From ee8e207e8b1e23dd0209c3180a256bda3acc3ecf Mon Sep 17 00:00:00 2001 From: yaojingang Date: Tue, 16 Jun 2026 05:13:52 +0800 Subject: [PATCH] Refresh weekly curator source evidence --- registry/index.json | 2 +- registry/packages/yao-meta-skill.json | 6 +- reports/adoption_drift_report.json | 2 +- reports/architecture_maintainability.json | 18 ++--- reports/architecture_maintainability.md | 18 ++--- reports/compiled_targets.json | 90 +++++++++++++---------- reports/install_simulation.json | 2 +- reports/output_execution_runs.json | 18 ++--- reports/output_execution_runs.md | 18 ++--- reports/package_verification.json | 4 +- reports/package_verification.md | 2 +- reports/python_compatibility.json | 20 ++++- reports/python_compatibility.md | 2 +- reports/registry_audit.json | 8 +- reports/registry_audit.md | 4 +- reports/security_trust_report.json | 43 ++++++++--- reports/security_trust_report.md | 17 +++-- reports/skill-os-2-review.md | 10 ++- reports/skill_atlas.json | 1 + reports/skill_os2_audit.json | 4 +- reports/skill_os2_audit.md | 4 +- reports/skill_os2_coverage.json | 39 ++++++++-- reports/skill_os2_coverage.md | 16 +++- reports/upgrade_check.json | 4 +- reports/world_class_claim_guard.json | 14 +++- reports/world_class_claim_guard.md | 6 +- skill_atlas/catalog.json | 1 + 27 files changed, 237 insertions(+), 136 deletions(-) diff --git a/registry/index.json b/registry/index.json index afcf1ca5..0b042d6e 100644 --- a/registry/index.json +++ b/registry/index.json @@ -16,7 +16,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" + "package_sha256": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada" } ] } diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json index 08fe1de7..09c21593 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": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", - "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" + "package_sha256": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada", + "archive_sha256": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d" }, "compatibility": { "openai": "pass", @@ -48,7 +48,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_sha256": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" diff --git a/reports/adoption_drift_report.json b/reports/adoption_drift_report.json index 73c2722c..71fe0fda 100644 --- a/reports/adoption_drift_report.json +++ b/reports/adoption_drift_report.json @@ -1,7 +1,7 @@ { "ok": true, "schema_version": "2.0", - "generated_at": "2026-06-15T20:47:47Z", + "generated_at": "2026-06-16", "skill_dir": ".", "privacy_contract": { "storage": "local-first", diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json index 1d179a08..24581901 100644 --- a/reports/architecture_maintainability.json +++ b/reports/architecture_maintainability.json @@ -4,12 +4,12 @@ "generated_at": "2026-06-16", "skill_dir": ".", "summary": { - "python_file_count": 183, - "script_file_count": 116, - "test_file_count": 67, + "python_file_count": 186, + "script_file_count": 117, + "test_file_count": 69, "internal_module_count": 35, - "cli_script_count": 83, - "command_handler_count": 66, + "cli_script_count": 84, + "command_handler_count": 67, "entrypoint_command_handler_count": 18, "command_module_count": 6, "warn_line_threshold": 900, @@ -38,7 +38,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 843, + "lines": 854, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -66,7 +66,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 767, + "lines": 768, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." @@ -124,7 +124,7 @@ }, { "path": "scripts/yao_cli_parser.py", - "lines": 843, + "lines": 854, "kind": "internal-module", "severity": "pass", "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates." @@ -152,7 +152,7 @@ }, { "path": "tests/verify_review_studio.py", - "lines": 767, + "lines": 768, "kind": "test", "severity": "pass", "recommendation": "Break broad integration assertions into focused verifier helpers when the next behavior change lands." diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md index f0084e06..4238e680 100644 --- a/reports/architecture_maintainability.md +++ b/reports/architecture_maintainability.md @@ -5,12 +5,12 @@ Generated at: `2026-06-16` ## Summary - decision: `pass` -- python files: `183` -- scripts: `116` -- tests: `67` +- python files: `186` +- scripts: `117` +- tests: `69` - internal modules: `35` -- CLI scripts: `83` -- Yao CLI command handlers: `66` +- CLI scripts: `84` +- Yao CLI command handlers: `67` - entrypoint command handlers: `18` - command modules: `6` - largest file lines: `899` @@ -31,11 +31,11 @@ No file-size hotspots found. | --- | ---: | --- | --- | | `tests/verify_yao_cli.py` | `899` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `scripts/render_evidence_consistency.py` | `859` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | -| `scripts/yao_cli_parser.py` | `843` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | +| `scripts/yao_cli_parser.py` | `854` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/skill_report_layout.py` | `808` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/skill_report_model.py` | `800` | `internal-module` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `tests/verify_world_class_evidence_intake.py` | `795` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | -| `tests/verify_review_studio.py` | `767` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | +| `tests/verify_review_studio.py` | `768` | `test` | Break