diff --git a/registry/index.json b/registry/index.json
index 116c2ed..56b1ac6 100644
--- a/registry/index.json
+++ b/registry/index.json
@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+      "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
     }
   ]
 }
diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json
index cbf7cda..d39e92e 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": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-    "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+    "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+    "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
   },
   "compatibility": {
     "openai": "pass",
@@ -48,7 +48,7 @@
   },
   "distribution": {
     "archive_verified": true,
-    "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+    "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
     "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 e4f5188..79a8134 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": "2026-06-13T18:27:31Z",
+  "generated_at": "2026-06-13T21:15:27Z",
   "skill_dir": ".",
   "privacy_contract": {
     "storage": "local-first",
diff --git a/reports/architecture_maintainability.json b/reports/architecture_maintainability.json
index 3bee2b4..ab12b24 100644
--- a/reports/architecture_maintainability.json
+++ b/reports/architecture_maintainability.json
@@ -4,27 +4,20 @@
   "generated_at": "2026-06-14",
   "skill_dir": ".",
   "summary": {
-    "python_file_count": 144,
-    "script_file_count": 88,
+    "python_file_count": 145,
+    "script_file_count": 89,
     "test_file_count": 56,
-    "internal_module_count": 17,
+    "internal_module_count": 18,
     "cli_script_count": 72,
-    "command_handler_count": 35,
+    "command_handler_count": 33,
     "warn_line_threshold": 900,
     "block_line_threshold": 1500,
-    "largest_file_lines": 1159,
-    "hotspot_count": 1,
+    "largest_file_lines": 887,
+    "hotspot_count": 0,
     "blocker_count": 0,
-    "decision": "watch-maintainability-hotspots"
+    "decision": "pass"
   },
   "largest_files": [
-    {
-      "path": "scripts/yao.py",
-      "lines": 1159,
-      "kind": "cli-script",
-      "severity": "warn",
-      "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-    },
     {
       "path": "scripts/render_review_studio.py",
       "lines": 887,
@@ -32,6 +25,13 @@
       "severity": "pass",
       "recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
     },
+    {
+      "path": "scripts/yao.py",
+      "lines": 839,
+      "kind": "cli-script",
+      "severity": "pass",
+      "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
+    },
     {
       "path": "tests/verify_yao_cli.py",
       "lines": 838,
@@ -103,22 +103,8 @@
       "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
     }
   ],
-  "hotspots": [
-    {
-      "path": "scripts/yao.py",
-      "lines": 1159,
-      "kind": "cli-script",
-      "severity": "warn",
-      "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-    }
-  ],
-  "actions": [
-    {
-      "path": "scripts/yao.py",
-      "severity": "warn",
-      "action": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-    }
-  ],
+  "hotspots": [],
+  "actions": [],
   "artifacts": {
     "json": "reports/architecture_maintainability.json",
     "markdown": "reports/architecture_maintainability.md"
diff --git a/reports/architecture_maintainability.md b/reports/architecture_maintainability.md
index bca50ca..f6f3263 100644
--- a/reports/architecture_maintainability.md
+++ b/reports/architecture_maintainability.md
@@ -4,31 +4,29 @@ Generated at: `2026-06-14`
 
 ## Summary
 
-- decision: `watch-maintainability-hotspots`
-- python files: `144`
-- scripts: `88`
+- decision: `pass`
+- python files: `145`
+- scripts: `89`
 - tests: `56`
-- internal modules: `17`
+- internal modules: `18`
 - CLI scripts: `72`
-- Yao CLI command handlers: `35`
-- largest file lines: `1159`
-- hotspots: `1`
+- Yao CLI command handlers: `33`
+- largest file lines: `887`
+- hotspots: `0`
 - blockers: `0`
 
 This report keeps maintainability risk visible before the Meta Skill grows more gates, renderers, and CLI commands.
 
 ## Hotspots
 
-| File | Lines | Kind | Severity | Recommended action |
-| --- | ---: | --- | --- | --- |
-| `scripts/yao.py` | `1159` | `cli-script` | `warn` | Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator. |
+No file-size hotspots found.
 
 ## Largest Files
 
 | File | Lines | Kind | Severity |
 | --- | ---: | --- | --- |
-| `scripts/yao.py` | `1159` | `cli-script` | `warn` |
 | `scripts/render_review_studio.py` | `887` | `cli-script` | `pass` |
+| `scripts/yao.py` | `839` | `cli-script` | `pass` |
 | `tests/verify_yao_cli.py` | `838` | `test` | `pass` |
 | `scripts/skill_report_model.py` | `782` | `internal-module` | `pass` |
 | `scripts/compile_skill.py` | `734` | `cli-script` | `pass` |
diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index 6fd9dad..fcde446 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,11 +3,11 @@
   "ok": true,
   "generated_at": "2026-06-14",
   "skill_dir": ".",
-  "commit": "479b098ccfe8756b15cbde1c8b97048ed53e9807",
+  "commit": "628acc5c35a9cf4cd0d3d684be50ee27724150ba",
   "git_status": {
     "available": true,
     "dirty": true,
-    "changed_file_count": 40,
+    "changed_file_count": 36,
     "sample": [
       "MM registry/index.json",
       "MM registry/packages/yao-meta-skill.json",
@@ -16,11 +16,11 @@
       "M  reports/architecture_maintainability.md",
       "MM reports/benchmark_reproducibility.json",
       "MM reports/benchmark_reproducibility.md",
-      "M  reports/compiled_targets.json",
-      "M  reports/context_budget.json",
+      "MM reports/context_budget.json",
       "M  reports/install_simulation.json",
       "MM reports/output_execution_runs.json",
-      "MM reports/output_execution_runs.md"
+      "MM reports/output_execution_runs.md",
+      "MM reports/package_verification.json"
     ]
   },
   "summary": {
@@ -42,7 +42,7 @@
     "world_class_task_count": 4,
     "world_class_ledger_pending_count": 4,
     "working_tree_dirty": true,
-    "changed_file_count": 40
+    "changed_file_count": 36
   },
   "methodology": {
     "path": "reports/benchmark_methodology.md",
@@ -115,8 +115,8 @@
       "label": "output_execution",
       "path": "reports/output_execution_runs.json",
       "exists": true,
-      "bytes": 7966,
-      "sha256": "d0eedcbfe9c349e51a3b99619a61fbcdb63dfbb91c6fc33d9826ba2f35aee653"
+      "bytes": 7964,
+      "sha256": "5d8dd9775201caadbb68d4514261bd17459cc580eea3d0b273c0034d4103f41a"
     },
     {
       "label": "blind_review",
@@ -150,43 +150,43 @@
       "label": "trust_report",
       "path": "reports/security_trust_report.json",
       "exists": true,
-      "bytes": 91352,
-      "sha256": "029777a16cc11e5b21f85c14e999f0d51f1a8f249803a9f601f13f0abe7b0e27"
+      "bytes": 91959,
+      "sha256": "e64df7a7d3a9f30dadc0133b96d2473dcdce458be6c3b7c1feaa3778bca3a864"
     },
     {
       "label": "python_compatibility",
       "path": "reports/python_compatibility.json",
       "exists": true,
-      "bytes": 19171,
-      "sha256": "8c3be56386b732d17891fe596131c926b2f9caae4da5212596c54606f407480f"
+      "bytes": 19297,
+      "sha256": "f65de3392609ef1e9e2b9dde7991ba0d84b3803b128bd0a1277b2453eb05b41c"
     },
     {
       "label": "registry_audit",
       "path": "reports/registry_audit.json",
       "exists": true,
       "bytes": 3183,
-      "sha256": "87a5c389da2bc79ce7e17de455afab0478533efea07b41957d9438f6d5aa4ce8"
+      "sha256": "1aeda726a6302c6b37a36d179a34d17c93277d7c798b3fb15044ce1c6632494d"
     },
     {
       "label": "package_verification",
       "path": "reports/package_verification.json",
       "exists": true,
       "bytes": 19325,
-      "sha256": "583dc48f80f27ec6400bf754c949a1bd2245a84c94ff7916d7ca08be7a54c35c"
+      "sha256": "9e12aa80888c3c2508ff0681bc1bddb5fcd308657f87695c02ced23dc214ff3f"
     },
     {
       "label": "install_simulation",
       "path": "reports/install_simulation.json",
       "exists": true,
       "bytes": 8557,
-      "sha256": "efbddb4eb6c7dd1749c1499002da0d9890f9404b3dad204b02970f44a0bd2899"
+      "sha256": "11985a19c3bcbe02fbe0146f57eb11992b3f298e99bad77149f0039787a96f18"
     },
     {
       "label": "skill_os2_audit",
       "path": "reports/skill_os2_audit.json",
       "exists": true,
       "bytes": 13946,
-      "sha256": "3066a5a9f46200667e2bc2e986bad281922d7546194f908594301930a0eeeac4"
+      "sha256": "0fcd7f82c65f1fd85323919e573e3b4910738684440acaf29ed2c6ebe26bd611"
     },
     {
       "label": "world_class_evidence_plan",
diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md
index 6598032..2e95676 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,7 +1,7 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-06-14`
-Commit: `479b098ccfe8756b15cbde1c8b97048ed53e9807`
+Commit: `628acc5c35a9cf4cd0d3d684be50ee27724150ba`
 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: `40`
+- changed files at generation: `36`
 
 This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete.
 
@@ -40,17 +40,17 @@ This report proves local benchmark reproducibility only. It keeps external provi
 | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
 | output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
 | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
-| output_execution | `reports/output_execution_runs.json` | present | `d0eedcbfe9c3` |
+| output_execution | `reports/output_execution_runs.json` | present | `5d8dd9775201` |
 | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
 | review_adjudication | `reports/output_review_adjudication.json` | present | `ddd9af90d42e` |
 | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
 | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
-| trust_report | `reports/security_trust_report.json` | present | `029777a16cc1` |
-| python_compatibility | `reports/python_compatibility.json` | present | `8c3be56386b7` |
-| registry_audit | `reports/registry_audit.json` | present | `87a5c389da2b` |
-| package_verification | `reports/package_verification.json` | present | `583dc48f80f2` |
-| install_simulation | `reports/install_simulation.json` | present | `efbddb4eb6c7` |
-| skill_os2_audit | `reports/skill_os2_audit.json` | present | `3066a5a9f462` |
+| trust_report | `reports/security_trust_report.json` | present | `e64df7a7d3a9` |
+| python_compatibility | `reports/python_compatibility.json` | present | `f65de3392609` |
+| registry_audit | `reports/registry_audit.json` | present | `1aeda726a630` |
+| package_verification | `reports/package_verification.json` | present | `9e12aa80888c` |
+| install_simulation | `reports/install_simulation.json` | present | `11985a19c3bc` |
+| skill_os2_audit | `reports/skill_os2_audit.json` | present | `0fcd7f82c65f` |
 | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `ed1274b7c18c` |
 | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `5ed043491c3d` |
 | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `124b9239d7f3` |
diff --git a/reports/context_budget.json b/reports/context_budget.json
index 83db2dd..edfbd7e 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": 1084834,
+    "other_text_tokens": 1084478,
     "estimated_initial_load_tokens": 944,
-    "estimated_total_text_tokens": 1085585,
-    "relevant_file_count": 475,
+    "estimated_total_text_tokens": 1085229,
+    "relevant_file_count": 477,
     "unused_resource_dirs": [],
     "quality_signal_points": 130,
     "quality_density": 137.7
diff --git a/reports/install_simulation.json b/reports/install_simulation.json
index d59ad17..30cde14 100644
--- a/reports/install_simulation.json
+++ b/reports/install_simulation.json
@@ -8,7 +8,7 @@
   "installed_skill_dir": "[temporary-install-root]/yao-meta-skill",
   "summary": {
     "archive_present": true,
-    "archive_entry_count": 556,
+    "archive_entry_count": 557,
     "archive_extracted": true,
     "entrypoint_loaded": true,
     "manifest_loaded": true,
diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json
index 72e7fdd..f059d17 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": 25.77,
+      "duration_ms": 31.86,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -62,7 +62,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 26.06,
+      "duration_ms": 31.95,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -85,7 +85,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.36,
+      "duration_ms": 32.1,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -113,7 +113,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.91,
+      "duration_ms": 31.57,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -136,7 +136,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.66,
+      "duration_ms": 31.44,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -164,7 +164,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.45,
+      "duration_ms": 30.59,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -187,7 +187,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 26.13,
+      "duration_ms": 28.84,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -214,7 +214,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.42,
+      "duration_ms": 28.9,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -237,7 +237,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.7,
+      "duration_ms": 28.78,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -266,7 +266,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 25.71,
+      "duration_ms": 28.9,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md
index 4bdbfc3..e93da56 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 | 25.77 | 33 | 0.0 | pass |
-| skill-package-contract | with_skill | command | local-output-eval-runner | 26.06 | 73 | 100.0 | pass |
-| output-eval-expectation | baseline | command | local-output-eval-runner | 25.36 | 36 | 0.0 | pass |
-| output-eval-expectation | with_skill | command | local-output-eval-runner | 25.91 | 80 | 100.0 | pass |
-| ir-before-packaging | baseline | command | local-output-eval-runner | 25.66 | 33 | 0.0 | pass |
-| ir-before-packaging | with_skill | command | local-output-eval-runner | 25.45 | 80 | 100.0 | pass |
-| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.13 | 36 | 0.0 | pass |
-| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.42 | 65 | 100.0 | pass |
-| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.7 | 37 | 0.0 | pass |
-| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.71 | 98 | 100.0 | pass |
+| skill-package-contract | baseline | command | local-output-eval-runner | 31.86 | 33 | 0.0 | pass |
+| skill-package-contract | with_skill | command | local-output-eval-runner | 31.95 | 73 | 100.0 | pass |
+| output-eval-expectation | baseline | command | local-output-eval-runner | 32.1 | 36 | 0.0 | pass |
+| output-eval-expectation | with_skill | command | local-output-eval-runner | 31.57 | 80 | 100.0 | pass |
+| ir-before-packaging | baseline | command | local-output-eval-runner | 31.44 | 33 | 0.0 | pass |
+| ir-before-packaging | with_skill | command | local-output-eval-runner | 30.59 | 80 | 100.0 | pass |
+| near-neighbor-boundary | baseline | command | local-output-eval-runner | 28.84 | 36 | 0.0 | pass |
+| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 28.9 | 65 | 100.0 | pass |
+| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.78 | 37 | 0.0 | pass |
+| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.9 | 98 | 100.0 | pass |
 
