yao_cli.py", - "lines": 850, + "lines": 871, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." }, { "path": "scripts/yao.py", - "lines": 839, + "lines": 840, "kind": "cli-script", "severity": "pass", "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator." @@ -13092,7 +13133,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 692, + "lines": 703, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -13141,10 +13182,10 @@ "context_budget_tier": "production", "context_budget_limit": 1000, "skill_body_tokens": 751, - "other_text_tokens": 1113302, + "other_text_tokens": 1117410, "estimated_initial_load_tokens": 944, - "estimated_total_text_tokens": 1114053, - "relevant_file_count": 479, + "estimated_total_text_tokens": 1118161, + "relevant_file_count": 480, "unused_resource_dirs": [], "quality_signal_points": 130, "quality_density": 137.7 @@ -13988,7 +14029,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -14029,6 +14070,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -14161,8 +14203,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, @@ -14825,7 +14867,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 75, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" @@ -14993,7 +15035,7 @@ "adoption_drift": { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-13T22:00:20Z", + "generated_at": "2026-06-13T22:14:54Z", "skill_dir": ".", "privacy_contract": { "storage": "local-first", @@ -15017,14 +15059,14 @@ }, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -15033,7 +15075,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -15045,31 +15087,31 @@ { "skill": "yao-meta-skill", "events": 1, - "adoption_events": 0, - "accepted": 0, + "adoption_events": 1, + "accepted": 1, "edited": 0, "rejected": 0, "missed": 0, - "adoption_rate": 0 + "adoption_rate": 100.0 } ], "next_iteration_candidates": [], "recent_events": [ { "command": "unknown", - "event": "review_event", + "event": "skill_activation", "skill": "yao-meta-skill", "source": "manual", "version": "1.1.0", - "activation_type": "manual", - "outcome": "reviewed", + "activation_type": "explicit", + "outcome": "accepted", "failure_type": "none", - "timestamp": "2026-06-13T12:00:00Z" + "timestamp": "2026-06-13T10:00:00Z" } ], "failures": [], "artifacts": { - "events_jsonl": "reports/telemetry_events.jsonl", + "events_jsonl": "tests/tmp_review_studio/telemetry_events.jsonl", "json": "reports/adoption_drift_report.json", "markdown": "reports/adoption_drift_report.md" } @@ -15078,7 +15120,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -15128,7 +15170,7 @@ "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 2027-06-14 --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", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { @@ -15158,7 +15200,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, @@ -15374,7 +15416,7 @@ "owner": "Browser/Chrome/IDE/provider client integrator", "status": "pending", "source_status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "provenance_requirements": [ "real external client source", @@ -15402,7 +15444,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false @@ -15505,7 +15547,7 @@ "template_path": "evidence/world_class/templates/provider-holdout.intake.json", "submission_path": "evidence/world_class/submissions/provider-holdout.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/provider-holdout.intake.json evidence/world_class/submissions/provider-holdout.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -15556,7 +15598,7 @@ "template_path": "evidence/world_class/templates/human-adjudication.intake.json", "submission_path": "evidence/world_class/submissions/human-adjudication.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/human-adjudication.intake.json evidence/world_class/submissions/human-adjudication.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -15608,7 +15650,7 @@ "template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json", "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-permission-enforcement.intake.json evidence/world_class/submissions/native-permission-enforcement.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -15659,7 +15701,7 @@ "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json", "submission_path": "evidence/world_class/submissions/native-client-telemetry.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-client-telemetry.intake.json evidence/world_class/submissions/native-client-telemetry.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -16056,8 +16098,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9", - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, "compatibility": { "openai": "pass", @@ -16088,7 +16130,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -16113,7 +16155,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" } ] }, @@ -16136,8 +16178,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", - "archive_entry_count": 558, + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", + "archive_entry_count": 559, "failure_count": 0, "warning_count": 0 }, @@ -16798,11 +16840,11 @@ "generated_at": "2026-06-14", "skill_dir": ".", "package_dir": "dist", - "install_root": "[temporary-install-root]", - "installed_skill_dir": "[temporary-install-root]/yao-meta-skill", + "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": 558, + "archive_entry_count": 559, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -16812,7 +16854,7 @@ "installer_permission_failure_count": 0, "permission_target_count": 4, "permission_capability_count": 3, - "install_root_is_temp": true, + "install_root_is_temp": false, "failure_count": 0, "warning_count": 0 }, @@ -17144,12 +17186,12 @@ { "field": "archive_sha256", "from": "", - "to": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "to": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "to": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" } ] }, diff --git a/reports/review_annotations.json b/reports/review_annotations.json index 76fadc1f..66f2b1d9 100644 --- a/reports/review_annotations.json +++ b/reports/review_annotations.json @@ -2,7 +2,7 @@ "schema_version": "1.0", "ok": true, "skill_dir": ".", - "source": "reports/review_annotations_input.json", + "source": "tests/tmp_review_studio/empty_review_annotations_input.json", "summary": { "annotation_count": 0, "open_count": 0, diff --git a/reports/review_waivers.json b/reports/review_waivers.json index 0071c002..5f4a2e69 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": "2026-06-14", + "generated_at": "2026-06-13", "summary": { "waiver_count": 0, "active_count": 0, @@ -52,7 +52,7 @@ "Reviewer links output_review_adjudication or output_execution evidence." ], "suggested_evidence": "reports/output_review_adjudication.md", - "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-14 --evidence reports/output_review_adjudication.md", + "suggested_command": "python3 scripts/yao.py review-waivers . --add-waiver --gate-key output-lab --reviewer \"\" --reason \"Output Lab has pending human/provider evidence; accepted only for this bounded review scope.