broad integration assertions into focused verifier helpers when the next behavior change lands. | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/prepare_world_class_submission_kit.py` | `724` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | | `scripts/compile_skill.py` | `723` | `cli-script` | Watch this file before adding new responsibilities; extract a helper module when one concern dominates. | @@ -47,11 +47,11 @@ No file-size hotspots found. | --- | ---: | --- | --- | | `tests/verify_yao_cli.py` | `899` | `test` | `pass` | | `scripts/render_evidence_consistency.py` | `859` | `cli-script` | `pass` | -| `scripts/yao_cli_parser.py` | `843` | `internal-module` | `pass` | +| `scripts/yao_cli_parser.py` | `854` | `internal-module` | `pass` | | `scripts/skill_report_layout.py` | `808` | `internal-module` | `pass` | | `scripts/skill_report_model.py` | `800` | `internal-module` | `pass` | | `tests/verify_world_class_evidence_intake.py` | `795` | `test` | `pass` | -| `tests/verify_review_studio.py` | `767` | `test` | `pass` | +| `tests/verify_review_studio.py` | `768` | `test` | `pass` | | `scripts/build_skill_atlas.py` | `730` | `cli-script` | `pass` | | `scripts/prepare_world_class_submission_kit.py` | `724` | `cli-script` | `pass` | | `scripts/compile_skill.py` | `723` | `cli-script` | `pass` | diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json index 8032bb49..aaf72bf5 100644 --- a/reports/compiled_targets.json +++ b/reports/compiled_targets.json @@ -421,7 +421,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -476,6 +476,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -533,14 +534,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -562,7 +563,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -675,7 +676,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -730,6 +731,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -787,14 +789,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -814,7 +816,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -1324,7 +1326,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -1379,6 +1381,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -1436,14 +1439,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1465,7 +1468,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -1578,7 +1581,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -1633,6 +1636,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -1690,14 +1694,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -1717,7 +1721,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -2227,7 +2231,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -2282,6 +2286,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -2339,14 +2344,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2368,7 +2373,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -2474,7 +2479,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -2529,6 +2534,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -2586,14 +2592,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -2613,7 +2619,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -3114,7 +3120,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -3169,6 +3175,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -3226,14 +3233,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3255,7 +3262,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -3361,7 +3368,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -3416,6 +3423,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -3473,14 +3481,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -3500,7 +3508,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -4001,7 +4009,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -4056,6 +4064,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -4113,14 +4122,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4142,7 +4151,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, @@ -4252,7 +4261,7 @@ }, "file_write": { "required": true, - "script_count": 71, + "script_count": 72, "scripts": [ "scripts/adjudicate_output_review.py", "scripts/apply_adaptation.py", @@ -4307,6 +4316,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", @@ -4364,14 +4374,14 @@ }, "help_smoke": { "enabled": true, - "checked_count": 84, + "checked_count": 85, "failed_count": 0, "failed_scripts": [] }, "trust_summary": { "secret_findings": 0, "network_script_count": 3, - "file_write_script_count": 71, + "file_write_script_count": 72, "subprocess_script_count": 10, "interactive_script_count": 0, "help_smoke_failed_count": 0 @@ -4391,7 +4401,7 @@ ], "capability_counts": { "network": 3, - "file_write": 71, + "file_write": 72, "subprocess": 10, "interactive": 0 }, diff --git a/reports/install_simulation.json b/reports/install_simulation.json index 6dbc3d4e..f46e8674 100644 --- a/reports/install_simulation.json +++ b/reports/install_simulation.json @@ -8,7 +8,7 @@ "installed_skill_dir": "dist/install-simulation/simulate-yao-meta-skill/yao-meta-skill", "summary": { "archive_present": true, - "archive_entry_count": 634, + "archive_entry_count": 639, "archive_extracted": true, "entrypoint_loaded": true, "manifest_loaded": true, diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json index 2aa5cd77..55d78460 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": 26.41, + "duration_ms": 26.74, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -62,7 +62,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.38, + "duration_ms": 26.39, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -85,7 +85,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.02, + "duration_ms": 26.52, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -113,7 +113,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.01, + "duration_ms": 29.86, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -136,7 +136,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 25.98, + "duration_ms": 29.62, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -164,7 +164,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.24, + "duration_ms": 30.03, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -187,7 +187,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.23, + "duration_ms": 26.61, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -214,7 +214,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.52, + "duration_ms": 26.34, "provider": "local-output-eval-runner", "model": "", "usage": { @@ -266,7 +266,7 @@ "execution_mode": "command", "model_executed": false, "command_executed": true, - "duration_ms": 26.24, + "duration_ms": 26.52, "provider": "local-output-eval-runner", "model": "", "usage": { diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md index eaa78bc0..0081d6a3 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 | 26.41 | 33 | 0.0 | pass | -| skill-package-contract | with_skill | command | local-output-eval-runner | 26.38 | 73 | 100.0 | pass | -| output-eval-expectation | baseline | command | local-output-eval-runner | 26.02 | 36 | 0.0 | pass | -| output-eval-expectation | with_skill | command | local-output-eval-runner | 26.01 | 80 | 100.0 | pass | -| ir-before-packaging | baseline | command | local-output-eval-runner | 25.98 | 33 | 0.0 | pass | -| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.24 | 80 | 100.0 | pass | -| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.23 | 36 | 0.0 | pass | -| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.52 | 65 | 100.0 | pass | +| skill-package-contract | baseline | command | local-output-eval-runner | 26.74 | 33 | 0.0 | pass | +| skill-package-contract | with_skill | command | local-output-eval-runner | 26.39 | 73 | 100.0 | pass | +| output-eval-expectation | baseline | command | local-output-eval-runner | 26.52 | 36 | 0.0 | pass | +| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.86 | 80 | 100.0 | pass | +| ir-before-packaging | baseline | command | local-output-eval-runner | 29.62 | 33 | 0.0 | pass | +| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.03 | 80 | 100.0 | pass | +| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.61 | 36 | 0.0 | pass | +| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.34 | 65 | 100.0 | pass | | file-backed-governed-package | baseline | command | local-output-eval-runner | 26.24 | 37 | 0.0 | pass | -| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.24 | 98 | 100.0 | pass | +| file-backed-governed-package | with_skill | command | local-output-eval-runner | 26.52 | 98 | 100.0 | pass | ## Next Fixes diff --git a/reports/package_verification.json b/reports/package_verification.json index 253f9202..0288f9f8 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": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", - "archive_entry_count": 634, + "archive_sha256": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d", + "archive_entry_count": 639, "failure_count": 0, "warning_count": 0 }, diff --git a/reports/package_verification.md b/reports/package_verification.md index 0d3d405c..cabc73bd 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: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35` +- Archive SHA256: `ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d` - Failures: `0` - Warnings: `0` diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json index d7b89493..1520fd11 100644 --- a/reports/python_compatibility.json +++ b/reports/python_compatibility.json @@ -5,7 +5,7 @@ "root": ".", "summary": { "target_python": "3.11", - "file_count": 186, + "file_count": 189, "issue_count": 0, "syntax_error_count": 0, "fstring_311_violation_count": 0, @@ -424,6 +424,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "scripts/render_weekly_curator_report.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "scripts/render_world_class_claim_guard.py", "ok": true, @@ -1090,6 +1096,12 @@ "issue_count": 0, "issues": [] }, + { + "path": "tests/verify_weekly_curator.py", + "ok": true, + "issue_count": 0, + "issues": [] + }, { "path": "tests/verify_world_class_claim_guard.py", "ok": true, @@ -1137,6 +1149,12 @@ "ok": true, "issue_count": 0, "issues": [] + }, + { + "path": "tests/yao_cli_report_refresh.py", + "ok": true, + "issue_count": 0, + "issues": [] } ], "issues": [], diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md index fef92c23..32831e93 100644 --- a/reports/python_compatibility.md +++ b/reports/python_compatibility.md @@ -6,7 +6,7 @@ Generated at: `2026-06-16` - decision: `pass` - target python: `3.11` -- files scanned: `186` +- files scanned: `189` - issues: `0` - syntax errors: `0` - f-string 3.11 violations: `0` diff --git a/reports/registry_audit.json b/reports/registry_audit.json index 1a4767c9..cf61112d 100644 --- a/reports/registry_audit.json +++ b/reports/registry_audit.json @@ -21,8 +21,8 @@ "trust_level": "local", "license": "MIT", "checksums": { - "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7", - "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" + "package_sha256": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada", + "archive_sha256": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d" }, "compatibility": { "openai": "pass", @@ -53,7 +53,7 @@ }, "distribution": { "archive_verified": true, - "archive_sha256": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35", + "archive_sha256": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d", "package_verification": "reports/package_verification.json", "install_simulated": true, "install_simulation": "reports/install_simulation.json" @@ -78,7 +78,7 @@ "vscode" ], "package_metadata": "registry/packages/yao-meta-skill.json", - "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" + "package_sha256": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada" } ] }, diff --git a/reports/registry_audit.md b/reports/registry_audit.md index c4c4aa34..a2675846 100644 --- a/reports/registry_audit.md +++ b/reports/registry_audit.md @@ -6,8 +6,8 @@ - Maturity: `governed` - Owner: `Yao Team` - License: `MIT` -- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7` -- Archive SHA256: `1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35` +- Package SHA256: `c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada` +- Archive SHA256: `ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d` - Install simulated: `True` ## Compatibility diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json index 1f60be0f..dc3db9c8 100644 --- a/reports/security_trust_report.json +++ b/reports/security_trust_report.json @@ -2,8 +2,8 @@ "ok": true, "skill_dir": ".", "summary": { - "scanned_files": 204, - "script_count": 116, + "scanned_files": 205, + "script_count": 117, "internal_module_count": 32, "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": 71, + "file_write_script_count": 72, "permission_required_count": 3, "permission_approved_count": 3, "permission_missing_count": 0, "permission_invalid_count": 0, "permission_expired_count": 0, - "help_smoke_checked_count": 84, + "help_smoke_checked_count": 85, "help_smoke_failed_count": 0, "interactive_script_count": 0, "package_hash_scope": "source-contract-without-generated-reports", - "package_hash_file_count": 204, - "package_sha256": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" + "package_hash_file_count": 205, + "package_sha256": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada" }, "failures": [], "warnings": [], @@ -942,6 +942,20 @@ "network_urls": [], "network_hosts": [] }, + { + "path": "scripts/render_weekly_curator_report.py", + "interface": "cli", + "interface_declared": true, + "interface_reason": "Renders a weekly SkillOps curator report from generated reports without scanning private logs or writing source files.", + "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/render_world_class_claim_guard.py", "interface": "cli", @@ -1701,9 +1715,9 @@ "help_smoke": { "enabled": true, "timeout_seconds": 5.0, - "candidate_count": 84, - "checked_count": 84, - "passed_count": 84, + "candidate_count": 85, + "checked_count": 85, + "passed_count": 85, "failed_count": 0, "skipped_count": 32, "failed_scripts": [], @@ -2318,6 +2332,16 @@ "stdout_excerpt": "usage: render_telemetry_hook_recipes.py [-h] [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [--output-jsonl OUTPUT_JSONL]\n ", "stderr_excerpt": "" }, + { + "path": "scripts/render_weekly_curator_report.py", + "command": "python3 scripts/render_weekly_curator_report.py --help", + "returncode": 0, + "timed_out": false, + "passed": true, + "has_help_text": true, + "stdout_excerpt": "usage: render_weekly_curator_report.py [-h] [--daily-json DAILY_JSON]\n [--output-json OUTPUT_JSON]\n [--output-md OUTPUT_MD]\n [", + "stderr_excerpt": "" + }, { "path": "scripts/render_world_class_claim_guard.py", "command": "python3 scripts/render_world_class_claim_guard.py --help", @@ -2785,6 +2809,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md index b630a008..2a1a849f 100644 --- a/reports/security_trust_report.md +++ b/reports/security_trust_report.md @@ -1,22 +1,22 @@ # Security Trust Report - OK: `True` -- Scanned files: `204` -- Scripts: `116` +- Scanned files: `205` +- Scripts: `117` - Internal script modules: `32` - Secret findings: `0` - Network-capable scripts: `3` - Network policy covered scripts: `3` - Network policy missing scripts: `0` -- File-write scripts: `71` +- File-write scripts: `72` - Permission approvals: `3 / 3` - Permission approval gaps: `0` -- CLI help smoke checked: `84` +- CLI help smoke checked: `85` - CLI help smoke failures: `0` - Interactive scripts: `0` - Package hash scope: `source-contract-without-generated-reports` -- Package hash files: `204` -- Package SHA256: `7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7` +- Package hash files: `205` +- Package SHA256: `c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada` ## Failures @@ -54,8 +54,8 @@ - Enabled: `True` - Timeout seconds: `5.0` -- Checked scripts: `84` -- Passed scripts: `84` +- Checked scripts: `85` +- Passed scripts: `85` - Failed scripts: `none` ## Script Surface @@ -126,6 +126,7 @@ | scripts/render_social_preview.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/render_system_model.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | | scripts/render_telemetry_hook_recipes.