 ## Next Fixes
 
diff --git a/reports/package_verification.json b/reports/package_verification.json
index 23d4396..b418d11 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": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
-    "archive_entry_count": 556,
+    "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
+    "archive_entry_count": 557,
     "failure_count": 0,
     "warning_count": 0
   },
diff --git a/reports/package_verification.md b/reports/package_verification.md
index a1120ac..0965c98 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: `43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f`
+- Archive SHA256: `a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653`
 - Failures: `0`
 - Warnings: `0`
 
diff --git a/reports/python_compatibility.json b/reports/python_compatibility.json
index 2b3a638..e235bf3 100644
--- a/reports/python_compatibility.json
+++ b/reports/python_compatibility.json
@@ -5,7 +5,7 @@
   "root": ".",
   "summary": {
     "target_python": "3.11",
-    "file_count": 147,
+    "file_count": 148,
     "issue_count": 0,
     "syntax_error_count": 0,
     "fstring_311_violation_count": 0,
@@ -544,6 +544,12 @@
       "issue_count": 0,
       "issues": []
     },
+    {
+      "path": "scripts/yao_cli_create_commands.py",
+      "ok": true,
+      "issue_count": 0,
+      "issues": []
+    },
     {
       "path": "scripts/yao_cli_parser.py",
       "ok": true,
diff --git a/reports/python_compatibility.md b/reports/python_compatibility.md
index baac3d3..3df4d50 100644
--- a/reports/python_compatibility.md
+++ b/reports/python_compatibility.md
@@ -6,7 +6,7 @@ Generated at: `2026-06-14`
 
 - decision: `pass`
 - target python: `3.11`
-- files scanned: `147`
+- files scanned: `148`
 - issues: `0`
 - syntax errors: `0`
 - f-string 3.11 violations: `0`
diff --git a/reports/registry_audit.json b/reports/registry_audit.json
index 986f6e3..326615e 100644
--- a/reports/registry_audit.json
+++ b/reports/registry_audit.json
@@ -21,8 +21,8 @@
     "trust_level": "local",
     "license": "MIT",
     "checksums": {
-      "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-      "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+      "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+      "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
     },
     "compatibility": {
       "openai": "pass",
@@ -53,7 +53,7 @@
     },
     "distribution": {
       "archive_verified": true,
-      "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+      "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
       "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": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+        "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
       }
     ]
   },
diff --git a/reports/registry_audit.md b/reports/registry_audit.md
index 3e39ce1..f0f248b 100644
--- a/reports/registry_audit.md
+++ b/reports/registry_audit.md
@@ -6,8 +6,8 @@
 - Maturity: `governed`
 - Owner: `Yao Team`
 - License: `MIT`
-- Package SHA256: `38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc`
-- Archive SHA256: `43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f`
+- Package SHA256: `ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c`
+- Archive SHA256: `a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653`
 - Install simulated: `True`
 
 ## Compatibility
diff --git a/reports/review-studio.html b/reports/review-studio.html
index 4ad91ea..343b4e1 100644
--- a/reports/review-studio.html
+++ b/reports/review-studio.html
@@ -286,28 +286,28 @@
       <div class="decision">
         <span>审查结论</span>
         <strong>review</strong>
-        <span>Score 89/100</span>
+        <span>Score 91/100</span>
       </div>
     </header>
 
     <section>
       <h2>核心指标</h2>
-      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native enforcement targets</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>88 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>147 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>1</strong><p>1159 largest lines; 35 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>68 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>556 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
+      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native enforcement targets</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>89 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>148 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>887 largest lines; 33 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>68 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>557 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
     </section>
 
     <section>
       <h2>审查闸门</h2>
-      <div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 944/1000; quality density 137.7</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 88 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 147 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>架构维护</h3></div><p>144 Python files; 1 hotspot; 0 blockers; largest 1159 lines; 35 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 2 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
+      <div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 944/1000; quality density 137.7</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 89 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 148 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>145 Python files; 0 hotspots; 0 blockers; largest 887 lines; 33 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
     </section>
 
     <div class="twocol">
       <section><h2>阻断事项</h2><p class='muted'>无。</p></section>
-      <section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>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</span></li><li><strong>架构维护</strong><span>144 Python files; 1 hotspot; 0 blockers; largest 1159 lines; 35 CLI handlers</span></li><li><strong>人工批准</strong><span>0 active waivers; 2 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</span></li></ul></section>
+      <section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>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</span></li><li><strong>人工批准</strong><span>0 active waivers; 1 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</span></li></ul></section>
     </div>
 
     <section id="actions">
       <h2>修复动作</h2>
-      <div class="actions-grid"><article class='action-card warn'><div><span>关注</span><h3>输出实验</h3></div><p>补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。</p><small>没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。</small><dl><dt>修复位置</dt><dd>evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_decisions.json + reports/output_review_adjudication.md</dd><dt>验证命令</dt><dd><code>python3 scripts/adjudicate_output_review.py --write-template &amp;&amp; python3 scripts/yao.py output-review</code></dd></dl><ul class='source-ref-list'><li><a href='../evals/output/cases.jsonl'>evals/output/cases.jsonl:1</a><small>output eval cases · eval</small></li><li><a href='output_quality_scorecard.md'>reports/output_quality_scorecard.md:1</a><small>output scorecard · report</small></li><li><a href='output_execution_runs.md'>reports/output_execution_runs.md:1</a><small>output execution runs · report</small></li><li><a href='output_blind_review_pack.md'>reports/output_blind_review_pack.md:1</a><small>blind A/B review pack · report</small></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:5</a><small>review decisions template · report</small></li><li><a href='output_review_adjudication.md'>reports/output_review_adjudication.md:1</a><small>review adjudication · report</small></li></ul><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>架构维护</h3></div><p>处理大文件和 CLI command surface 的维护性热点，优先拆分稳定职责边界。</p><small>Meta Skill 的门禁、报告和 CLI 会持续增长；如果不把架构债纳入审查，后续能力会越来越难验证和迁移。</small><dl><dt>修复位置</dt><dd>reports/architecture_maintainability.md + scripts/yao.py + scripts/render_review_viewer.py</dd><dt>验证命令</dt><dd><code>python3 scripts/yao.py architecture-audit .</code></dd></dl><ul class='source-ref-list'><li><a href='architecture_maintainability.md'>reports/architecture_maintainability.md:1</a><small>architecture maintainability · report</small></li><li><a href='../scripts/yao.py'>scripts/yao.py:111</a><small>Yao CLI orchestrator · source</small></li><li><a href='../scripts/render_review_studio.py'>scripts/render_review_studio.py:121</a><small>Review Studio renderer · source</small></li><li><a href='../scripts/render_review_viewer.py'>scripts/render_review_viewer.py:18</a><small>review viewer renderer · source</small></li></ul><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>人工批准</h3></div><p>对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。</p><small>warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。</small><dl><dt>修复位置</dt><dd>reports/review_waivers.md</dd><dt>验证命令</dt><dd><code>python3 scripts/render_review_waivers.py .</code></dd></dl><ul class='source-ref-list'><li><a href='review_waivers.md'>reports/review_waivers.md:1</a><small>waiver ledger · report</small></li><li><a href='../references/review-waiver-method.md'>references/review-waiver-method.md:1</a><small>waiver method · method</small></li></ul><footer>reports/review_waivers.json <a href='review_waivers.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>世界证据</h3></div><p>补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。</p><small>世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。</small><dl><dt>修复位置</dt><dd>reports/world_class_evidence_ledger.md + reports/world_class_evidence_plan.md + reports/world_class_evidence_intake.md</dd><dt>验证命令</dt><dd><code>python3 scripts/yao.py world-class-ledger . &amp;&amp; python3 scripts/yao.py review-studio .</code></dd></dl><ul class='source-ref-list'><li><a href='world_class_evidence_ledger.md'>reports/world_class_evidence_ledger.md:1</a><small>world-class evidence ledger · report</small></li><li><a href='world_class_evidence_plan.md'>reports/world_class_evidence_plan.md:1</a><small>world-class evidence plan · report</small></li><li><a href='world_class_evidence_intake.md'>reports/world_class_evidence_intake.md:1</a><small>world-class evidence intake · report</small></li><li><a href='world_class_claim_guard.md'>reports/world_class_claim_guard.md:1</a><small>world-class claim guard · report</small></li><li><a href='../evidence/world_class/intake.schema.json'>evidence/world_class/intake.schema.json:4</a><small>evidence intake schema · schema</small></li><li><a href='../evidence/world_class/templates/provider-holdout.intake.json'>evidence/world_class/templates/provider-holdout.intake.json:3</a><small>provider intake template · template</small></li><li><a href='../evidence/world_class/templates/human-adjudication.intake.json'>evidence/world_class/templates/human-adjudication.intake.json:3</a><small>human intake template · template</small></li><li><a href='skill_os2_audit.md'>reports/skill_os2_audit.md:1</a><small>Skill OS 2.0 audit · report</small></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:6</a><small>human review decisions · report</small></li><li><a href='runtime_permission_probes.md'>reports/runtime_permission_probes.md:1</a><small>runtime permission probes · report</small></li><li><a href='adoption_drift_report.md'>reports/adoption_drift_report.md:1</a><small>adoption drift · report</small></li></ul><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>打开证据</a></footer></article></div>
+      <div class="actions-grid"><article class='action-card warn'><div><span>关注</span><h3>输出实验</h3></div><p>补足 output eval 覆盖、execution evidence、blind A/B 和 reviewer adjudication。</p><small>没有输出质量和人工盲评证据时，Skill 只能证明会触发，不能证明输出真的更好且经得起审查。</small><dl><dt>修复位置</dt><dd>evals/output/cases.jsonl + reports/output_quality_scorecard.md + reports/output_review_decisions.json + reports/output_review_adjudication.md</dd><dt>验证命令</dt><dd><code>python3 scripts/adjudicate_output_review.py --write-template &amp;&amp; python3 scripts/yao.py output-review</code></dd></dl><ul class='source-ref-list'><li><a href='../evals/output/cases.jsonl'>evals/output/cases.jsonl:1</a><small>output eval cases · eval</small></li><li><a href='output_quality_scorecard.md'>reports/output_quality_scorecard.md:1</a><small>output scorecard · report</small></li><li><a href='output_execution_runs.md'>reports/output_execution_runs.md:1</a><small>output execution runs · report</small></li><li><a href='output_blind_review_pack.md'>reports/output_blind_review_pack.md:1</a><small>blind A/B review pack · report</small></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:5</a><small>review decisions template · report</small></li><li><a href='output_review_adjudication.md'>reports/output_review_adjudication.md:1</a><small>review adjudication · report</small></li></ul><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>人工批准</h3></div><p>对保留的 warning 写入 reviewer、理由、范围和到期时间，或修掉 warning。</p><small>warning 可以被接受，但必须可审计、会过期，并且不能掩盖 blocker。</small><dl><dt>修复位置</dt><dd>reports/review_waivers.md</dd><dt>验证命令</dt><dd><code>python3 scripts/render_review_waivers.py .</code></dd></dl><ul class='source-ref-list'><li><a href='review_waivers.md'>reports/review_waivers.md:1</a><small>waiver ledger · report</small></li><li><a href='../references/review-waiver-method.md'>references/review-waiver-method.md:1</a><small>waiver method · method</small></li></ul><footer>reports/review_waivers.json <a href='review_waivers.md'>打开证据</a></footer></article><article class='action-card warn'><div><span>关注</span><h3>世界证据</h3></div><p>补齐 provider、真人盲评、原生权限执行和真实客户端遥测证据，或明确本次发布不声明 world-class 完成。</p><small>世界级结论必须来自已接受的外部/人工证据；计划、metadata fallback、待评审和本地命令都不能替代完成证据。</small><dl><dt>修复位置</dt><dd>reports/world_class_evidence_ledger.md + reports/world_class_evidence_plan.md + reports/world_class_evidence_intake.md</dd><dt>验证命令</dt><dd><code>python3 scripts/yao.py world-class-ledger . &amp;&amp; python3 scripts/yao.py review-studio .</code></dd></dl><ul class='source-ref-list'><li><a href='world_class_evidence_ledger.md'>reports/world_class_evidence_ledger.md:1</a><small>world-class evidence ledger · report</small></li><li><a href='world_class_evidence_plan.md'>reports/world_class_evidence_plan.md:1</a><small>world-class evidence plan · report</small></li><li><a href='world_class_evidence_intake.md'>reports/world_class_evidence_intake.md:1</a><small>world-class evidence intake · report</small></li><li><a href='world_class_claim_guard.md'>reports/world_class_claim_guard.md:1</a><small>world-class claim guard · report</small></li><li><a href='../evidence/world_class/intake.schema.json'>evidence/world_class/intake.schema.json:4</a><small>evidence intake schema · schema</small></li><li><a href='../evidence/world_class/templates/provider-holdout.intake.json'>evidence/world_class/templates/provider-holdout.intake.json:3</a><small>provider intake template · template</small></li><li><a href='../evidence/world_class/templates/human-adjudication.intake.json'>evidence/world_class/templates/human-adjudication.intake.json:3</a><small>human intake template · template</small></li><li><a href='skill_os2_audit.md'>reports/skill_os2_audit.md:1</a><small>Skill OS 2.0 audit · report</small></li><li><a href='output_review_decisions.json'>reports/output_review_decisions.json:6</a><small>human review decisions · report</small></li><li><a href='runtime_permission_probes.md'>reports/runtime_permission_probes.md:1</a><small>runtime permission probes · report</small></li><li><a href='adoption_drift_report.md'>reports/adoption_drift_report.md:1</a><small>adoption drift · report</small></li></ul><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>打开证据</a></footer></article></div>
     </section>
 