\" --expires-at 2027-06-13 --evidence reports/output_review_adjudication.md", "world_class_boundary": "Does not count as provider, human, or public world-class completion evidence." }, { diff --git a/reports/review_waivers.md b/reports/review_waivers.md index a29aeeca..06b59140 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 2027-06-14 --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` - 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 a989e325..6d6254fb 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": "dist", + "package_dir": "tests/tmp_review_studio/dist", "expected_capabilities": [ "file_write", "network", @@ -22,7 +22,7 @@ { "target": "openai", "status": "pass", - "adapter": "dist/targets/openai/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/openai/adapter.json", "permission_model": "metadata-only", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -107,7 +107,7 @@ { "target": "claude", "status": "pass", - "adapter": "dist/targets/claude/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/claude/adapter.json", "permission_model": "neutral-source-plus-adapter", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -177,7 +177,7 @@ { "target": "generic", "status": "pass", - "adapter": "dist/targets/generic/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/generic/adapter.json", "permission_model": "agent-skills-compatible-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, @@ -247,7 +247,7 @@ { "target": "vscode", "status": "pass", - "adapter": "dist/targets/vscode/adapter.json", + "adapter": "tests/tmp_review_studio/dist/targets/vscode/adapter.json", "permission_model": "vscode-workspace-trust-plus-metadata", "native_enforcement": false, "metadata_fallback_explicit": true, diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 4ca3c3f0..bce90a7b 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,8 +2,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 174, - "script_count": 90, + "scanned_files": 175, + "script_count": 91, "internal_module_count": 17, "secret_findings": 0, "dependency_files": [ @@ -12,18 +12,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 60, + "file_write_script_count": 61, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 73, + "help_smoke_checked_count": 74, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 174, - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_hash_file_count": 175, + "package_sha256": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75" }, "failures": [], "warnings": [], @@ -332,6 +332,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Prepares editable world-class evidence intake packets without counting drafts as accepted evidence.", + "has_argparse": true, + "has_main_guard": true, + "uses_input": false, + "uses_network": false, + "uses_file_write": true, + "uses_subprocess": false, + "network_urls": [], + "network_hosts": [] + }, { "path": "scripts/probe_runtime_permissions.py", "interface": "cli", @@ -1337,9 +1351,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 73, - "checked_count": 73, - "passed_count": 73, + "candidate_count": 74, + "checked_count": 74, + "passed_count": 74, "failed_count": 0, "skipped_count": 17, "failed_scripts": [], @@ -1554,6 +1568,16 @@ "stdout_excerpt": "usage: optimize_description.py [-h] --description-file DESCRIPTION_FILE\n [--baseline-description-file BASELINE_DESCRIPTION_FILE]\n --dev-cases DEV_CASES\n ", "stderr_excerpt": "" }, + { + "path": "scripts/prepare_world_class_submission_kit.py", + "command": "python3 scripts/prepare_world_class_submission_kit.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: prepare_world_class_submission_kit.py [-h] [--output-dir OUTPUT_DIR]\n [--evidence-key EVIDENCE_KEY]\n [--overwrite]\n ", + "stderr_excerpt": "" + }, { "path": "scripts/probe_runtime_permissions.py", "command": "python3 scripts/probe_runtime_permissions.py --help", @@ -2212,6 +2236,7 @@ "scripts/github_benchmark_scan.py", "scripts/import_telemetry_events.py", "scripts/init_skill.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/python_compat_check.py", diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index 08b4b4e4..ee983991 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,22 +1,22 @@ # Security Trust Report - OK: `True` -- Scanned files: `174` -- Scripts: `90` +- Scanned files: `175` +- Scripts: `91` - Internal script modules: `17` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` - Network policy missing scripts: `0` -- File-write scripts: `60` +- File-write scripts: `61` - Permission approvals: `3 / 3` - Permission approval gaps: `0` -- CLI help smoke checked: `73` +- CLI help smoke checked: `74` - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `174` -- Package SHA256: `0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9` +- Package hash files: `175` +- Package SHA256: `4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75` ## Failures @@ -54,8 +54,8 @@ - Enabled: `True` - Timeout seconds: `5.0` -- Checked scripts: `73` -- Passed scripts: `73` +- Checked scripts: `74` +- Passed scripts: `74` - Failed scripts: `none` ## Script Surface @@ -83,6 +83,7 @@ | scripts/lint_skill.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/local_output_eval_runner.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/optimize_description.py | cli | False | True | True | False | False | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | +| scripts/prepare_world_class_submission_kit.py | cli | True | True | True | False | False | True | False | Prepares editable world-class evidence intake packets without counting drafts as accepted evidence. | | scripts/probe_runtime_permissions.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/promotion_checker.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/provider_output_eval_runner.py | cli | False | True | True | False | True | False | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | diff --git a/reports/skill-overview.html b/reports/skill-overview.html index 5b85ee23..edef224e 100644 --- a/reports/skill-overview.html +++ b/reports/skill-overview.html @@ -771,7 +771,7 @@