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. | +| scripts/render_weekly_curator_report.py | cli | True | True | True | False | False | True | False | Renders a weekly SkillOps curator report from generated reports without scanning private logs or writing source files. | | scripts/render_world_class_claim_guard.py | cli | True | True | True | False | False | True | False | Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists. | | scripts/render_world_class_evidence_intake.py | cli | True | True | True | False | False | True | False | Validates world-class human and external evidence intake packets before ledger review. | | scripts/render_world_class_evidence_ledger.py | cli | True | True | True | False | False | True | False | Renders a machine-checkable ledger for world-class external and human evidence gaps. | diff --git a/reports/skill-os-2-review.md b/reports/skill-os-2-review.md index 94763334..4d62880d 100644 --- a/reports/skill-os-2-review.md +++ b/reports/skill-os-2-review.md @@ -41,6 +41,7 @@ Yao Meta Skill is no longer only a Meta Skill factory. The current working tree - Review Studio Output Lab actions now link directly to `reports/output_review_decisions.json`, so pending blind A/B reviewer decisions have a concrete template instead of only a general adjudication warning. - Output Review Adjudication now preserves blind-review integrity by hiding expected winners for pending or invalid reviewer decisions; answer keys are revealed only after a valid A/B decision exists for that case. - Provider Output Eval Runner v0 so `python3 scripts/yao.py output-exec --provider-runner openai` can collect real provider-backed model evidence through a reviewed OpenAI Responses API compatible runner instead of ad hoc shell glue. +- Weekly SkillOps Curator v0 so daily SkillOps opportunities, Skill Atlas portfolio signals, release-lock state, and world-class evidence gaps roll up into a proposal-only weekly maintenance queue without source-file writes. This is still not the final world-class state. Target-native behavior contracts are now explicit, VS Code / Copilot package metadata is auditable, local output-eval command execution is wired, blind-review answers remain hidden until valid decisions exist, a provider-backed output runner exists, installer-level permission coverage is now locally enforced during install simulation and local install sync, opt-in `yao.py` CLI telemetry can capture metadata-only real run signals, external clients can now emit one validated metadata-only event into a local spool, hook recipes now make Browser/Chrome/VS Code/wrapper/provider-adapter integration commands auditable, a Browser/Chrome Native Messaging host can receive length-prefixed metadata events and generate a local launcher plus manifest, validated external JSONL imports can bring those non-CLI client signals into the same drift loop, and Skill Atlas now consumes aggregate drift reports. Review Studio keeps pending human adjudication and pending world-class evidence visible as warnings instead of treating them as a clean pass. Deeper provider-native execution transforms, installed platform-native client telemetry implementations, provider-native installer integration, real provider holdout runs, real human adjudication decisions, accepted external evidence, and native runtime permission enforcement remain open. @@ -61,6 +62,7 @@ This is still not the final world-class state. Target-native behavior contracts | Review Studio 2.0 | `scripts/render_review_studio.py`, `reports/review-studio.html`, `reports/review-studio.json` with per-warning `review_actions` | v0 landed | | Review Studio Source Refs | `scripts/render_review_studio.py`, `tests/verify_review_studio.py`, `references/review-studio-method.md` | v0 landed | | Review Annotations | `scripts/render_review_annotations.py`, `reports/review_annotations.md`, `tests/verify_review_annotations.py`, Review Studio annotation panel and blocker decision hook | v0 landed | +| Weekly SkillOps Curator | `scripts/render_weekly_curator_report.py`, `reports/skillops/weekly/2026-W25.md`, `tests/verify_weekly_curator.py`, proposal-only maintenance queue with no source writes | v0 landed | | Skill Atlas | `scripts/build_skill_atlas.py`, `skill_atlas/catalog.json`, `skill_atlas/route_overlap_matrix.csv`, `skill_atlas/drift_signals.json`, `reports/skill_atlas.html` | v0 landed | | Registry & Distribution | `registry/*.schema.json`, `scripts/registry_audit.py`, `reports/registry_audit.md`, `registry/packages/yao-meta-skill.json` | v0 landed | | Package Verification | `scripts/verify_package.py`, `reports/package_verification.md`, `tests/verify_package_verification.py` | v0 landed | @@ -114,13 +116,13 @@ Next move: add real client or installer permission enforcement integration. | Output Eval | `5` cases, with-skill pass rate `100`, baseline pass rate `0`, with file-backed, near-neighbor, boundary coverage, `10` local command-runner execution runs, `0` recorded fixture runs, `0` provider model-executed runs in root release evidence, `10` estimated token counts, provider runner v0 available, `5` blind A/B review pairs, a generated `reports/output_review_decisions.json` template, `0 / 5` reviewer decisions pending, `0` answer keys revealed, and `5` pending answers hidden | | Runtime Conformance | `5 / 5` targets passing | | Target Compiler | `5 / 5` compiled target contracts generated for OpenAI, Claude, generic, Agent Skills compatible, and VS Code / Copilot