     <section id="annotations">
@@ -363,12 +363,12 @@
     </section>
 
     <section id="trust" class="twocol">
-      <div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>88</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc</code></dd></div></dl></div>
+      <div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>89</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c</code></dd></div></dl></div>
       <div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
     </section>
 
     <section class="twocol">
-      <div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>147</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
+      <div class="panel"><h2>Python 兼容</h2><dl class='kv-grid'><div><dt>目标 Python</dt><dd>3.11</dd></div><div><dt>文件数</dt><dd>148</dd></div><div><dt>问题数</dt><dd>0</dd></div><div><dt>语法错误</dt><dd>0</dd></div><div><dt>F-string 3.11</dt><dd>0</dd></div></dl></div>
       <div class="panel"><h2>解释器边界</h2><p>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。</p></div>
     </section>
 
@@ -393,7 +393,7 @@
     </section>
 
     <section id="waivers" class="twocol">
-      <div class="panel"><h2>人工批准</h2><p>0 active waivers; 2 warning gates still need reviewer decision</p></div>
+      <div class="panel"><h2>人工批准</h2><p>0 active waivers; 1 warning gates still need reviewer decision</p></div>
       <div class="panel"><h2>批准台账</h2><dl class='kv-grid'><div><dt>Waiver Count</dt><dd>0</dd></div><div><dt>Active Count</dt><dd>0</dd></div><div><dt>Expired Count</dt><dd>0</dd></div><div><dt>Invalid Count</dt><dd>0</dd></div><div><dt>覆盖 Gate</dt><dd>0</dd></div></dl></div>
     </section>
 
@@ -425,12 +425,12 @@
 
     <section id="registry" class="twocol">
       <div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
-      <div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f</code></dd></div></dl></div>
+      <div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653</code></dd></div></dl></div>
     </section>
 
     <section id="release" class="twocol">
       <div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
-      <div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>556</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f</code></dd></div></dl></div>
+      <div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>557</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653</code></dd></div></dl></div>
     </section>
 