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349项SKILL.mdREADME.mdagents/interface.yamlmanifest.jsonreferencesscripts
资产分布图展示当前包体的文件和目录重心。
+
资产分布350项SKILL.mdREADME.mdagents/interface.yamlmanifest.jsonreferencesscripts
资产分布图展示当前包体的文件和目录重心。
diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 1a73aa1e..a031873d 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -436,7 +436,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 90 + "file_count": 91 }, { "path": "evals", @@ -451,7 +451,7 @@ "file_count": 195 } ], - "file_count": 349, + "file_count": 350, "folder_count": 4, "distribution": [ { @@ -476,7 +476,7 @@ }, { "label": "scripts", - "value": 90 + "value": 91 }, { "label": "evals", @@ -605,7 +605,7 @@ "path": "scripts", "label": "Deterministic helpers or local tooling", "kind": "folder", - "file_count": 90 + "file_count": 91 }, { "path": "evals", @@ -909,9 +909,9 @@ "world_class_task_count": 4, "world_class_ledger_pending_count": 4, "working_tree_dirty": true, - "changed_file_count": 30 + "changed_file_count": 54 }, - "commit": "c5e7b05faae8536b420c5120c1d3a59456c96e51", + "commit": "b540f580b373cb9c0f575b687fb82c5a16748a5d", "missing_artifacts": [], "limitations": [ "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.", @@ -986,8 +986,8 @@ "failures": [] }, "trust_security": { - "scanned_files": 174, - "script_count": 90, + "scanned_files": 175, + "script_count": 91, "internal_module_count": 17, "secret_findings": 0, "dependency_files": [ @@ -996,18 +996,18 @@ "network_script_count": 3, "network_policy_covered_count": 3, "network_policy_missing_count": 0, - "file_write_script_count": 60, + "file_write_script_count": 61, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 73, + "help_smoke_checked_count": 74, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 174, - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "package_hash_file_count": 175, + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" }, "skill_atlas": { "skill_count": 12, @@ -1045,8 +1045,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9", - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "package_sha256": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, "compatibility": { "openai": "pass", @@ -1077,7 +1077,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -1093,8 +1093,8 @@ "target_count": 4, "adapter_count": 4, "archive_present": true, - "archive_sha256": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d", - "archive_entry_count": 558, + "archive_sha256": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e", + "archive_entry_count": 559, "failure_count": 0, "warning_count": 0 }, @@ -1105,7 +1105,7 @@ "ok": true, "summary": { "archive_present": true, - "archive_entry_count": 558, + "archive_entry_count": 559, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, @@ -1115,7 +1115,7 @@ "installer_permission_failure_count": 0, "permission_target_count": 4, "permission_capability_count": 3, - "install_root_is_temp": true, + "install_root_is_temp": false, "failure_count": 0, "warning_count": 0 }, @@ -1172,12 +1172,12 @@ { "field": "archive_sha256", "from": "", - "to": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "to": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "to": "d799ec85c035b6335ea1e262b980d630ec05cd07448239cf97a34540eb4c2bac" } ] }, @@ -1194,14 +1194,14 @@ "ok": true, "summary": { "event_count": 1, - "adoption_sample_count": 0, - "activation_count": 0, - "accepted_count": 0, + "adoption_sample_count": 1, + "activation_count": 1, + "accepted_count": 1, "edited_count": 0, "rejected_count": 0, "missed_count": 0, "failed_count": 0, - "adoption_rate": 0, + "adoption_rate": 100.0, "missed_trigger_count": 0, "wrong_trigger_count": 0, "bad_output_count": 0, @@ -1210,7 +1210,7 @@ "review_overdue_count": 0, "risk_band": "low", "event_types": { - "review_event": 1 + "skill_activation": 1 }, "failure_types": {}, "source_types": { @@ -1423,7 +1423,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", @@ -1655,7 +1655,7 @@ "owner": "Browser/Chrome/IDE/provider client integrator", "status": "pending", "source_status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "provenance_requirements": [ "real external client source", @@ -1683,7 +1683,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index 12b23844..eb73abc9 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -44,7 +44,7 @@ }, "catalog": { "workspace_root": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -85,6 +85,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -217,8 +218,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, @@ -881,7 +882,7 @@ "name": "incident-command-governor", "path": "examples/governed-incident-command/generated-skill", "reason": "review overdue by cadence monthly", - "age_days": 75, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index b8506c70..70038c1e 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": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 15, @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 90; help failures 0", + "current": "secrets 0; scripts 91; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { @@ -281,7 +281,7 @@ "key": "registry-distribution", "label": "Registry Distribution", "status": "pass", - "current": "zip entries 558; install failures 0; permission failures 0", + "current": "zip entries 559; install failures 0; permission failures 0", "target": "Package metadata, archive checksum, package verification, and install simulation pass", "evidence": [ { @@ -347,7 +347,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { @@ -425,7 +425,7 @@ "key": "native-client-telemetry", "label": "Native Client Telemetry", "status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "target": "A real Browser/Chrome/provider client sends production metadata events", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 0a3ba09a..fb8d0e2b 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -1,6 +1,6 @@ # Skill OS 2.0 Audit -Generated at: `2026-06-14` +Generated at: `2026-06-13` ## Summary @@ -23,14 +23,14 @@ Generated at: `2026-06-14` | 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 20; 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 90; 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 91; 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 | Packaged adapters expose explicit permission metadata and residual risks | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0 | At least one target/client enforces approved permissions at runtime | Integrate a