outputs, including target permission contracts and target-native behavior contracts | -| Trust | `0` secret findings, `1` pinned dependency file, `32` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `84 / 84` CLI help smoke checks passing across `116` scripts, source-contract hash scope explicit | +| Trust | `0` secret findings, `1` pinned dependency file, `32` declared internal modules, `3 / 3` network-capable scripts covered by bounded host policy, `85 / 85` CLI help smoke checks passing across `117` scripts, source-contract hash scope explicit | | Permission Governance | `3 / 3` required high-permission capabilities approved, `0` missing, `0` invalid, `0` expired | | Runtime Permission Probes | `4 / 4` target adapters probed, `0` native-enforcement adapters, `4` explicit metadata fallbacks, `4` residual risks retained for reviewer visibility | | Skill Atlas | `12` scanned skills, `1` actionable root skill, `1` telemetry report, `0` actionable route collisions, `0` actionable owner gaps, `0` actionable stale skills, `0` actionable drift signals, `24` scoped non-actionable issue signals retained for visibility | | Registry Audit | package metadata generated with version, owner, license, source checksum, archive checksum, Skill IR provenance, and compatibility matrix | -| Package Verification | `4 / 4` target adapters present, archive verified, `634` zip entries, `0` failures, `0` warnings | -| Install Simulation | archive with `634` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | +| Package Verification | `4 / 4` target adapters present, archive verified, `639` zip entries, `0` failures, `0` warnings | +| Install Simulation | archive with `639` entries extracted into a local verification root, entrypoint/manifest/interface loaded, reports present, `4` adapters readable, `12` installer permission checks enforced, `0` permission failures, `0` failures, `0` warnings | | Local Install Sync Preflight | `make sync-local-install` and `make sync-active-install` rebuild the package first, then sync only after install simulation passes with `12` enforced installer permission checks and `0` permission failures | | Upgrade Check | current package declares `minor` over the 1.0.0 baseline, recommended bump is `minor`, and release notes include added targets plus checksum changes | | Adoption Drift | `1` metadata-only review event, `1` adoption sample, adoption `100`, risk band `low`; optional `yao.py` CLI capture, external client `telemetry-emit`, `5` `telemetry-hooks` recipes, Browser/Chrome native messaging host, and validated external JSONL import are available but off by default for reproducible release evidence; raw `reports/telemetry_events.jsonl` is gitignored and blocked from zip packages | @@ -133,7 +135,7 @@ Next move: add real client or installer permission enforcement integration. | Benchmark Reproducibility | local reproducibility ready with `25` required artifacts, `0` missing artifacts, `23` reproduction commands, and `3` disclosed failure cases; provider and human evidence remain explicit limitations | | IR-first Packaging | `openai`, `claude`, `generic`, and `vscode` adapters include compiler contracts, permission contracts, target-native behavior contracts, IR provenance, semantic parity checks, and install-scope notes where applicable | | Context Budget | initial load `990/1000`, under the production budget | -| CI | `make ci-test` target count is `79` after the SkillOps opportunity scoring gate update | +| CI | `make ci-test` target count is `80` after the Weekly SkillOps Curator gate update | ## Next Highest-Leverage Moves diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json index 55c53b1e..ce7f4621 100644 --- a/reports/skill_atlas.json +++ b/reports/skill_atlas.json @@ -128,6 +128,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py", diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json index 452ce92f..3545b190 100644 --- a/reports/skill_os2_audit.json +++ b/reports/skill_os2_audit.json @@ -197,7 +197,7 @@ "key": "trust-security", "label": "Trust Security", "status": "pass", - "current": "secrets 0; scripts 116; help failures 0", + "current": "secrets 0; scripts 117; help failures 0", "target": "Secrets, scripts, dependencies, permissions, and package hash are reviewable", "evidence": [ { @@ -285,7 +285,7 @@ "key": "registry-distribution", "label": "Registry Distribution", "status": "pass", - "current": "zip entries 634; install failures 0; permission failures 0", + "current": "zip entries 639; install failures 0; permission failures 0", "target": "Package metadata, archive checksum, package verification, and install simulation pass", "evidence": [ { diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md index 78d02ff4..eedb9998 100644 --- a/reports/skill_os2_audit.md +++ b/reports/skill_os2_audit.md @@ -23,11 +23,11 @@ Generated at: `2026-06-16` | Human Adjudication | human-required | 0/5 decisions; pending 5 | Real reviewer decisions recorded before claiming output review completion | Record real A/B choices in the decision template, then regenerate adjudication. | | Benchmark Reproducibility | pass | artifacts 25; missing 0; failures 3 | Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable | Keep the manifest current with every benchmark, package, and release evidence change. | | Runtime Conformance | pass | 5/5 targets pass | Target package structure, metadata, relative paths, and degradation notes