     <section class="twocol">
diff --git a/reports/review-studio.json b/reports/review-studio.json
index 048ce02..f6b5cd0 100644
--- a/reports/review-studio.json
+++ b/reports/review-studio.json
@@ -4,11 +4,11 @@
   "skill_dir": ".",
   "summary": {
     "decision": "review",
-    "world_class_score": 89,
+    "world_class_score": 91,
     "gate_count": 16,
     "blocker_count": 0,
-    "warning_count": 4,
-    "action_count": 4,
+    "warning_count": 3,
+    "action_count": 3,
     "annotation_count": 0,
     "open_annotation_count": 0,
     "open_annotation_blocker_count": 0,
@@ -59,7 +59,7 @@
       "key": "trust-report",
       "label": "信任报告",
       "status": "pass",
-      "detail": "0 secrets; 88 scripts; 3 network-capable scripts; 0 help smoke failures",
+      "detail": "0 secrets; 89 scripts; 3 network-capable scripts; 0 help smoke failures",
       "evidence": "reports/security_trust_report.json",
       "link": "security_trust_report.md"
     },
@@ -67,15 +67,15 @@
       "key": "python-compat",
       "label": "Python 兼容",
       "status": "pass",
-      "detail": "Python 3.11; 147 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
+      "detail": "Python 3.11; 148 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards",
       "evidence": "reports/python_compatibility.json",
       "link": "python_compatibility.md"
     },
     {
       "key": "architecture-maintainability",
       "label": "架构维护",
-      "status": "warn",
-      "detail": "144 Python files; 1 hotspot; 0 blockers; largest 1159 lines; 35 CLI handlers",
+      "status": "pass",
+      "detail": "145 Python files; 0 hotspots; 0 blockers; largest 887 lines; 33 CLI handlers",
       "evidence": "reports/architecture_maintainability.json",
       "link": "architecture_maintainability.md"
     },
@@ -115,7 +115,7 @@
       "key": "review-waivers",
       "label": "人工批准",
       "status": "warn",
-      "detail": "0 active waivers; 2 warning gates still need reviewer decision",
+      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
       "evidence": "reports/review_waivers.json",
       "link": "review_waivers.md"
     },
@@ -154,19 +154,11 @@
       "evidence": "reports/output_quality_scorecard.json",
       "link": "output_quality_scorecard.md"
     },
-    {
-      "key": "architecture-maintainability",
-      "label": "架构维护",
-      "status": "warn",
-      "detail": "144 Python files; 1 hotspot; 0 blockers; largest 1159 lines; 35 CLI handlers",
-      "evidence": "reports/architecture_maintainability.json",
-      "link": "architecture_maintainability.md"
-    },
     {
       "key": "review-waivers",
       "label": "人工批准",
       "status": "warn",
-      "detail": "0 active waivers; 2 warning gates still need reviewer decision",
+      "detail": "0 active waivers; 1 warning gates still need reviewer decision",
       "evidence": "reports/review_waivers.json",
       "link": "review_waivers.md"
     },
@@ -242,52 +234,6 @@
       "evidence_link": "output_quality_scorecard.md",
       "verification_command": "python3 scripts/adjudicate_output_review.py --write-template && python3 scripts/yao.py output-review"
     },
-    {
-      "gate_key": "architecture-maintainability",
-      "label": "架构维护",
-      "status": "warn",
-      "priority": "warning",
-      "summary": "处理大文件和 CLI command surface 的维护性热点，优先拆分稳定职责边界。",
-      "why": "Meta Skill 的门禁、报告和 CLI 会持续增长；如果不把架构债纳入审查，后续能力会越来越难验证和迁移。",
-      "source_fix": "reports/architecture_maintainability.md + scripts/yao.py + scripts/render_review_viewer.py",
-      "source_refs": [
-        {
-          "path": "reports/architecture_maintainability.md",
-          "label": "architecture maintainability",
-          "kind": "report",
-          "line": 1,
-          "exists": true,
-          "link": "architecture_maintainability.md"
-        },
-        {
-          "path": "scripts/yao.py",
-          "label": "Yao CLI orchestrator",
-          "kind": "source",
-          "line": 111,
-          "exists": true,
-          "link": "../scripts/yao.py"
-        },
-        {
-          "path": "scripts/render_review_studio.py",
-          "label": "Review Studio renderer",
-          "kind": "source",
-          "line": 121,
-          "exists": true,
-          "link": "../scripts/render_review_studio.py"
-        },
-        {
-          "path": "scripts/render_review_viewer.py",
-          "label": "review viewer renderer",
-          "kind": "source",
-          "line": 18,
-          "exists": true,
-          "link": "../scripts/render_review_viewer.py"
-        }
-      ],
-      "evidence": "reports/architecture_maintainability.json",
-      "evidence_link": "architecture_maintainability.md",
-      "verification_command": "python3 scripts/yao.py architecture-audit ."
-    },
     {
       "gate_key": "review-waivers",
       "label": "人工批准",
@@ -891,7 +837,7 @@
             "path": "scripts",
             "label": "Deterministic helpers or local tooling",
             "kind": "folder",
-            "file_count": 88
+            "file_count": 89
           },
           {
             "path": "evals",
@@ -906,7 +852,7 @@
             "file_count": 195
           }
         ],
-        "file_count": 347,
+        "file_count": 348,
         "folder_count": 4,
         "distribution": [
           {
@@ -931,7 +877,7 @@
           },
           {
             "label": "scripts",
-            "value": 88
+            "value": 89
           },
           {
             "label": "evals",
@@ -1060,7 +1006,7 @@
           "path": "scripts",
           "label": "Deterministic helpers or local tooling",
           "kind": "folder",
-          "file_count": 88
+          "file_count": 89
         },
         {
           "path": "evals",
@@ -1360,9 +1306,9 @@
           "world_class_task_count": 4,
           "world_class_ledger_pending_count": 4,
           "working_tree_dirty": true,
-          "changed_file_count": 40
+          "changed_file_count": 36
         },
-        "commit": "479b098ccfe8756b15cbde1c8b97048ed53e9807",
+        "commit": "628acc5c35a9cf4cd0d3d684be50ee27724150ba",
         "missing_artifacts": [],
         "limitations": [
           "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -1437,9 +1383,9 @@
         "failures": []
       },
       "trust_security": {
-        "scanned_files": 172,
-        "script_count": 88,
-        "internal_module_count": 15,
+        "scanned_files": 173,
+        "script_count": 89,
+        "internal_module_count": 16,
         "secret_findings": 0,
         "dependency_files": [
           "requirements-ci.txt"
@@ -1457,8 +1403,8 @@
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 172,
-        "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+        "package_hash_file_count": 173,
+        "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
       },
       "skill_atlas": {
         "skill_count": 12,
@@ -1496,8 +1442,8 @@
           "trust_level": "local",
           "license": "MIT",
           "checksums": {
-            "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-            "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+            "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+            "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
           },
           "compatibility": {
             "openai": "pass",
@@ -1528,7 +1474,7 @@
           },
           "distribution": {
             "archive_verified": true,
-            "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+            "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
             "package_verification": "reports/package_verification.json",
             "install_simulated": true,
             "install_simulation": "reports/install_simulation.json"
@@ -1544,8 +1490,8 @@
           "target_count": 4,
           "adapter_count": 4,
           "archive_present": true,
-          "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
-          "archive_entry_count": 556,
+          "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
+          "archive_entry_count": 557,
           "failure_count": 0,
           "warning_count": 0
         },
@@ -1556,7 +1502,7 @@
         "ok": true,
         "summary": {
           "archive_present": true,
-          "archive_entry_count": 556,
+          "archive_entry_count": 557,
           "archive_extracted": true,
           "entrypoint_loaded": true,
           "manifest_loaded": true,
@@ -1623,12 +1569,12 @@
             {
               "field": "archive_sha256",
               "from": "",
-              "to": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+              "to": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
             },
             {
               "field": "package_sha256",
               "from": "0000000000000000000000000000000000000000000000000000000000000000",
-              "to": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+              "to": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
             }
           ]
         },
@@ -3745,7 +3691,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.77,
+          "duration_ms": 31.86,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3773,7 +3719,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 26.06,
+          "duration_ms": 31.95,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3796,7 +3742,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.36,
+          "duration_ms": 32.1,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3824,7 +3770,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.91,
+          "duration_ms": 31.57,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3847,7 +3793,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.66,
+          "duration_ms": 31.44,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3875,7 +3821,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.45,
+          "duration_ms": 30.59,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3898,7 +3844,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 26.13,
+          "duration_ms": 28.84,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3925,7 +3871,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.42,
+          "duration_ms": 28.9,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3948,7 +3894,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.7,
+          "duration_ms": 28.78,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3977,7 +3923,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 25.71,
+          "duration_ms": 28.9,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4408,7 +4354,7 @@
           "label": "Trust Security",
           "status": "pass",
           "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
-          "current": "88 scripts; secrets 0; help failures 0",
+          "current": "89 scripts; secrets 0; help failures 0",
           "command": "python3 scripts/yao.py trust .",
           "test": "python3 tests/verify_trust_check.py",
           "evidence": [
@@ -4482,7 +4428,7 @@
           "label": "Registry Distribution",
           "status": "pass",
           "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
-          "current": "archive entries 556; install failures 0",
+          "current": "archive entries 557; 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": [
@@ -4523,7 +4469,7 @@
           "label": "Review Studio",
           "status": "pass",
           "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
-          "current": "16 gates; decision review; warnings 4",
+          "current": "16 gates; decision review; warnings 3",
           "command": "python3 scripts/yao.py review-studio .",
           "test": "python3 tests/verify_review_studio.py",
           "evidence": [
@@ -9655,9 +9601,9 @@
       "ok": true,
       "skill_dir": ".",
       "summary": {
-        "scanned_files": 172,
-        "script_count": 88,
-        "internal_module_count": 15,
+        "scanned_files": 173,
+        "script_count": 89,
+        "internal_module_count": 16,
         "secret_findings": 0,
         "dependency_files": [
           "requirements-ci.txt"
@@ -9675,8 +9621,8 @@
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 172,
-        "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+        "package_hash_file_count": 173,
+        "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
       },
       "failures": [],
       "warnings": [],
@@ -10875,6 +10821,20 @@
           "network_urls": [],
           "network_hosts": []
         },
+        {
+          "path": "scripts/yao_cli_create_commands.py",
+          "interface": "internal-module",
+          "interface_declared": true,
+          "interface_reason": "Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator.",
+          "has_argparse": true,
+          "has_main_guard": false,
+          "uses_input": false,
+          "uses_network": false,
+          "uses_file_write": false,
+          "uses_subprocess": false,
+          "network_urls": [],
+          "network_hosts": []
+        },
         {
           "path": "scripts/yao_cli_parser.py",
           "interface": "internal-module",
@@ -10966,7 +10926,7 @@
         "checked_count": 73,
         "passed_count": 73,
         "failed_count": 0,
-        "skipped_count": 15,
+        "skipped_count": 16,
         "failed_scripts": [],
         "results": [
           {
@@ -11745,6 +11705,10 @@
             "path": "scripts/yao_cli_config.py",
             "reason": "internal module"
           },
+          {
+            "path": "scripts/yao_cli_create_commands.py",
+            "reason": "internal module"
+          },
           {
             "path": "scripts/yao_cli_parser.py",
             "reason": "internal module"
@@ -11942,7 +11906,7 @@
       "root": ".",
       "summary": {
         "target_python": "3.11",
-        "file_count": 147,
+        "file_count": 148,
         "issue_count": 0,
         "syntax_error_count": 0,
         "fstring_311_violation_count": 0,
@@ -12481,6 +12445,12 @@
           "issue_count": 0,
           "issues": []
         },
+        {
+          "path": "scripts/yao_cli_create_commands.py",
+          "ok": true,
+          "issue_count": 0,
+          "issues": []
+        },
         {
           "path": "scripts/yao_cli_parser.py",
           "ok": true,
@@ -12854,27 +12824,20 @@
       "generated_at": "2026-06-14",
       "skill_dir": ".",
       "summary": {
-        "python_file_count": 144,
-        "script_file_count": 88,
+        "python_file_count": 145,
+        "script_file_count": 89,
         "test_file_count": 56,
-        "internal_module_count": 17,
+        "internal_module_count": 18,
         "cli_script_count": 72,
-        "command_handler_count": 35,
+        "command_handler_count": 33,
         "warn_line_threshold": 900,
         "block_line_threshold": 1500,
-        "largest_file_lines": 1159,
-        "hotspot_count": 1,
+        "largest_file_lines": 887,
+        "hotspot_count": 0,
         "blocker_count": 0,
-        "decision": "watch-maintainability-hotspots"
+        "decision": "pass"
       },
       "largest_files": [
-        {
-          "path": "scripts/yao.py",
-          "lines": 1159,
-          "kind": "cli-script",
-          "severity": "warn",
-          "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-        },
         {
           "path": "scripts/render_review_studio.py",
           "lines": 887,
@@ -12882,6 +12845,13 @@
           "severity": "pass",
           "recommendation": "Move data loading and large section renderers into focused review_studio_* modules."
         },
+        {
+          "path": "scripts/yao.py",
+          "lines": 839,
+          "kind": "cli-script",
+          "severity": "pass",
+          "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
+        },
         {
           "path": "tests/verify_yao_cli.py",
           "lines": 838,
@@ -12953,22 +12923,8 @@
           "recommendation": "Watch this file before adding new responsibilities; extract a helper module when one concern dominates."
         }
       ],
-      "hotspots": [
-        {
-          "path": "scripts/yao.py",
-          "lines": 1159,
-          "kind": "cli-script",
-          "severity": "warn",
-          "recommendation": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-        }
-      ],
-      "actions": [
-        {
-          "path": "scripts/yao.py",
-          "severity": "warn",
-          "action": "Split command handlers by domain while keeping scripts/yao.py as the thin CLI orchestrator."
-        }
-      ],
+      "hotspots": [],
+      "actions": [],
       "artifacts": {
         "json": "reports/architecture_maintainability.json",
         "markdown": "reports/architecture_maintainability.md"
@@ -12982,10 +12938,10 @@
         "context_budget_tier": "production",
         "context_budget_limit": 1000,
         "skill_body_tokens": 751,
-        "other_text_tokens": 1084834,
+        "other_text_tokens": 1084478,
         "estimated_initial_load_tokens": 944,
-        "estimated_total_text_tokens": 1085585,
-        "relevant_file_count": 475,
+        "estimated_total_text_tokens": 1085229,
+        "relevant_file_count": 477,
         "unused_resource_dirs": [],
         "quality_signal_points": 130,
         "quality_density": 137.7
@@ -13933,6 +13889,7 @@
               "scripts/verify_package.py",
               "scripts/yao.py",
               "scripts/yao_cli_config.py",
+              "scripts/yao_cli_create_commands.py",
               "scripts/yao_cli_parser.py",
               "scripts/yao_cli_report_commands.py",
               "scripts/yao_cli_runtime.py",
@@ -14832,7 +14789,7 @@
     "adoption_drift": {
       "ok": true,
       "schema_version": "2.0",
-      "generated_at": "2026-06-13T18:27:31Z",
+      "generated_at": "2026-06-13T21:15:27Z",
       "skill_dir": ".",
       "privacy_contract": {
         "storage": "local-first",
@@ -15606,8 +15563,8 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-          "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+          "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+          "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
         },
         "compatibility": {
           "openai": "pass",
@@ -15638,7 +15595,7 @@
         },
         "distribution": {
           "archive_verified": true,
-          "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+          "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
           "package_verification": "reports/package_verification.json",
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
@@ -15663,7 +15620,7 @@
               "vscode"
             ],
             "package_metadata": "registry/packages/yao-meta-skill.json",
-            "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+            "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
           }
         ]
       },
@@ -15686,8 +15643,8 @@
         "target_count": 4,
         "adapter_count": 4,
         "archive_present": true,
-        "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
-        "archive_entry_count": 556,
+        "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
+        "archive_entry_count": 557,
         "failure_count": 0,
         "warning_count": 0
       },
@@ -16352,7 +16309,7 @@
       "installed_skill_dir": "[temporary-install-root]/yao-meta-skill",
       "summary": {
         "archive_present": true,
-        "archive_entry_count": 556,
+        "archive_entry_count": 557,
         "archive_extracted": true,
         "entrypoint_loaded": true,
         "manifest_loaded": true,
@@ -16694,12 +16651,12 @@
           {
             "field": "archive_sha256",
             "from": "",
-            "to": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+            "to": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
           },
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+            "to": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
           }
         ]
       },
diff --git a/reports/review-viewer.json b/reports/review-viewer.json
index afda420..96aa70a 100644
--- a/reports/review-viewer.json
+++ b/reports/review-viewer.json
@@ -437,7 +437,7 @@
           "path": "scripts",
           "label": "Deterministic helpers or local tooling",
           "kind": "folder",
-          "file_count": 88
+          "file_count": 89
         },
         {
           "path": "evals",
@@ -452,7 +452,7 @@
           "file_count": 195
         }
       ],
-      "file_count": 347,
+      "file_count": 348,
       "folder_count": 4,
       "distribution": [
         {
@@ -477,7 +477,7 @@
         },
         {
           "label": "scripts",
-          "value": 88
+          "value": 89
         },
         {
           "label": "evals",
@@ -606,7 +606,7 @@
         "path": "scripts",
         "label": "Deterministic helpers or local tooling",
         "kind": "folder",
-        "file_count": 88
+        "file_count": 89
       },
       {
         "path": "evals",
@@ -906,9 +906,9 @@
         "world_class_task_count": 4,
         "world_class_ledger_pending_count": 4,
         "working_tree_dirty": true,
-        "changed_file_count": 40
+        "changed_file_count": 36
       },
-      "commit": "479b098ccfe8756b15cbde1c8b97048ed53e9807",
+      "commit": "628acc5c35a9cf4cd0d3d684be50ee27724150ba",
       "missing_artifacts": [],
       "limitations": [
         "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -983,9 +983,9 @@
       "failures": []
     },
     "trust_security": {
-      "scanned_files": 172,
-      "script_count": 88,
-      "internal_module_count": 15,
+      "scanned_files": 173,
+      "script_count": 89,
+      "internal_module_count": 16,
       "secret_findings": 0,
       "dependency_files": [
         "requirements-ci.txt"
@@ -1003,8 +1003,8 @@
       "help_smoke_failed_count": 0,
       "interactive_script_count": 0,
       "package_hash_scope": "source-contract-without-generated-reports",
-      "package_hash_file_count": 172,
-      "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+      "package_hash_file_count": 173,
+      "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
     },
     "skill_atlas": {
       "skill_count": 12,
@@ -1042,8 +1042,8 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-          "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+          "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+          "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
         },
         "compatibility": {
           "openai": "pass",
@@ -1074,7 +1074,7 @@
         },
         "distribution": {
           "archive_verified": true,
-          "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+          "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
           "package_verification": "reports/package_verification.json",
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
@@ -1090,8 +1090,8 @@
         "target_count": 4,
         "adapter_count": 4,
         "archive_present": true,
-        "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
-        "archive_entry_count": 556,
+        "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
+        "archive_entry_count": 557,
         "failure_count": 0,
         "warning_count": 0
       },
@@ -1102,7 +1102,7 @@
       "ok": true,
       "summary": {
         "archive_present": true,
-        "archive_entry_count": 556,
+        "archive_entry_count": 557,
         "archive_extracted": true,
         "entrypoint_loaded": true,
         "manifest_loaded": true,
@@ -1169,12 +1169,12 @@
           {
             "field": "archive_sha256",
             "from": "",
-            "to": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+            "to": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
           },
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+            "to": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
           }
         ]
       },
diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json
index 8d7a9b1..c64f871 100644
--- a/reports/security_trust_report.json
+++ b/reports/security_trust_report.json
@@ -2,9 +2,9 @@
   "ok": true,
   "skill_dir": ".",
   "summary": {
-    "scanned_files": 172,
-    "script_count": 88,
-    "internal_module_count": 15,
+    "scanned_files": 173,
+    "script_count": 89,
+    "internal_module_count": 16,
     "secret_findings": 0,
     "dependency_files": [
       "requirements-ci.txt"
@@ -22,8 +22,8 @@
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 172,
-    "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+    "package_hash_file_count": 173,
+    "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
   },
   "failures": [],
   "warnings": [],
@@ -1222,6 +1222,20 @@
       "network_urls": [],
       "network_hosts": []
     },
+    {
+      "path": "scripts/yao_cli_create_commands.py",
+      "interface": "internal-module",
+      "interface_declared": true,
+      "interface_reason": "Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator.",
+      "has_argparse": true,
+      "has_main_guard": false,
+      "uses_input": false,
+      "uses_network": false,
+      "uses_file_write": false,
+      "uses_subprocess": false,
+      "network_urls": [],
+      "network_hosts": []
+    },
     {
       "path": "scripts/yao_cli_parser.py",
       "interface": "internal-module",
@@ -1313,7 +1327,7 @@
     "checked_count": 73,
     "passed_count": 73,
     "failed_count": 0,
-    "skipped_count": 15,
+    "skipped_count": 16,
     "failed_scripts": [],
     "results": [
       {
@@ -2092,6 +2106,10 @@
         "path": "scripts/yao_cli_config.py",
         "reason": "internal module"
       },
+      {
+        "path": "scripts/yao_cli_create_commands.py",
+        "reason": "internal module"
+      },
       {
         "path": "scripts/yao_cli_parser.py",
         "reason": "internal module"
diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md
index abcc5d3..14b1171 100644
--- a/reports/security_trust_report.md
+++ b/reports/security_trust_report.md
@@ -1,9 +1,9 @@
 # Security Trust Report
 