real client or 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 558; 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 559; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | | Review Studio | pass | decision review; warnings 3; score 91 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. | | Telemetry Drift | pass | events 1; risk low; recipes 5 | Local-first metadata-only event contract, aggregate drift report, hook recipes, and import path | Keep raw JSONL out of distributed packages and use aggregate reports for Atlas. | -| Native Client Telemetry | external-required | external source events 0; adoption samples 0 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | +| Native Client Telemetry | external-required | external source events 0; adoption samples 1 | A real Browser/Chrome/provider client sends production metadata events | Install a real client against the native host and import production metadata-only events. | ## Open Highest-Leverage Gaps diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index 7ff45da7..7dc94d4a 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": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "item_count": 20, @@ -122,7 +122,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "90 scripts; secrets 0; help failures 0", + "current": "91 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -196,7 +196,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 558; install failures 0", + "current": "archive entries 559; 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 9f539e18..ba971edb 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: `2026-06-14` +Generated at: `2026-06-13` ## Summary @@ -21,9 +21,9 @@ 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` | 90 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 91 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 558; 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 559; 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/upgrade_check.json b/reports/upgrade_check.json index 17b06776..b29c7978 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "previous": { "name": "yao-meta-skill", "version": "1.0.0", @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "934b2967ff56afa5d725b9c129d4fc1e280854d85aa09783ffdb1b6b3108346d" + "to": "fe47e53a7a89918ef2d7ae53c1e62a6b73da0bd80904d5a157c71a2758c8004e" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "0b47fb8b2db508e32d5aafd5c46bd008dc23493c1ff909427686609e9f99d5a9" + "to": "4871c36233a53615c8e19c1c59449af60e732fff2d389742ca510422d7cbac75" } ] }, @@ -90,7 +90,7 @@ "artifacts": { "previous_package": "registry/examples/yao-meta-skill-1.0.0.json", "current_package": "reports/registry_audit.json", - "json": "reports/upgrade_check.json", - "markdown": "reports/upgrade_check.md" + "json": "tests/tmp_review_studio/upgrade_check.json", + "markdown": "tests/tmp_review_studio/upgrade_check.md" } } diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index 68d837f6..40809356 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": "2026-06-14", + "generated_at": "2026-06-13", "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 35462189..aca98a62 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: `2026-06-14` +Generated at: `2026-06-13` ## Summary diff --git a/reports/world_class_evidence_intake.json b/reports/world_class_evidence_intake.json index 6cb58407..84e91347 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": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "schema_present": true, @@ -64,7 +64,7 @@ "template_path": "evidence/world_class/templates/provider-holdout.intake.json", "submission_path": "evidence/world_class/submissions/provider-holdout.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/provider-holdout.intake.json evidence/world_class/submissions/provider-holdout.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -115,7 +115,7 @@ "template_path": "evidence/world_class/templates/human-adjudication.intake.json", "submission_path": "evidence/world_class/submissions/human-adjudication.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/human-adjudication.intake.json evidence/world_class/submissions/human-adjudication.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -167,7 +167,7 @@ "template_path": "evidence/world_class/templates/native-permission-enforcement.intake.json", "submission_path": "evidence/world_class/submissions/native-permission-enforcement.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-permission-enforcement.intake.json evidence/world_class/submissions/native-permission-enforcement.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." @@ -218,7 +218,7 @@ "template_path": "evidence/world_class/templates/native-client-telemetry.intake.json", "submission_path": "evidence/world_class/submissions/native-client-telemetry.json", "commands": { - "prepare_submission": "mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-client-telemetry.intake.json evidence/world_class/submissions/native-client-telemetry.json", + "prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions", "validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", "guard_claim": "python3 scripts/yao.py world-class-claim-guard ." diff --git a/reports/world_class_evidence_intake.md b/reports/world_class_evidence_intake.md index d345c95a..add660a2 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: `2026-06-14` +Generated at: `2026-06-13` ## Summary @@ -51,7 +51,7 @@ This report validates the intake contract for human and external evidence. A val #### Commands -- prepare_submission: `mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/provider-holdout.intake.json evidence/world_class/submissions/provider-holdout.json` +- prepare_submission: `python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions` - validate_intake: `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions` - refresh_ledger: `python3 scripts/yao.py world-class-ledger .` - guard_claim: `python3 scripts/yao.py world-class-claim-guard .` @@ -89,7 +89,7 @@ This report validates the intake contract for human and external evidence. A val #### Commands -- prepare_submission: `mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/human-adjudication.intake.json evidence/world_class/submissions/human-adjudication.json` +- prepare_submission: `python3 scripts/yao.py world-class-submission-kit . --evidence-key human-adjudication --output-dir evidence/world_class/submissions` - validate_intake: `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions` - refresh_ledger: `python3 scripts/yao.py world-class-ledger .