pass | Keep target conformance fixtures updated as platform contracts change. | -| Trust Security | pass | secrets 0; scripts 116; 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 117; help failures 0 | Secrets, scripts, dependencies, permissions, and package hash are reviewable | Keep high-permission approvals scoped, expiring, and target-mapped. | | Permission Metadata | pass | 4/4 target probes pass; metadata fallback 4; installer enforcement 4 | Packaged adapters expose explicit permission metadata, residual risks, and installer enforcement evidence when available | Preserve residual-risk notes until real native enforcement exists. | | Native Permission Enforcement | external-required | native-enforced targets 0; installer-enforced targets 4 | At least one target/client enforces approved permissions at runtime | Integrate a real target-client or external installer runtime guard before claiming native permission enforcement. | | Skill Atlas | pass | 12 skills; actionable collisions 0 | Workspace catalog, route overlap, stale/owner gaps, drift, and no-route opportunities | Feed real drift data into Atlas once client telemetry is installed. | -| Registry Distribution | pass | zip entries 634; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. | +| Registry Distribution | pass | zip entries 639; 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. | diff --git a/reports/skill_os2_coverage.json b/reports/skill_os2_coverage.json index c7a35e63..7ebadab0 100644 --- a/reports/skill_os2_coverage.json +++ b/reports/skill_os2_coverage.json @@ -10,10 +10,10 @@ "pass_count": 21, "warn_count": 0, "missing_count": 0, - "extension_track_count": 3, + "extension_track_count": 4, "extension_partial_count": 0, "extension_planned_count": 0, - "extension_covered_count": 3, + "extension_covered_count": 4, "adaptive_extension_ready": true, "local_blueprint_ready": true, "public_world_class_ready": false, @@ -26,7 +26,7 @@ "missing": 0 }, "extension_status_counts": { - "covered": 3 + "covered": 4 }, "modules": [ { @@ -130,7 +130,7 @@ "label": "Trust Security", "status": "pass", "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.", - "current": "116 scripts; secrets 0; help failures 0", + "current": "117 scripts; secrets 0; help failures 0", "command": "python3 scripts/yao.py trust .", "test": "python3 tests/verify_trust_check.py", "evidence": [ @@ -204,7 +204,7 @@ "label": "Registry Distribution", "status": "pass", "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.", - "current": "archive entries 634; install failures 0", + "current": "archive entries 639; 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": [ @@ -758,6 +758,33 @@ } ], "next_action": "Keep Daily SkillOps report aligned with proposal, approval, coverage, and world-class ledger contracts as the operations layer evolves." + }, + { + "key": "weekly-curator-report", + "label": "Weekly Curator Report", + "status": "covered", + "objective": "Weekly curator layer aggregates Daily SkillOps opportunities, Skill Atlas portfolio signals, release locks, and world-class evidence gaps into a maintenance queue.", + "current": "Weekly curator report is CLI-backed, proposal-only, and backed by committed weekly JSON/Markdown evidence.", + "target": "Generate reports/skillops/weekly/YYYY-WNN.* without private log scanning, source writes, auto-patching, or world-class overclaiming.", + "evidence": [ + { + "path": "scripts/render_weekly_curator_report.py", + "exists": true + }, + { + "path": "tests/verify_weekly_curator.py", + "exists": true + }, + { + "path": "reports/skillops/weekly/2026-W25.json", + "exists": true + }, + { + "path": "reports/skillops/weekly/2026-W25.md", + "exists": true + } + ], + "next_action": "Use weekly curator output as the Skill Librarian maintenance queue before approving any durable skill-library changes." } ], "next_highest_leverage": [ @@ -770,7 +797,7 @@ "title": "Skill Overview / Skill OS 2.0 upgrade plan", "core_module_count": 8, "recommended_pr_count": 13, - "reference_extension_count": 3, + "reference_extension_count": 4, "reference_extensions": [ "Skill interpretation report", "Adaptive self-iteration with local preference memory and approval gates", diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md index 99090853..3ec611e6 100644 --- a/reports/skill_os2_coverage.md +++ b/reports/skill_os2_coverage.md @@ -10,8 +10,8 @@ Generated at: `2026-06-16` - pass: `21` / `21` - missing: `0` - warn: `0` -- reference extensions: `3` -- extension covered: `3` +- reference extensions: `4` +- extension covered: `4` - extension partial: `0` - extension planned: `0` - adaptive extension ready: `true` @@ -26,9 +26,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` | | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` | | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` | -| Trust Security | `pass` | 116 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` | +| Trust Security | `pass` | 117 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 634; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` | +| Registry Distribution | `pass` | archive entries 639; 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` | @@ -57,6 +57,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts, | Skill Interpretation Report | `covered` | Skill Overview v2 is canonical and mirrored as first-class skill-interpretation HTML/JSON with schema and tests. | Either keep skill-overview as the canonical interpretation report with an explicit contract, or split a dedicated reports/skill-interpretation.