 - OK: `True`
-- Scanned files: `172`
-- Scripts: `88`
-- Internal script modules: `15`
+- Scanned files: `173`
+- Scripts: `89`
+- Internal script modules: `16`
 - Secret findings: `0`
 - Network-capable scripts: `3`
 - Network policy covered scripts: `3`
@@ -15,8 +15,8 @@
 - CLI help smoke failures: `0`
 - Interactive scripts: `0`
 - Package hash scope: `source-contract-without-generated-reports`
-- Package hash files: `172`
-- Package SHA256: `38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc`
+- Package hash files: `173`
+- Package SHA256: `ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c`
 
 ## Failures
 
@@ -146,6 +146,7 @@
 | scripts/verify_package.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/yao.py | cli | False | True | True | False | False | False | True | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/yao_cli_config.py | internal-module | True | False | False | False | False | False | False | Imported by yao.py for CLI target maps and side-effect-free shaping helpers. |
+| scripts/yao_cli_create_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator. |
 | scripts/yao_cli_parser.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep CLI parser declarations separate from command orchestration. |
 | scripts/yao_cli_report_commands.py | internal-module | True | True | False | False | False | False | False | Imported by yao.py to keep report and evidence command handlers out of the CLI orchestrator. |
 | scripts/yao_cli_runtime.py | internal-module | True | False | False | False | False | False | True | Imported by yao.py and command modules for shared subprocess execution and JSON payload parsing. |
diff --git a/reports/skill-overview.html b/reports/skill-overview.html
index 16c90cf..4d386a1 100644
--- a/reports/skill-overview.html
+++ b/reports/skill-overview.html
@@ -771,7 +771,7 @@
           <p><span data-lang="zh-CN">让 reviewer 快速确认关键文件、目录和资产分布。</span><span data-lang="en">Lets reviewers confirm key files, directories, and asset distribution quickly.</span></p>
         </div>
         <div class="two-col">
-          <figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="25.8 74.2" stroke-dashoffset="-3.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="71.0 29.0" stroke-dashoffset="-29.0" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">347项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
+          <figure class="chart-figure" data-chart="asset_donut"><svg viewBox="0 0 430 270" role="img" aria-label="资产分布"><text x="20" y="30" class="chart-title">资产分布</text><circle cx="130" cy="130" r="70" fill="none" stroke="#1B365D" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="0.0" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#2D5A8A" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-0.8" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-1.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.8 99.2" stroke-dashoffset="-2.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="25.6 74.4" stroke-dashoffset="-3.2" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="71.2 28.8" stroke-dashoffset="-28.8" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">348项</text><text x="235" y="78">SKILL.md</text><text x="235" y="100">README.md</text><text x="235" y="122">agents/interface.yaml</text><text x="235" y="144">manifest.json</text><text x="235" y="166">references</text><text x="235" y="188">scripts</text></svg><figcaption>资产分布图展示当前包体的文件和目录重心。</figcaption></figure>
           <table>
             <thead><tr><th><span data-lang="zh-CN">路径</span><span data-lang="en">Path</span></th><th><span data-lang="zh-CN">作用</span><span data-lang="en">Role</span></th><th><span data-lang="zh-CN">类型</span><span data-lang="en">Type</span></th></tr></thead>
             <tbody><tr><td>SKILL.md</td><td><span data-lang="zh-CN">Skill 入口文件</span><span data-lang="en">Skill entrypoint</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>README.md</td><td><span data-lang="zh-CN">人类可读使用说明</span><span data-lang="en">Human-readable usage guide</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>agents/interface.yaml</td><td><span data-lang="zh-CN">跨平台接口元数据</span><span data-lang="en">Neutral interface metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>manifest.json</td><td><span data-lang="zh-CN">生命周期与打包元数据</span><span data-lang="en">Lifecycle and portability metadata</span></td><td><span data-lang="zh-CN">文件</span><span data-lang="en">file</span></td></tr><tr><td>references</td><td><span data-lang="zh-CN">扩展指导与复用资料</span><span data-lang="en">Extended guidance and reusable notes</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>scripts</td><td><span data-lang="zh-CN">确定性脚本或本地工具</span><span data-lang="en">Deterministic helpers or local tooling</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>evals</td><td><span data-lang="zh-CN">触发与质量检查</span><span data-lang="en">Trigger and quality checks</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr><tr><td>reports</td><td><span data-lang="zh-CN">生成的证据与总结报告</span><span data-lang="en">Generated evidence and overview artifacts</span></td><td><span data-lang="zh-CN">目录</span><span data-lang="en">folder</span></td></tr></tbody>
diff --git a/reports/skill-overview.json b/reports/skill-overview.json
index 06bf487..a16fd41 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": 88
+        "file_count": 89
       },
       {
         "path": "evals",
@@ -451,7 +451,7 @@
         "file_count": 195
       }
     ],
-    "file_count": 347,
+    "file_count": 348,
     "folder_count": 4,
     "distribution": [
       {
@@ -476,7 +476,7 @@
       },
       {
         "label": "scripts",
-        "value": 88
+        "value": 89
       },
       {
         "label": "evals",
@@ -605,7 +605,7 @@
       "path": "scripts",
       "label": "Deterministic helpers or local tooling",
       "kind": "folder",
-      "file_count": 88
+      "file_count": 89
     },
     {
       "path": "evals",
@@ -905,9 +905,9 @@
       "world_class_task_count": 4,
       "world_class_ledger_pending_count": 4,
       "working_tree_dirty": true,
-      "changed_file_count": 40
+      "changed_file_count": 36
     },
-    "commit": "479b098ccfe8756b15cbde1c8b97048ed53e9807",
+    "commit": "628acc5c35a9cf4cd0d3d684be50ee27724150ba",
     "missing_artifacts": [],
     "limitations": [
       "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -982,9 +982,9 @@
     "failures": []
   },
   "trust_security": {
-    "scanned_files": 172,
-    "script_count": 88,
-    "internal_module_count": 15,
+    "scanned_files": 173,
+    "script_count": 89,
+    "internal_module_count": 16,
     "secret_findings": 0,
     "dependency_files": [
       "requirements-ci.txt"
@@ -1002,8 +1002,8 @@
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 172,
-    "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+    "package_hash_file_count": 173,
+    "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
   },
   "skill_atlas": {
     "skill_count": 12,
@@ -1041,8 +1041,8 @@
       "trust_level": "local",
       "license": "MIT",
       "checksums": {
-        "package_sha256": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc",
-        "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+        "package_sha256": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c",
+        "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
       },
       "compatibility": {
         "openai": "pass",
@@ -1073,7 +1073,7 @@
       },
       "distribution": {
         "archive_verified": true,
-        "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
+        "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
         "package_verification": "reports/package_verification.json",
         "install_simulated": true,
         "install_simulation": "reports/install_simulation.json"
@@ -1089,8 +1089,8 @@
       "target_count": 4,
       "adapter_count": 4,
       "archive_present": true,
-      "archive_sha256": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f",
-      "archive_entry_count": 556,
+      "archive_sha256": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653",
+      "archive_entry_count": 557,
       "failure_count": 0,
       "warning_count": 0
     },
@@ -1101,7 +1101,7 @@
     "ok": true,
     "summary": {
       "archive_present": true,
-      "archive_entry_count": 556,
+      "archive_entry_count": 557,
       "archive_extracted": true,
       "entrypoint_loaded": true,
       "manifest_loaded": true,
@@ -1168,12 +1168,12 @@
         {
           "field": "archive_sha256",
           "from": "",
-          "to": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+          "to": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
         },
         {
           "field": "package_sha256",
           "from": "0000000000000000000000000000000000000000000000000000000000000000",
-          "to": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+          "to": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
         }
       ]
     },
diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json
index 99fd421..b7688da 100644
--- a/reports/skill_atlas.json
+++ b/reports/skill_atlas.json
@@ -148,6 +148,7 @@
           "scripts/verify_package.py",
           "scripts/yao.py",
           "scripts/yao_cli_config.py",
+          "scripts/yao_cli_create_commands.py",
           "scripts/yao_cli_parser.py",
           "scripts/yao_cli_report_commands.py",
           "scripts/yao_cli_runtime.py",
diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json
index dcd02ba..4e888c1 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 88; help failures 0",
+      "current": "secrets 0; scripts 89; 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 556; install failures 0; permission failures 0",
+      "current": "zip entries 557; install failures 0; permission failures 0",
       "target": "Package metadata, archive checksum, package verification, and install simulation pass",
       "evidence": [
         {
@@ -303,7 +303,7 @@
       "key": "review-studio",
       "label": "Review Studio",
       "status": "pass",
-      "current": "decision review; warnings 4; score 89",
+      "current": "decision review; warnings 3; score 91",
       "target": "One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations",
       "evidence": [
         {
diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md
index 7ab84c1..4d63f0f 100644
--- a/reports/skill_os2_audit.md
+++ b/reports/skill_os2_audit.md
@@ -23,12 +23,12 @@ 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 88; 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 89; 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 556; 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 4; score 89 | One page shows gates, evidence paths, blockers, warnings, actions, waivers, and annotations | Resolve human/external warning gates before claiming full release readiness. |
+| Registry Distribution | pass | zip entries 557; 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 4b7c0b4..5cae860 100644
--- a/reports/skill_os2_coverage.json
+++ b/reports/skill_os2_coverage.json
@@ -122,7 +122,7 @@
       "label": "Trust Security",
       "status": "pass",
       "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
-      "current": "88 scripts; secrets 0; help failures 0",
+      "current": "89 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 556; install failures 0",
+      "current": "archive entries 557; 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": [
@@ -237,7 +237,7 @@
       "label": "Review Studio",
       "status": "pass",
       "objective": "One HTML page supports first-pass production review across trigger, output, runtime, trust, release, and evidence actions.",
-      "current": "16 gates; decision review; warnings 4",
+      "current": "16 gates; decision review; warnings 3",
       "command": "python3 scripts/yao.py review-studio .",
       "test": "python3 tests/verify_review_studio.py",
       "evidence": [
diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md
index fb81cf6..73d5d6b 100644
--- a/reports/skill_os2_coverage.md
+++ b/reports/skill_os2_coverage.md
@@ -21,10 +21,10 @@ 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` | 88 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
+| Trust Security | `pass` | 89 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 556; 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 4 | `python3 scripts/yao.py review-studio .` | `python3 tests/verify_review_studio.py` |
+| Registry Distribution | `pass` | archive entries 557; 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` |
 