` - guard_claim: `python3 scripts/yao.py world-class-claim-guard .` @@ -128,7 +128,7 @@ This report validates the intake contract for human and external evidence. A val #### Commands -- prepare_submission: `mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-permission-enforcement.intake.json evidence/world_class/submissions/native-permission-enforcement.json` +- prepare_submission: `python3 scripts/yao.py world-class-submission-kit . --evidence-key native-permission-enforcement --output-dir evidence/world_class/submissions` - validate_intake: `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions` - refresh_ledger: `python3 scripts/yao.py world-class-ledger .` - guard_claim: `python3 scripts/yao.py world-class-claim-guard .` @@ -166,7 +166,7 @@ This report validates the intake contract for human and external evidence. A val #### Commands -- prepare_submission: `mkdir -p evidence/world_class/submissions && cp evidence/world_class/templates/native-client-telemetry.intake.json evidence/world_class/submissions/native-client-telemetry.json` +- prepare_submission: `python3 scripts/yao.py world-class-submission-kit . --evidence-key native-client-telemetry --output-dir evidence/world_class/submissions` - validate_intake: `python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions` - refresh_ledger: `python3 scripts/yao.py world-class-ledger .` - guard_claim: `python3 scripts/yao.py world-class-claim-guard .` diff --git a/reports/world_class_evidence_ledger.json b/reports/world_class_evidence_ledger.json index 5e2ddcba..cec9e6a3 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": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "ledger_entry_count": 4, @@ -194,7 +194,7 @@ "owner": "Browser/Chrome/IDE/provider client integrator", "status": "pending", "source_status": "external_required", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "provenance_requirements": [ "real external client source", @@ -222,7 +222,7 @@ ], "observed_state": { "external_source_events": 0, - "adoption_sample_count": 0, + "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false diff --git a/reports/world_class_evidence_ledger.md b/reports/world_class_evidence_ledger.md index 67cf921a..126493b9 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: `2026-06-14` +Generated at: `2026-06-13` ## Summary @@ -25,7 +25,7 @@ This ledger records the current evidence state. It does not treat planned work, | `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 | Integrate a real client or installer runtime guard before claiming native permission enforcement. | -| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 0 | Install a real client against the native host and import production metadata-only events. | +| `native-client-telemetry` | `pending` | `missing` | `external` | external source events 0; adoption samples 1 | Install a real client against the native host and import production metadata-only events. | ## Provider Holdout @@ -105,7 +105,7 @@ This ledger records the current evidence state. It does not treat planned work, - objective: Import production metadata-only events from a real external client into the local drift loop. - source status: `external_required` -- observed state: `{"external_source_events": 0, "adoption_sample_count": 0, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` +- observed state: `{"external_source_events": 0, "adoption_sample_count": 1, "raw_content_allowed": false, "risk_band": "low", "accepted": false}` - 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 diff --git a/reports/world_class_evidence_plan.json b/reports/world_class_evidence_plan.json index 2cc7917c..85dfd242 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": "2026-06-14", + "generated_at": "2026-06-13", "skill_dir": ".", "summary": { "audit_decision": "continue-iteration", @@ -132,7 +132,7 @@ "status": "external_required", "category": "external", "owner": "Browser/Chrome/IDE/provider client integrator", - "current": "external source events 0; adoption samples 0", + "current": "external source events 0; adoption samples 1", "objective": "Import production metadata-only events from a real external client into the local drift loop.", "runbook": [ "python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension:///", diff --git a/reports/world_class_evidence_plan.md b/reports/world_class_evidence_plan.md index fc6570e5..8be81391 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: `2026-06-14` +Generated at: `2026-06-13` ## Summary @@ -20,7 +20,7 @@ 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 | -| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 0 | +| `native-client-telemetry` | `external_required` | `external` | Browser/Chrome/IDE/provider client integrator | external source events 0; adoption samples 1 | ## Provider Holdout diff --git a/scripts/ci_test.py b/scripts/ci_test.py index 241c9ac0..fdb8521a 100644 --- a/scripts/ci_test.py +++ b/scripts/ci_test.py @@ -20,6 +20,7 @@ SAFE_ENV_KEYS = ( "TERM", "TMP", "TMPDIR", + "TZ", ) DEFAULT_TARGETS = [ "eval", diff --git a/scripts/prepare_world_class_submission_kit.py b/scripts/prepare_world_class_submission_kit.py new file mode 100644 index 00000000..bb7e83f4 --- /dev/null +++ b/scripts/prepare_world_class_submission_kit.py @@ -0,0 +1,218 @@ +#!/usr/bin/env python3 +import argparse +import json +import shutil +from datetime import date +from pathlib import Path +from typing import Any + +from render_world_class_evidence_intake import build_intake + + +ROOT = Path(__file__).resolve().parent.parent +SCRIPT_INTERFACE = "cli" +SCRIPT_INTERFACE_REASON = "Prepares editable world-class evidence intake packets without counting drafts as accepted evidence." + + +def rel_path(path: Path, root: Path) -> str: + try: + return str(path.resolve().relative_to(root.resolve())) + except ValueError: + return str(path.resolve()) + + +def write_json(path: Path, payload: dict[str, Any]) -> None: + path.parent.mkdir(parents=True, exist_ok=True) + path.write_text(json.dumps(payload, ensure_ascii=False, indent=2) + "\n", encoding="utf-8") + + +def requested_checklist_items(intake: dict[str, Any], evidence_keys: list[str]) -> list[dict[str, Any]]: + items = intake.get("operator_checklist", []) + if not evidence_keys: + return items + requested = set(evidence_keys) + return [item for item in items if item.get("evidence_key") in requested] + + +def template_result_by_key(intake: dict[str, Any]) -> dict[str, dict[str, Any]]: + return {str(item.get("evidence_key")): item for item in