* renderer and tests. | Keep overview and interpretation contracts in lockstep when report sections, metrics, or layout semantics change. | | Adaptive Self-Iteration | `covered` | Full adaptive loop includes proposal, approval, patch application, regression evidence, and rollback metadata. | Proposal-only adaptation with explicit input source, redaction, allowlisted write targets, approval ledger, regression report, and rollback plan. | Start with policy and read-only scan tests; do not read shell history or private logs unless the user provides an explicit source path. | | Daily SkillOps Report | `covered` | Daily SkillOps report is a CLI-backed, explicit-source operations cockpit with tests and committed dated evidence. | Generate reports/skillops/daily/YYYY-MM-DD.* from explicit sources without private log scanning, source writes, auto-patching, or world-class overclaiming. | Keep Daily SkillOps report aligned with proposal, approval, coverage, and world-class ledger contracts as the operations layer evolves. | +| Weekly Curator Report | `covered` | Weekly curator report is CLI-backed, proposal-only, and backed by committed weekly JSON/Markdown evidence. | Generate reports/skillops/weekly/YYYY-WNN.* without private log scanning, source writes, auto-patching, or world-class overclaiming. | Use weekly curator output as the Skill Librarian maintenance queue before approving any durable skill-library changes. | These extension tracks come from the user-supplied 2.0 reference plan. They are tracked separately from the formal Skill OS blueprint so the report can distinguish landed local architecture from planned explainer/adaptor evolution. @@ -236,3 +237,10 @@ These extension tracks come from the user-supplied 2.0 reference plan. They are - status: `covered` - existing evidence: `scripts/render_daily_skillops_report.py`, `tests/verify_daily_skillops.py`, `reports/skillops/daily/2026-06-16.json`, `reports/skillops/daily/2026-06-16.md` - next action: Keep Daily SkillOps report aligned with proposal, approval, coverage, and world-class ledger contracts as the operations layer evolves. + +### Weekly Curator Report + +- objective: Weekly curator layer aggregates Daily SkillOps opportunities, Skill Atlas portfolio signals, release locks, and world-class evidence gaps into a maintenance queue. +- status: `covered` +- existing evidence: `scripts/render_weekly_curator_report.py`, `tests/verify_weekly_curator.py`, `reports/skillops/weekly/2026-W25.json`, `reports/skillops/weekly/2026-W25.md` +- next action: Use weekly curator output as the Skill Librarian maintenance queue before approving any durable skill-library changes. diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json index fbecf450..8f7189ef 100644 --- a/reports/upgrade_check.json +++ b/reports/upgrade_check.json @@ -70,12 +70,12 @@ { "field": "archive_sha256", "from": "", - "to": "1d4626e5f8a27d7c708bb0e13f6f1aab44db25f9c5154b548fc5e70a52042a35" + "to": "ff4e46e4a22fee8a7bcd7c155b00df4ad4df7d9a85c939d657027fa6dea59d6d" }, { "field": "package_sha256", "from": "0000000000000000000000000000000000000000000000000000000000000000", - "to": "7de584946cac8f2ed241aa331ba4c0c2d69fa1c4eae2c06b92882b8af6ad07d7" + "to": "c29e7a583ec56e9ab8ec665f9a4e152e4135f0babb4806b4564e6aface56dada" } ] }, diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json index a4f2f9c3..18f8d5e4 100644 --- a/reports/world_class_claim_guard.json +++ b/reports/world_class_claim_guard.json @@ -6,9 +6,9 @@ "summary": { "ledger_ready_to_claim_world_class": false, "ledger_pending_count": 4, - "claim_surface_count": 178, - "json_claim_surface_count": 87, - "metadata_claim_surface_count": 88, + "claim_surface_count": 180, + "json_claim_surface_count": 88, + "metadata_claim_surface_count": 89, "package_claim_surface_count": 17, "violation_count": 0, "overclaim_guard_active": true, @@ -618,6 +618,14 @@ "path": "reports/skillops/daily/2026-06-16.md", "violation_count": 0 }, + { + "path": "reports/skillops/weekly/2026-W25.json", + "violation_count": 0 + }, + { + "path": "reports/skillops/weekly/2026-W25.md", + "violation_count": 0 + }, { "path": "reports/system-model.json", "violation_count": 0 diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md index ee6c3083..e33c9532 100644 --- a/reports/world_class_claim_guard.md +++ b/reports/world_class_claim_guard.md @@ -7,9 +7,9 @@ Generated at: `2026-06-16` - decision: `claim-guard-pass-evidence-pending` - ledger ready to claim world-class: `false` - ledger pending evidence: `4` -- claim surfaces scanned: `178` -- JSON claim surfaces scanned: `87` -- metadata claim surfaces scanned: `88` +- claim surfaces scanned: `180` +- JSON claim surfaces scanned: `88` +- metadata claim surfaces scanned: `89` - package/runtime claim surfaces scanned: `17` - violations: `0` - overclaim guard active: `true` diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json index 265edbc2..47156279 100644 --- a/skill_atlas/catalog.json +++ b/skill_atlas/catalog.json @@ -84,6 +84,7 @@ "scripts/render_social_preview.py", "scripts/render_system_model.py", "scripts/render_telemetry_hook_recipes.py", + "scripts/render_weekly_curator_report.py", "scripts/render_world_class_claim_guard.py", "scripts/render_world_class_evidence_intake.py", "scripts/render_world_class_evidence_ledger.py",