 ## Recommended PR Coverage
diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json
index 48fdcbc..5a8c664 100644
--- a/reports/upgrade_check.json
+++ b/reports/upgrade_check.json
@@ -70,12 +70,12 @@
       {
         "field": "archive_sha256",
         "from": "",
-        "to": "43e1251fe70c406ed6d0e5ec135bc2294492add1b5176427894f7df4dae8e14f"
+        "to": "a35cc5a6ebbbb278f826506ff52274ec65c8c5ffbdaa9dee2ef477d9dc409653"
       },
       {
         "field": "package_sha256",
         "from": "0000000000000000000000000000000000000000000000000000000000000000",
-        "to": "38e25604b3d11793a45c37b0680dc50e8233c5d0aecf982879109022fbed0cfc"
+        "to": "ac773f9145981816dd82890dd769bb608245fb14a5f6605db7e606d377ffcd9c"
       }
     ]
   },
diff --git a/scripts/yao.py b/scripts/yao.py
index 0066d60..322b4b9 100644
--- a/scripts/yao.py
+++ b/scripts/yao.py
@@ -2,26 +2,16 @@
 import argparse
 import json
 import subprocess
-import sys
 from pathlib import Path
 
-from github_benchmark_scan import build_query
-from render_intent_confidence import assess_intent_confidence
 from yao_cli_config import (
-    ARCHETYPE_MODE,
-    archetype_guidance,
     baseline_compare_args,
-    diagnose_skill_candidates,
-    diagnosis_note,
-    discovery_summary,
-    infer_archetype,
     local_output_runner_command,
     provider_output_runner_command,
-    recommendation_from_synthesis,
-    reference_visibility,
     resolve_promotion_target,
     resolve_target,
 )
+from yao_cli_create_commands import command_init, command_quickstart
 from yao_cli_parser import build_parser as build_cli_parser
 from yao_cli_report_commands import (
     command_artifact_design_profile,
@@ -49,316 +39,6 @@ from yao_cli_runtime import ROOT, run_script
 from yao_cli_telemetry import add_telemetry_args, maybe_record_cli_event
 