intake.get("templates", [])} + + +def copy_template( + skill_dir: Path, + output_dir: Path, + item: dict[str, Any], + template_results: dict[str, dict[str, Any]], + overwrite: bool, +) -> dict[str, Any]: + key = str(item.get("evidence_key", "")) + template_result = template_results.get(key, {}) + template_path = skill_dir / str(item.get("template_path", "")) + output_path = output_dir / f"{key}.json" + errors: list[str] = [] + + if template_result.get("status") != "pass": + errors.append("template failed intake validation") + if not template_path.exists(): + errors.append("template file is missing") + + if errors: + return { + "evidence_key": key, + "status": "skipped", + "template_path": rel_path(template_path, skill_dir), + "output_path": rel_path(output_path, skill_dir), + "errors": errors, + } + + if output_path.exists() and not overwrite: + return { + "evidence_key": key, + "status": "exists", + "template_path": rel_path(template_path, skill_dir), + "output_path": rel_path(output_path, skill_dir), + "errors": [], + } + + output_path.parent.mkdir(parents=True, exist_ok=True) + shutil.copyfile(template_path, output_path) + return { + "evidence_key": key, + "status": "written", + "template_path": rel_path(template_path, skill_dir), + "output_path": rel_path(output_path, skill_dir), + "errors": [], + } + + +def render_readme(report: dict[str, Any]) -> str: + commands = report["commands"] + lines = [ + "# World-Class Evidence Submission Kit", + "", + f"Generated at: `{report['generated_at']}`", + "", + "This kit contains editable drafts for human and external evidence packets. Drafts are not accepted evidence.", + "", + "## Workflow", + "", + "1. Run the real provider, human review, native permission, or native client telemetry work first.", + "2. Edit the matching JSON draft with only aggregate artifact references and provenance metadata.", + "3. Set `template_only` to `false` only after real evidence exists.", + "4. Set attestation booleans truthfully; do not include credentials, raw prompts, raw outputs, transcripts, notes, or private user content.", + "5. Validate the packet before asking the ledger reviewer to accept it.", + "", + "## Commands", + "", + f"- validate intake: `{commands['validate_intake']}`", + f"- refresh ledger: `{commands['refresh_ledger']}`", + f"- guard public claims: `{commands['guard_claim']}`", + "", + "## Drafts", + "", + "| Evidence | Draft | Status |", + "| --- | --- | --- |", + ] + for item in report["files"]: + lines.append(f"| `{item['evidence_key']}` | `{item['output_path']}` | `{item['status']}` |") + lines.extend( + [ + "", + "## Anti-Overclaim", + "", + "- This kit never marks ledger evidence as accepted.", + "- Planned work, metadata fallback, pending review, and local command-runner output remain non-evidence.", + "- A valid intake packet means ready for ledger review, not world-class completion.", + ] + ) + return "\n".join(lines).rstrip() + "\n" + + +def build_submission_kit( + skill_dir: Path, + output_dir: Path, + generated_at: str, + evidence_keys: list[str] | None = None, + overwrite: bool = False, +) -> dict[str, Any]: + intake = build_intake(skill_dir, generated_at, submissions_dir=output_dir) + items = requested_checklist_items(intake, evidence_keys or []) + valid_keys = {str(item.get("evidence_key")) for item in intake.get("operator_checklist", [])} + unknown_keys = sorted(set(evidence_keys or []) - valid_keys) + template_results = template_result_by_key(intake) + files = [copy_template(skill_dir, output_dir, item, template_results, overwrite) for item in items] + manifest_path = output_dir / "submission_manifest.json" + readme_path = output_dir / "README.md" + written_count = sum(1 for item in files if item["status"] == "written") + existing_count = sum(1 for item in files if item["status"] == "exists") + skipped_count = sum(1 for item in files if item["status"] == "skipped") + ok = not unknown_keys and skipped_count == 0 + report = { + "schema_version": "1.0", + "ok": ok, + "generated_at": generated_at, + "skill_dir": rel_path(skill_dir, ROOT), + "output_dir": rel_path(output_dir, skill_dir), + "summary": { + "requested_count": len(items) + len(unknown_keys), + "prepared_count": len(files), + "written_count": written_count, + "existing_count": existing_count, + "skipped_count": skipped_count, + "unknown_key_count": len(unknown_keys), + "drafts_count_as_evidence": False, + "ledger_counts_submission_as_completion": False, + "decision": "submission-kit-ready" if ok else "fix-submission-kit", + }, + "unknown_evidence_keys": unknown_keys, + "files": files, + "commands": { + "validate_intake": f"python3 scripts/yao.py world-class-intake . --submissions-dir {rel_path(output_dir, skill_dir)}", + "refresh_ledger": f"python3 scripts/yao.py world-class-ledger . --submissions-dir {rel_path(output_dir, skill_dir)}", + "guard_claim": "python3 scripts/yao.py world-class-claim-guard .", + }, + "safety": { + "template_only_drafts": True, + "real_evidence_required_before_template_only_false": True, + "raw_content_allowed": False, + "credentials_allowed": False, + "drafts_count_as_evidence": False, + }, + "artifacts": { + "manifest": rel_path(manifest_path, skill_dir), + "readme": rel_path(readme_path, skill_dir), + }, + } + output_dir.mkdir(parents=True, exist_ok=True) + write_json(manifest_path, report) + readme_path.write_text(render_readme(report), encoding="utf-8") + return report + + +def main() -> None: + parser = argparse.ArgumentParser(description="Prepare editable world-class evidence submission drafts.") + parser.add_argument("skill_dir", nargs="?", default=".") + parser.add_argument("--output-dir", default="evidence/world_class/submission-kit") + parser.add_argument("--evidence-key", action="append", default=[]) + parser.add_argument("--overwrite", action="store_true") + parser.add_argument("--generated-at", default=date.today().isoformat()) + args = parser.parse_args() + + skill_dir = Path(args.skill_dir).resolve() + output_dir = Path(args.output_dir) + if not output_dir.is_absolute(): + output_dir = skill_dir / output_dir + report = build_submission_kit( + skill_dir, + output_dir.resolve(), + args.generated_at, + evidence_keys=args.evidence_key, + overwrite=args.overwrite, + ) + print(json.dumps(report, ensure_ascii=False, indent=2)) + if not report["ok"]: + raise SystemExit(2) + + +if __name__ == "__main__": + main() diff --git a/scripts/render_world_class_evidence_intake.py b/scripts/render_world_class_evidence_intake.py index 84fe1406..58746311 100644 --- a/scripts/render_world_class_evidence_intake.py +++ b/scripts/render_world_class_evidence_intake.py @@ -179,7 +179,8 @@ def template_paths(skill_dir: Path, keys: list[str]) -> dict[str, Path]: def submission_paths(submissions_dir: Path) -> list[Path]: if not submissions_dir.exists(): return [] - return sorted(path for path in submissions_dir.glob("*.json") if path.is_file()) + ignored_names = {"submission_manifest.json"} + return sorted(path for path in submissions_dir.glob("*.json") if path.is_file() and path.name not in ignored_names) def find_entry(entries: list[dict[str, Any]], key: str) -> dict[str, Any] | None: @@ -250,8 +251,8 @@ def build_operator_checklist( "submission_path": rel_path(submission_path, skill_dir), "commands": { "prepare_submission": ( - f"mkdir -p {shell_path(submission_path.parent, skill_dir)} && " - f"cp {shell_path(template_path, skill_dir)} {shell_path(submission_path, skill_dir)}" + "python3 scripts/yao.py world-class-submission-kit . " + f"--evidence-key {shlex.quote(key)} --output-dir {shell_path(submission_path.parent, skill_dir)}" ), "validate_intake": f"python3 scripts/yao.py world-class-intake . --submissions-dir {submissions_dir_arg}", "refresh_ledger": "python3 scripts/yao.py world-class-ledger .", diff --git a/scripts/yao.py b/scripts/yao.py index 322b4b9a..7b0b24af 100644 --- a/scripts/yao.py +++ b/scripts/yao.py @@ -34,6 +34,7 @@ from yao_cli_report_commands import ( command_world_class_evidence, command_world_class_intake, command_world_class_ledger, + command_world_class_submission_kit, ) from yao_cli_runtime import ROOT, run_script from yao_cli_telemetry import add_telemetry_args, maybe_record_cli_event diff --git a/scripts/yao_cli_parser.py b/scripts/yao_cli_parser.py index c9286bee..a0300c75 100644 --- a/scripts/yao_cli_parser.py +++ b/scripts/yao_cli_parser.py @@ -208,6 +208,17 @@ def build_parser(command_handlers: dict[str, Callable[[argparse.Namespace], int] world_class_intake_cmd.add_argument("--generated-at") world_class_intake_cmd.set_defaults(func=_handler(command_handlers, "command_world_class_intake")) + world_class_submission_kit_cmd = subparsers.add_parser( + "world-class-submission-kit", + help="Prepare editable world-class evidence submission drafts.", + ) + world_class_submission_kit_cmd.add_argument("skill_dir", nargs="?", default=".") + world_class_submission_kit_cmd.add_argument("--output-dir") + world_class_submission_kit_cmd.add_argument("--evidence-key", action="append", default=[]) + world_class_submission_kit_cmd.add_argument("--overwrite", action="store_true") + world_class_submission_kit_cmd.add_argument("--generated-at") + world_class_submission_kit_cmd.set_defaults(func=_handler(command_handlers, "command_world_class_submission_kit")) + world_class_claim_guard_cmd = subparsers.add_parser( "world-class-claim-guard", help="Scan public claim surfaces for premature world-class completion claims.", diff --git a/scripts/yao_cli_report_commands.py b/scripts/yao_cli_report_commands.py index 778327c3..a6cd3d06 100644 --- a/scripts/yao_cli_report_commands.py +++ b/scripts/yao_cli_report_commands.py @@ -77,6 +77,19 @@ def command_world_class_intake(args: argparse.Namespace) -> int: return emit_result(run_script("render_world_class_evidence_intake.py", cmd)) +def command_world_class_submission_kit(args: argparse.Namespace) -> int: + cmd = [resolved_skill_dir(args)] + if args.output_dir: + cmd.extend(["--output-dir", args.output_dir]) + for key in args.evidence_key: + cmd.extend(["--evidence-key", key]) + if args.overwrite: + cmd.append("--overwrite") + if args.generated_at: + cmd.extend(["--generated-at", args.generated_at]) + return emit_result(run_script("prepare_world_class_submission_kit.py", cmd)) + + def command_world_class_claim_guard(args: argparse.Namespace) -> int: cmd = [resolved_skill_dir(args)] for surface in args.claim_surface: diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json index bc4c541f..e21ee3cf 100644 --- a/skill-ir/examples/yao-meta-skill.json +++ b/skill-ir/examples/yao-meta-skill.json @@ -129,6 +129,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -186,8 +187,7 @@ "scripts/skill_report_model.py", "scripts/sync_local_install.py", "scripts/telemetry_native_host.py", - "scripts/trigger_eval.py", - "scripts/trust_check.py" + "scripts/trigger_eval.py" ], "assets": [ "templates/basic_skill.md.j2", diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 551eabf5..ae65efde 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -1,6 +1,6 @@ { "workspace_root": ".", - "generated_at": "2026-06-14", + "generated_at": "2026-06-13", "skills": [ { "name": "yao-meta-skill", @@ -41,6 +41,7 @@ "scripts/lint_skill.py", "scripts/local_output_eval_runner.py", "scripts/optimize_description.py", + "scripts/prepare_world_class_submission_kit.py", "scripts/probe_runtime_permissions.py", "scripts/promotion_checker.py", "scripts/provider_output_eval_runner.py", @@ -173,8 +174,8 @@ "report": "reports/adoption_drift_report.json", "risk_band": "low", "event_count": 1, - "adoption_sample_count": 0, - "adoption_rate": 0, + "adoption_sample_count": 1, + "adoption_rate": 100.0, "candidate_count": 0 } }, diff --git a/skill_atlas/stale_skills.json b/skill_atlas/stale_skills.json index a3919831..6602e829 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": 75, + "age_days": 74, "allowed_days": 31, "actionable": false, "scope": "example" diff --git a/tests/verify_world_class_evidence_intake.py b/tests/verify_world_class_evidence_intake.py index d2de722c..133c8b1c 100644 --- a/tests/verify_world_class_evidence_intake.py +++ b/tests/verify_world_class_evidence_intake.py @@ -8,6 +8,7 @@ from pathlib import Path ROOT = Path(__file__).resolve().parent.parent SCRIPT = ROOT / "scripts" / "render_world_class_evidence_intake.py" +KIT_SCRIPT = ROOT / "scripts" / "prepare_world_class_submission_kit.py" TMP = ROOT / "tests" / "tmp_world_class_evidence_intake" @@ -29,6 +30,23 @@ def run_intake(*extra: str) -> dict: return json.loads(proc.stdout) +def run_kit(*extra: str) -> subprocess.CompletedProcess[str]: + return subprocess.run( + [ + sys.executable, + str(KIT_SCRIPT), + str(ROOT), + "--generated-at", + "2026-06-14", + *extra, + ], + cwd=ROOT, + capture_output=True, + text=True, + check=True, + ) + + def provider_submission(*, valid: bool) -> dict: return { "schema_version": "1.0", @@ -113,7 +131,10 @@ def main() -> None: assert checklist["provider-holdout"]["readiness"] == "awaiting-submission", checklist["provider-holdout"] assert checklist["provider-holdout"]["template_path"] == "evidence/world_class/templates/provider-holdout.intake.json", checklist["provider-holdout"] assert checklist["provider-holdout"]["submission_path"] == "evidence/world_class/submissions/provider-holdout.json", checklist["provider-holdout"] - assert "cp evidence/world_class/templates/provider-holdout.intake.json" in checklist["provider-holdout"]["commands"]["prepare_submission"], checklist["provider-holdout"] + assert checklist["provider-holdout"]["commands"]["prepare_submission"] == ( + "python3 scripts/yao.py world-class-submission-kit . " + "--evidence-key provider-holdout --output-dir evidence/world_class/submissions" + ), checklist["provider-holdout"] assert checklist["provider-holdout"]["commands"]["validate_intake"] == "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions", checklist["provider-holdout"] assert "provider-backed model run" in checklist["provider-holdout"]["must_collect"]["provenance_requirements"], checklist["provider-holdout"] assert "reports/output_execution_runs.json summary.model_executed_count > 0" in checklist["provider-holdout"]["must_collect"]["success_checks"], checklist["provider-holdout"] @@ -124,9 +145,41 @@ def main() -> None: assert "Operator Checklist" in markdown, markdown assert "operator checklist: `0` ready / `4` total" in markdown, markdown assert "`evidence/world_class/submissions/provider-holdout.json`" in markdown, markdown + assert "`python3 scripts/yao.py world-class-submission-kit . --evidence-key provider-holdout --output-dir evidence/world_class/submissions`" in markdown, markdown assert "`python3 scripts/yao.py world-class-ledger .`" in markdown, markdown assert "Templates and planned work do not count as accepted evidence." in markdown, markdown + kit_dir = TMP / "submission_kit" + kit_proc = run_kit("--output-dir", str(kit_dir), "--evidence-key", "provider-holdout") + kit_payload = json.loads(kit_proc.stdout) + assert kit_payload["ok"] is True, kit_payload + assert kit_payload["summary"]["decision"] == "submission-kit-ready", kit_payload["summary"] + assert kit_payload["summary"]["requested_count"] == 1, kit_payload["summary"] + assert kit_payload["summary"]["written_count"] == 1, kit_payload["summary"] + assert kit_payload["summary"]["drafts_count_as_evidence"] is False, kit_payload["summary"] + assert kit_payload["safety"]["template_only_drafts"] is True, kit_payload["safety"] + assert kit_payload["safety"]["raw_content_allowed"] is False, kit_payload["safety"] + assert kit_payload["files"][0]["output_path"].endswith("tests/tmp_world_class_evidence_intake/submission_kit/provider-holdout.json"), kit_payload["files"] + kit_draft = json.loads((kit_dir / "provider-holdout.json").read_text(encoding="utf-8")) + assert kit_draft["template_only"] is True, kit_draft + assert kit_draft["attestation"]["real_external_or_human_evidence"] is False, kit_draft + kit_manifest = json.loads((kit_dir / "submission_manifest.json").read_text(encoding="utf-8")) + assert kit_manifest["summary"]["ledger_counts_submission_as_completion"] is False, kit_manifest["summary"] + kit_readme = (kit_dir / "README.md").read_text(encoding="utf-8") + assert "Drafts are not accepted evidence." in kit_readme, kit_readme + assert "validate intake" in kit_readme, kit_readme + draft_intake = run_intake("--submissions-dir", str(kit_dir)) + assert draft_intake["ok"] is False, draft_intake + assert draft_intake["summary"]["submission_count"] == 1, draft_intake["summary"] + assert draft_intake["summary"]["invalid_submission_count"] == 1, draft_intake["summary"] + assert draft_intake["submissions"][0]["evidence_key"] == "provider-holdout", draft_intake["submissions"] + assert all(item["evidence_key"] != "unknown" for item in draft_intake["submissions"]), draft_intake["submissions"] + + existing_proc = run_kit("--output-dir", str(kit_dir), "--evidence-key", "provider-holdout") + existing_payload = json.loads(existing_proc.stdout) + assert existing_payload["summary"]["existing_count"] == 1, existing_payload["summary"] + assert existing_payload["files"][0]["status"] == "exists", existing_payload["files"] + valid_dir = TMP / "valid_submissions" valid_dir.mkdir() (valid_dir / "provider-holdout.json").write_text( diff --git a/tests/verify_yao_cli.py b/tests/verify_yao_cli.py index 783ee91c..45536c6a 100644 --- a/tests/verify_yao_cli.py +++ b/tests/verify_yao_cli.py @@ -85,6 +85,7 @@ def main() -> None: assert "world-class-evidence" in parser_help, parser_help assert "world-class-ledger" in parser_help, parser_help assert "world-class-intake" in parser_help, parser_help + assert "world-class-submission-kit" in parser_help, parser_help assert "world-class-claim-guard" in parser_help, parser_help assert "benchmark-reproducibility" in parser_help, parser_help assert "telemetry-import" in parser_help, parser_help @@ -270,9 +271,29 @@ def main() -> None: item for item in world_class_intake_result["payload"]["operator_checklist"] if item["evidence_key"] == "provider-holdout" ) assert provider_checklist["readiness"] == "awaiting-submission", provider_checklist - assert "cp evidence/world_class/templates/provider-holdout.intake.json" in provider_checklist["commands"]["prepare_submission"], provider_checklist + assert provider_checklist["commands"]["prepare_submission"] == ( + "python3 scripts/yao.py world-class-submission-kit . " + "--evidence-key provider-holdout --output-dir evidence/world_class/submissions" + ), provider_checklist assert world_class_ledger_result["payload"]["summary"]["ready_to_claim_world_class"] is False, world_class_ledger_result + world_class_submission_kit_result = run( + "world-class-submission-kit", + str(ROOT), + "--output-dir", + str(tmp_root / "world_class_submission_kit"), + "--evidence-key", + "provider-holdout", + "--generated-at", + "2026-06-14", + ) + assert world_class_submission_kit_result["ok"], world_class_submission_kit_result + assert world_class_submission_kit_result["payload"]["summary"]["decision"] == "submission-kit-ready", world_class_submission_kit_result + assert world_class_submission_kit_result["payload"]["summary"]["written_count"] == 1, world_class_submission_kit_result + assert world_class_submission_kit_result["payload"]["summary"]["drafts_count_as_evidence"] is False, world_class_submission_kit_result + assert (tmp_root / "world_class_submission_kit" / "provider-holdout.json").exists(), world_class_submission_kit_result + assert (tmp_root / "world_class_submission_kit" / "submission_manifest.json").exists(), world_class_submission_kit_result + world_class_claim_guard_result = run( "world-class-claim-guard", str(ROOT),
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