 
-def prompt_with_default(label: str, default: str) -> str:
-    sys.stderr.write(f"{label} [{default}]: ")
-    sys.stderr.flush()
-    value = sys.stdin.readline().strip()
-    return value or default
-
-
-def prompt_optional(label: str, default: str = "skip") -> str:
-    sys.stderr.write(f"{label} [{default}]: ")
-    sys.stderr.flush()
-    value = sys.stdin.readline().strip()
-    return value or default
-
-
-def prompt_optional_entries(label: str) -> list[str]:
-    sys.stderr.write(f"{label} [none]: ")
-    sys.stderr.flush()
-    value = sys.stdin.readline().strip()
-    if not value or value.lower() in {"none", "no", "n"}:
-        return []
-    return [item.strip() for item in value.split(",") if item.strip()]
-
-
-def update_context_slot(context: dict, slot: str, answer: str, list_mode: bool) -> None:
-    value = answer.strip()
-    if not value or value.lower() in {"skip", "none", "no", "n"}:
-        return
-    if list_mode:
-        context[slot] = [item.strip() for item in value.split(",") if item.strip()]
-    else:
-        context[slot] = value
-
-
-def intent_confidence_note(summary: dict) -> str:
-    lines = [
-        f"\nIntent confidence: {summary['score']}/100 ({summary['band']}).",
-        f"- Recommended action: {summary['recommended_action']}",
-    ]
-    if summary.get("gaps"):
-        top_gap = summary["gaps"][0]
-        lines.append(f"- Biggest gap: {top_gap['label']} — {top_gap['reason']}")
-    return "\n".join(lines) + "\n"
-
-
-def maybe_emit_update_notice(args: argparse.Namespace) -> None:
-    if getattr(args, "no_update_check", False):
-        return
-    result = run_script("check_update.py", [])
-    payload = result["payload"] if result["payload"] is not None else {}
-    if not result["ok"] and not payload:
-        return
-    if payload.get("update_available"):
-        sys.stderr.write(
-            "\nUpdate available for yao-meta-skill: "
-            f"{payload.get('local_version')} -> {payload.get('remote_version')}.\n"
-            f"Run: {payload.get('install_hint')}\n"
-        )
-
-
-def command_init(args: argparse.Namespace) -> int:
-    cmd = [
-        args.name,
-        "--description",
-        args.description,
-        "--output-dir",
-        args.output_dir,
-        "--mode",
-        args.mode,
-        "--archetype",
-        args.archetype,
-        *(["--title", args.title] if args.title else []),
-    ]
-    for reference in args.external_reference:
-        cmd.extend(["--external-reference", reference])
-    for reference in args.user_reference:
-        cmd.extend(["--user-reference", reference])
-    for constraint in args.local_constraint:
-        cmd.extend(["--local-constraint", constraint])
-    if args.github_query:
-        cmd.extend(["--github-query", args.github_query])
-    cmd.extend(["--github-top-n", str(args.github_top_n)])
-    if args.github_fixture_dir:
-        cmd.extend(["--github-fixture-dir", args.github_fixture_dir])
-    if args.intent_job:
-        cmd.extend(["--intent-job", args.intent_job])
-    for item in args.intent_real_input:
-        cmd.extend(["--intent-real-input", item])
-    if args.intent_primary_output:
-        cmd.extend(["--intent-primary-output", args.intent_primary_output])
-    for item in args.intent_exclusion:
-        cmd.extend(["--intent-exclusion", item])
-    for item in args.intent_constraint:
-        cmd.extend(["--intent-constraint", item])
-    for item in args.intent_standard:
-        cmd.extend(["--intent-standard", item])
-    if args.intent_correction:
-        cmd.extend(["--intent-correction", args.intent_correction])
-    result = run_script("init_skill.py", cmd)
-    print(json.dumps(result["payload"] if result["payload"] is not None else result, ensure_ascii=False, indent=2))
-    return 0 if result["ok"] else 2
-
-
-def command_quickstart(args: argparse.Namespace) -> int:
-    maybe_emit_update_notice(args)
-    sys.stderr.write("Let's start gently. You do not need a polished brief here.\n")
-    sys.stderr.write("Give me the real work in your own words, and I will help turn it into a clean first-pass skill.\n")
-    sys.stderr.write("While we shape the first pass, I will quietly check a few strong public patterns in the background and only surface them if there is real uncertainty or a design conflict.\n")
-    name = args.name or prompt_with_default("Skill name", "my-skill")
-    job = args.job or prompt_with_default(
-        "In your own words, what repeated work do you most want this skill to reliably handle",
-        "Turn a repeated workflow into a reusable skill.",
-    )
-    real_inputs = args.real_input or prompt_optional_entries(
-        "What material will people actually hand to this skill in practice (comma-separated)"
-    )
-    primary_output = args.primary_output or prompt_with_default(
-        "If it works beautifully, what should it hand back so you or the next person can keep moving",
-        "A reusable skill package.",
-    )
-    description = args.description or f"{job.rstrip('.')} Primary output: {primary_output.rstrip('.')}."
-    intent_context = {
-        "job": job,
-        "real_inputs": real_inputs,
-        "primary_output": primary_output,
-        "description": description,
-        "exclusions": [],
-        "constraints": [],
-        "standards": [],
-        "correction": "",
-        "user_references": [],
-    }
-    inferred_archetype, archetype_reason = infer_archetype(job, description)
-    guidance = archetype_guidance(inferred_archetype)
-    sys.stderr.write(discovery_summary(job, primary_output, inferred_archetype, guidance))
-    correction = prompt_optional(
-        "If I am off, what is the first thing I should correct before I package this idea",
-        "looks right",
-    )
-    if correction.lower() not in {"looks right", "skip", "none", "no"}:
-        description = f"{description.rstrip('.')} Keep this correction in scope: {correction.rstrip('.')}."
-        intent_context["description"] = description
-        intent_context["correction"] = correction
-        inferred_archetype, archetype_reason = infer_archetype(job, description)
-        guidance = archetype_guidance(inferred_archetype)
-        sys.stderr.write("\nThanks. I tightened the frame before moving on.\n")
-        sys.stderr.write(discovery_summary(job, primary_output, inferred_archetype, guidance))
-    confidence = assess_intent_confidence(intent_context)
-    sys.stderr.write(intent_confidence_note(confidence))
-    diagnosis = diagnose_skill_candidates(job, primary_output, inferred_archetype, confidence)
-    if diagnosis["fuzzy"]:
-        sys.stderr.write(diagnosis_note(diagnosis))
-    if not confidence["gate_passed"]:
-        sys.stderr.write("Before I package this idea, I want to close the highest-leverage gaps instead of guessing.\n")
-        for follow_up in confidence.get("follow_up_questions", [])[:2]:
-            answer = prompt_optional(follow_up["question"], "skip")
-            update_context_slot(intent_context, follow_up["slot"], answer, follow_up["list"])
-        confidence = assess_intent_confidence(intent_context)
-        sys.stderr.write("\nI tightened the intent frame once more before moving on.\n")
-        sys.stderr.write(intent_confidence_note(confidence))
-        diagnosis = diagnose_skill_candidates(job, primary_output, inferred_archetype, confidence)
-        if diagnosis["fuzzy"]:
-            sys.stderr.write(diagnosis_note(diagnosis))
-    archetype = args.archetype or prompt_with_default("I would start with this archetype (scaffold/production/library/governed)", inferred_archetype)
-    archetype = archetype if archetype in ARCHETYPE_MODE else inferred_archetype
-    default_mode = ARCHETYPE_MODE[archetype]
-    mode = args.mode or prompt_with_default("For the first pass, I would keep the mode here (scaffold/production/library/governed)", default_mode)
-    mode = mode if mode in ARCHETYPE_MODE.values() else default_mode
-    diagnosis = diagnose_skill_candidates(job, primary_output, archetype, confidence)
-    guidance = archetype_guidance(archetype)
-    sys.stderr.write(
-        f"\nGood. I will treat this as `{archetype}` in `{mode}` mode, so the first pass stays focused on {guidance['focus']}.\n"
-    )
-    user_references = args.user_reference or prompt_optional_entries(
-        "If there is anything you admire and want me to learn from as pattern hints, send it here (repo, product, page, workflow; comma-separated)"
-    )
-    external_references = args.external_reference or []
-    prompted_constraints = args.constraint if getattr(args, "constraint", None) else ([] if args.local_constraint else prompt_optional_entries(
-        "Tell me any local constraints I must keep in view (privacy, naming, compatibility; comma-separated)"
-    ))
-    local_constraints = args.local_constraint or prompted_constraints or intent_context.get("constraints", [])
-    intent_context["user_references"] = user_references
-    intent_context["constraints"] = local_constraints
-    confidence = assess_intent_confidence(intent_context)
-    github_query = args.github_query or build_query(" ".join(filter(None, [job, primary_output, description])))
-    title = args.title or name.replace("-", " ").title()
-    guidance = archetype_guidance(archetype)
-    cmd = [
-        name,
-        "--description",
-        description,
-        "--title",
-        title,
-        "--output-dir",
-        args.output_dir,
-        "--mode",
-        mode,
-        "--archetype",
-        archetype,
-        "--github-query",
-        github_query,
-        "--github-top-n",
-        str(args.github_top_n),
-        "--intent-job",
-        job,
-        "--intent-primary-output",
-        primary_output,
-    ]
-    for item in real_inputs:
-        cmd.extend(["--intent-real-input", item])
-    for item in intent_context.get("exclusions", []):
-        cmd.extend(["--intent-exclusion", item])
-    for item in intent_context.get("constraints", []):
-        cmd.extend(["--intent-constraint", item])
-    for item in intent_context.get("standards", []):
-        cmd.extend(["--intent-standard", item])
-    if intent_context.get("correction"):
-        cmd.extend(["--intent-correction", intent_context["correction"]])
-    if args.github_fixture_dir:
-        cmd.extend(["--github-fixture-dir", args.github_fixture_dir])
-    for reference in external_references:
-        cmd.extend(["--external-reference", reference])
-    for reference in user_references:
-        cmd.extend(["--user-reference", reference])
-    for constraint in local_constraints:
-        cmd.extend(["--local-constraint", constraint])
-    result = run_script("init_skill.py", cmd)
-    payload = result["payload"] if result["payload"] is not None else result
-    reference_synthesis = payload.get("reference_synthesis") or {}
-    visibility = reference_visibility(reference_synthesis)
-    recommendation = recommendation_from_synthesis(reference_synthesis, visibility)
-    sys.stderr.write(f"\nRecommendation: {recommendation['summary']}\n")
-    if visibility["user_decision_required"]:
-        if visibility["conflicts"]:
-            sys.stderr.write(f"I am surfacing this because there is a real design conflict: {visibility['conflicts'][0]['summary']}\n")
-        else:
-            sys.stderr.write("I am surfacing this because intent is still settling and the package should not deepen on guesswork.\n")
-    else:
-        sys.stderr.write("I will keep the underlying benchmark evidence in the reviewer reports and move ahead with this recommendation.\n")
-    if payload.get("report_view", {}).get("html_report"):
-        sys.stderr.write(f"Skill report: {payload['report_view']['html_report']}\n")
-
-    next_steps = [
-        "Open reports/skill-overview.html to review the generated Skill audit report.",
-        "Open reports/intent-dialogue.md and tighten the real job, outputs, and exclusions.",
-        "Open reports/review-studio.html to inspect the Review Studio 2.0 gate view before release.",
-        "Open reports/review-viewer.html to explain the package to a first-time reviewer.",
-        "Use reports/iteration-directions.md to choose only one high-value next move before adding more files.",
-    ]
-    if visibility["user_decision_required"]:
-        next_steps.insert(
-            1,
-            "Open reports/reference-synthesis.md if you want to inspect why the recommendation was surfaced and which tradeoff needs a call.",
-        )
-    report = {
-        "ok": result["ok"],
-        "root": payload.get("root"),
-        "mode": mode,
-        "archetype": archetype,
-        "artifacts": payload.get("artifacts", {}),
-        "report_view": payload.get("report_view", {}),
-        "intent_confidence": {
-            "score": confidence["score"],
-            "band": confidence["band"],
-            "gate_passed": confidence["gate_passed"],
-            "recommended_action": confidence["recommended_action"],
-        },
-        "recommendation": recommendation,
-        "reference_mode": {
-            "mode": visibility["mode"],
-            "user_decision_required": visibility["user_decision_required"],
-        },
-        "reviewer_evidence": {
-            "visibility": "full evidence in reports and review-viewer",
-            "artifacts": {
-                "benchmark_scan": payload.get("artifacts", {}).get("github_benchmark_scan_md"),
-                "reference_synthesis": payload.get("artifacts", {}).get("reference_synthesis_md"),
-                "artifact_design_profile": payload.get("artifacts", {}).get("artifact_design_profile_md"),
-                "prompt_quality_profile": payload.get("artifacts", {}).get("prompt_quality_profile_md"),
-                "system_model": payload.get("artifacts", {}).get("system_model_md"),
-                "review_studio": payload.get("artifacts", {}).get("review_studio_html"),
-                "review_viewer": payload.get("artifacts", {}).get("review_viewer_html"),
-            },
-        },
-        "guidance": {
-            "archetype_reason": archetype_reason,
-            "problem_diagnosis": diagnosis,
-            "why_this_mode": (
-                "Scaffold mode keeps the first package light and lets you postpone governance-heavy work until reuse becomes real."
-                if mode == "scaffold"
-                else "This mode expects stronger lifecycle metadata, validation, and review discipline."
-            ),
-            "first_gate": guidance["first_gate"],
-            "focus": guidance["focus"],
-            "next_steps": next_steps,
-            "experience_note": (
-                "The first pass should feel more like guided co-creation than a worksheet. "
-                "The system should make benchmark and pattern calls quietly unless there is a real reason to ask you to choose."
-            ),
-        },
-    }
-    if visibility["user_decision_required"]:
-        report["uncertainty_or_conflict"] = {
-            "reasons": visibility["reasons"],
-            "conflicts": visibility["conflicts"],
-            "note": "A design decision still needs your input before the package should be deepened.",
-        }
-    print(json.dumps(report, ensure_ascii=False, indent=2))
-    return 0 if result["ok"] else 2
-
-
 def command_validate(args: argparse.Namespace) -> int:
     skill_dir = str(Path(args.skill_dir).resolve())
     runs = [
diff --git a/scripts/yao_cli_create_commands.py b/scripts/yao_cli_create_commands.py
new file mode 100644
index 0000000..deea4cb
--- /dev/null
+++ b/scripts/yao_cli_create_commands.py
@@ -0,0 +1,334 @@
+#!/usr/bin/env python3
+"""Creation command handlers for the Yao CLI."""
+
+import argparse
+import json
+import sys
+
+from github_benchmark_scan import build_query
+from render_intent_confidence import assess_intent_confidence
+from yao_cli_config import (
+    ARCHETYPE_MODE,
+    archetype_guidance,
+    diagnose_skill_candidates,
+    diagnosis_note,
+    discovery_summary,
+    infer_archetype,
+    recommendation_from_synthesis,
+    reference_visibility,
+)
+from yao_cli_runtime import run_script
+
+
+SCRIPT_INTERFACE = "internal-module"
+SCRIPT_INTERFACE_REASON = "Imported by yao.py to keep skill creation and quickstart command handlers out of the CLI orchestrator."
+
+
+def prompt_with_default(label: str, default: str) -> str:
+    sys.stderr.write(f"{label} [{default}]: ")
+    sys.stderr.flush()
+    value = sys.stdin.readline().strip()
+    return value or default
+
+
+def prompt_optional(label: str, default: str = "skip") -> str:
+    sys.stderr.write(f"{label} [{default}]: ")
+    sys.stderr.flush()
+    value = sys.stdin.readline().strip()
+    return value or default
+
+
+def prompt_optional_entries(label: str) -> list[str]:
+    sys.stderr.write(f"{label} [none]: ")
+    sys.stderr.flush()
+    value = sys.stdin.readline().strip()
+    if not value or value.lower() in {"none", "no", "n"}:
+        return []
+    return [item.strip() for item in value.split(",") if item.strip()]
+
+
+def update_context_slot(context: dict, slot: str, answer: str, list_mode: bool) -> None:
+    value = answer.strip()
+    if not value or value.lower() in {"skip", "none", "no", "n"}:
+        return
+    if list_mode:
+        context[slot] = [item.strip() for item in value.split(",") if item.strip()]
+    else:
+        context[slot] = value
+
+
+def intent_confidence_note(summary: dict) -> str:
+    lines = [
+        f"\nIntent confidence: {summary['score']}/100 ({summary['band']}).",
+        f"- Recommended action: {summary['recommended_action']}",
+    ]
+    if summary.get("gaps"):
+        top_gap = summary["gaps"][0]
+        lines.append(f"- Biggest gap: {top_gap['label']} — {top_gap['reason']}")
+    return "\n".join(lines) + "\n"
+
+
+def maybe_emit_update_notice(args: argparse.Namespace) -> None:
+    if getattr(args, "no_update_check", False):
+        return
+    result = run_script("check_update.py", [])
+    payload = result["payload"] if result["payload"] is not None else {}
+    if not result["ok"] and not payload:
+        return
+    if payload.get("update_available"):
+        sys.stderr.write(
+            "\nUpdate available for yao-meta-skill: "
+            f"{payload.get('local_version')} -> {payload.get('remote_version')}.\n"
+            f"Run: {payload.get('install_hint')}\n"
+        )
+
+
+def command_init(args: argparse.Namespace) -> int:
+    cmd = [
+        args.name,
+        "--description",
+        args.description,
+        "--output-dir",
+        args.output_dir,
+        "--mode",
+        args.mode,
+        "--archetype",
+        args.archetype,
+        *(["--title", args.title] if args.title else []),
+    ]
+    for reference in args.external_reference:
+        cmd.extend(["--external-reference", reference])
+    for reference in args.user_reference:
+        cmd.extend(["--user-reference", reference])
+    for constraint in args.local_constraint:
+        cmd.extend(["--local-constraint", constraint])
+    if args.github_query:
+        cmd.extend(["--github-query", args.github_query])
+    cmd.extend(["--github-top-n", str(args.github_top_n)])
+    if args.github_fixture_dir:
+        cmd.extend(["--github-fixture-dir", args.github_fixture_dir])
+    if args.intent_job:
+        cmd.extend(["--intent-job", args.intent_job])
+    for item in args.intent_real_input:
+        cmd.extend(["--intent-real-input", item])
+    if args.intent_primary_output:
+        cmd.extend(["--intent-primary-output", args.intent_primary_output])
+    for item in args.intent_exclusion:
+        cmd.extend(["--intent-exclusion", item])
+    for item in args.intent_constraint:
+        cmd.extend(["--intent-constraint", item])
+    for item in args.intent_standard:
+        cmd.extend(["--intent-standard", item])
+    if args.intent_correction:
+        cmd.extend(["--intent-correction", args.intent_correction])
+    result = run_script("init_skill.py", cmd)
+    print(json.dumps(result["payload"] if result["payload"] is not None else result, ensure_ascii=False, indent=2))
+    return 0 if result["ok"] else 2
+
+
+def command_quickstart(args: argparse.Namespace) -> int:
+    maybe_emit_update_notice(args)
+    sys.stderr.write("Let's start gently. You do not need a polished brief here.\n")
+    sys.stderr.write("Give me the real work in your own words, and I will help turn it into a clean first-pass skill.\n")
+    sys.stderr.write("While we shape the first pass, I will quietly check a few strong public patterns in the background and only surface them if there is real uncertainty or a design conflict.\n")
+    name = args.name or prompt_with_default("Skill name", "my-skill")
+    job = args.job or prompt_with_default(
+        "In your own words, what repeated work do you most want this skill to reliably handle",
+        "Turn a repeated workflow into a reusable skill.",
+    )
+    real_inputs = args.real_input or prompt_optional_entries(
+        "What material will people actually hand to this skill in practice (comma-separated)"
+    )
+    primary_output = args.primary_output or prompt_with_default(
+        "If it works beautifully, what should it hand back so you or the next person can keep moving",
+        "A reusable skill package.",
+    )
+    description = args.description or f"{job.rstrip('.')} Primary output: {primary_output.rstrip('.')}."
+    intent_context = {
+        "job": job,
+        "real_inputs": real_inputs,
+        "primary_output": primary_output,
+        "description": description,
+        "exclusions": [],
+        "constraints": [],
+        "standards": [],
+        "correction": "",
+        "user_references": [],
+    }
+    inferred_archetype, archetype_reason = infer_archetype(job, description)
+    guidance = archetype_guidance(inferred_archetype)
+    sys.stderr.write(discovery_summary(job, primary_output, inferred_archetype, guidance))
+    correction = prompt_optional(
+        "If I am off, what is the first thing I should correct before I package this idea",
+        "looks right",
+    )
+    if correction.lower() not in {"looks right", "skip", "none", "no"}:
+        description = f"{description.rstrip('.')} Keep this correction in scope: {correction.rstrip('.')}."
+        intent_context["description"] = description
+        intent_context["correction"] = correction
+        inferred_archetype, archetype_reason = infer_archetype(job, description)
+        guidance = archetype_guidance(inferred_archetype)
+        sys.stderr.write("\nThanks. I tightened the frame before moving on.\n")
+        sys.stderr.write(discovery_summary(job, primary_output, inferred_archetype, guidance))
+    confidence = assess_intent_confidence(intent_context)
+    sys.stderr.write(intent_confidence_note(confidence))
+    diagnosis = diagnose_skill_candidates(job, primary_output, inferred_archetype, confidence)
+    if diagnosis["fuzzy"]:
+        sys.stderr.write(diagnosis_note(diagnosis))
+    if not confidence["gate_passed"]:
+        sys.stderr.write("Before I package this idea, I want to close the highest-leverage gaps instead of guessing.\n")
+        for follow_up in confidence.get("follow_up_questions", [])[:2]:
+            answer = prompt_optional(follow_up["question"], "skip")
+            update_context_slot(intent_context, follow_up["slot"], answer, follow_up["list"])
+        confidence = assess_intent_confidence(intent_context)
+        sys.stderr.write("\nI tightened the intent frame once more before moving on.\n")
+        sys.stderr.write(intent_confidence_note(confidence))
+        diagnosis = diagnose_skill_candidates(job, primary_output, inferred_archetype, confidence)
+        if diagnosis["fuzzy"]:
+            sys.stderr.write(diagnosis_note(diagnosis))
+    archetype = args.archetype or prompt_with_default("I would start with this archetype (scaffold/production/library/governed)", inferred_archetype)
+    archetype = archetype if archetype in ARCHETYPE_MODE else inferred_archetype
+    default_mode = ARCHETYPE_MODE[archetype]
+    mode = args.mode or prompt_with_default("For the first pass, I would keep the mode here (scaffold/production/library/governed)", default_mode)
+    mode = mode if mode in ARCHETYPE_MODE.values() else default_mode
+    diagnosis = diagnose_skill_candidates(job, primary_output, archetype, confidence)
+    guidance = archetype_guidance(archetype)
+    sys.stderr.write(
+        f"\nGood. I will treat this as `{archetype}` in `{mode}` mode, so the first pass stays focused on {guidance['focus']}.\n"
+    )
+    user_references = args.user_reference or prompt_optional_entries(
+        "If there is anything you admire and want me to learn from as pattern hints, send it here (repo, product, page, workflow; comma-separated)"
+    )
+    external_references = args.external_reference or []
+    prompted_constraints = args.constraint if getattr(args, "constraint", None) else ([] if args.local_constraint else prompt_optional_entries(
+        "Tell me any local constraints I must keep in view (privacy, naming, compatibility; comma-separated)"
+    ))
+    local_constraints = args.local_constraint or prompted_constraints or intent_context.get("constraints", [])
+    intent_context["user_references"] = user_references
+    intent_context["constraints"] = local_constraints
+    confidence = assess_intent_confidence(intent_context)
+    github_query = args.github_query or build_query(" ".join(filter(None, [job, primary_output, description])))
+    title = args.title or name.replace("-", " ").title()
+    guidance = archetype_guidance(archetype)
+    cmd = [
+        name,
+        "--description",
+        description,
+        "--title",
+        title,
+        "--output-dir",
+        args.output_dir,
+        "--mode",
+        mode,
+        "--archetype",
+        archetype,
+        "--github-query",
+        github_query,
+        "--github-top-n",
+        str(args.github_top_n),
+        "--intent-job",
+        job,
+        "--intent-primary-output",
+        primary_output,
+    ]
+    for item in real_inputs:
+        cmd.extend(["--intent-real-input", item])
+    for item in intent_context.get("exclusions", []):
+        cmd.extend(["--intent-exclusion", item])
+    for item in intent_context.get("constraints", []):
+        cmd.extend(["--intent-constraint", item])
+    for item in intent_context.get("standards", []):
+        cmd.extend(["--intent-standard", item])
+    if intent_context.get("correction"):
+        cmd.extend(["--intent-correction", intent_context["correction"]])
+    if args.github_fixture_dir:
+        cmd.extend(["--github-fixture-dir", args.github_fixture_dir])
+    for reference in external_references:
+        cmd.extend(["--external-reference", reference])
+    for reference in user_references:
+        cmd.extend(["--user-reference", reference])
+    for constraint in local_constraints:
+        cmd.extend(["--local-constraint", constraint])
+    result = run_script("init_skill.py", cmd)
+    payload = result["payload"] if result["payload"] is not None else result
+    reference_synthesis = payload.get("reference_synthesis") or {}
+    visibility = reference_visibility(reference_synthesis)
+    recommendation = recommendation_from_synthesis(reference_synthesis, visibility)
+    sys.stderr.write(f"\nRecommendation: {recommendation['summary']}\n")
+    if visibility["user_decision_required"]:
+        if visibility["conflicts"]:
+            sys.stderr.write(f"I am surfacing this because there is a real design conflict: {visibility['conflicts'][0]['summary']}\n")
+        else:
+            sys.stderr.write("I am surfacing this because intent is still settling and the package should not deepen on guesswork.\n")
+    else:
+        sys.stderr.write("I will keep the underlying benchmark evidence in the reviewer reports and move ahead with this recommendation.\n")
+    if payload.get("report_view", {}).get("html_report"):
+        sys.stderr.write(f"Skill report: {payload['report_view']['html_report']}\n")
+
+    next_steps = [
+        "Open reports/skill-overview.html to review the generated Skill audit report.",
+        "Open reports/intent-dialogue.md and tighten the real job, outputs, and exclusions.",
+        "Open reports/review-studio.html to inspect the Review Studio 2.0 gate view before release.",
+        "Open reports/review-viewer.html to explain the package to a first-time reviewer.",
+        "Use reports/iteration-directions.md to choose only one high-value next move before adding more files.",
+    ]
+    if visibility["user_decision_required"]:
+        next_steps.insert(
+            1,
+            "Open reports/reference-synthesis.md if you want to inspect why the recommendation was surfaced and which tradeoff needs a call.",
+        )
+    report = {
+        "ok": result["ok"],
+        "root": payload.get("root"),
+        "mode": mode,
+        "archetype": archetype,
+        "artifacts": payload.get("artifacts", {}),
+        "report_view": payload.get("report_view", {}),
+        "intent_confidence": {
+            "score": confidence["score"],
+            "band": confidence["band"],
+            "gate_passed": confidence["gate_passed"],
+            "recommended_action": confidence["recommended_action"],
+        },
+        "recommendation": recommendation,
+        "reference_mode": {
+            "mode": visibility["mode"],
+            "user_decision_required": visibility["user_decision_required"],
+        },
+        "reviewer_evidence": {
+            "visibility": "full evidence in reports and review-viewer",
+            "artifacts": {
+                "benchmark_scan": payload.get("artifacts", {}).get("github_benchmark_scan_md"),
+                "reference_synthesis": payload.get("artifacts", {}).get("reference_synthesis_md"),
+                "artifact_design_profile": payload.get("artifacts", {}).get("artifact_design_profile_md"),
+                "prompt_quality_profile": payload.get("artifacts", {}).get("prompt_quality_profile_md"),
+                "system_model": payload.get("artifacts", {}).get("system_model_md"),
+                "review_studio": payload.get("artifacts", {}).get("review_studio_html"),
+                "review_viewer": payload.get("artifacts", {}).get("review_viewer_html"),
+            },
+        },
+        "guidance": {
+            "archetype_reason": archetype_reason,
+            "problem_diagnosis": diagnosis,
+            "why_this_mode": (
+                "Scaffold mode keeps the first package light and lets you postpone governance-heavy work until reuse becomes real."
+                if mode == "scaffold"
+                else "This mode expects stronger lifecycle metadata, validation, and review discipline."
+            ),
+            "first_gate": guidance["first_gate"],
+            "focus": guidance["focus"],
+            "next_steps": next_steps,
+            "experience_note": (
+                "The first pass should feel more like guided co-creation than a worksheet. "
+                "The system should make benchmark and pattern calls quietly unless there is a real reason to ask you to choose."
+            ),
+        },
+    }
+    if visibility["user_decision_required"]:
+        report["uncertainty_or_conflict"] = {
+            "reasons": visibility["reasons"],
+            "conflicts": visibility["conflicts"],
+            "note": "A design decision still needs your input before the package should be deepened.",
+        }
+    print(json.dumps(report, ensure_ascii=False, indent=2))
+    return 0 if result["ok"] else 2
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json
index 845d458..d0f2529 100644
--- a/skill_atlas/catalog.json
+++ b/skill_atlas/catalog.json
@@ -104,6 +104,7 @@
         "scripts/verify_package.py",
         "scripts/yao.py",
         "scripts/yao_cli_config.py",
+        "scripts/yao_cli_create_commands.py",
         "scripts/yao_cli_parser.py",
         "scripts/yao_cli_report_commands.py",
         "scripts/yao_cli_runtime.py",
diff --git a/tests/verify_architecture_maintainability.py b/tests/verify_architecture_maintainability.py
index e21398a..1eb9e58 100644
--- a/tests/verify_architecture_maintainability.py
+++ b/tests/verify_architecture_maintainability.py
@@ -37,21 +37,21 @@ def main() -> None:
     )
     payload = json.loads(proc.stdout)
     assert payload["ok"], payload
-    assert payload["summary"]["decision"] == "watch-maintainability-hotspots", payload["summary"]
-    assert payload["summary"]["hotspot_count"] == 1, payload["summary"]
+    assert payload["summary"]["decision"] == "pass", payload["summary"]
+    assert payload["summary"]["hotspot_count"] == 0, payload["summary"]
     assert payload["summary"]["blocker_count"] == 0, payload["summary"]
     assert 30 <= payload["summary"]["command_handler_count"] < 50, payload["summary"]
-    assert payload["summary"]["largest_file_lines"] >= 900, payload["summary"]
-    assert payload["largest_files"][0]["path"] == "scripts/yao.py", payload["largest_files"][0]
-    assert payload["largest_files"][0]["severity"] == "warn", payload["largest_files"][0]
+    assert payload["summary"]["largest_file_lines"] < 900, payload["summary"]
+    assert payload["largest_files"][0]["path"] == "scripts/render_review_studio.py", payload["largest_files"][0]
+    assert payload["largest_files"][0]["severity"] == "pass", payload["largest_files"][0]
     hotspot_paths = {item["path"] for item in payload["hotspots"]}
-    assert {"scripts/yao.py"} <= hotspot_paths, hotspot_paths
+    assert "scripts/yao.py" not in hotspot_paths, hotspot_paths
     assert "scripts/render_review_studio.py" not in hotspot_paths, hotspot_paths
     assert "scripts/render_review_viewer.py" not in hotspot_paths, hotspot_paths
     assert output_json.exists(), output_json
     markdown = output_md.read_text(encoding="utf-8")
     assert "# Architecture Maintainability" in markdown, markdown
-    assert "Split command handlers by domain" in markdown, markdown
+    assert "No file-size hotspots found." in markdown, markdown
     assert "Do not split a file only for line count" in markdown, markdown
 
     blocker_proc = subprocess.run(
diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py
index 1565ca2..36357e5 100644
--- a/tests/verify_review_studio.py
+++ b/tests/verify_review_studio.py
@@ -276,16 +276,15 @@ def main() -> None:
     assert payload["schema_version"] == "2.0", payload
     assert payload["summary"]["decision"] == "review", payload
     assert payload["summary"]["gate_count"] == 16, payload
-    assert payload["summary"]["world_class_score"] == 89, payload
-    assert payload["summary"]["warning_count"] == 4, payload
+    assert payload["summary"]["world_class_score"] == 91, payload
+    assert payload["summary"]["warning_count"] == 3, payload
     assert payload["summary"]["blocker_count"] == 0, payload
-    assert payload["summary"]["action_count"] == 4, payload
+    assert payload["summary"]["action_count"] == 3, payload
     assert payload["summary"]["annotation_count"] == 0, payload
     assert payload["summary"]["open_annotation_blocker_count"] == 0, payload
     assert payload["summary"]["action_count"] == payload["summary"]["warning_count"] + payload["summary"]["blocker_count"], payload
     assert {item["gate_key"] for item in payload["review_actions"]} == {
         "output-lab",
-        "architecture-maintainability",
         "review-waivers",
         "world-class-evidence",
     }, payload
@@ -318,8 +317,8 @@ def main() -> None:
     assert "0 f-string 3.11 hazards" in python_compat_gate["detail"], python_compat_gate
     assert python_compat_gate["evidence"] == "reports/python_compatibility.json", python_compat_gate
     architecture_gate = next(item for item in payload["gates"] if item["key"] == "architecture-maintainability")
-    assert architecture_gate["status"] == "warn", architecture_gate
-    assert "1 hotspot" in architecture_gate["detail"], architecture_gate
+    assert architecture_gate["status"] == "pass", architecture_gate
+    assert "0 hotspots" in architecture_gate["detail"], architecture_gate
     assert "0 blockers" in architecture_gate["detail"], architecture_gate
     assert "CLI handlers" in architecture_gate["detail"], architecture_gate
     assert architecture_gate["evidence"] == "reports/architecture_maintainability.json", architecture_gate
@@ -345,7 +344,7 @@ def main() -> None:
     assert "reports/adoption_drift_report.json" in operations_gate["evidence"], operations_gate
     waivers_gate = next(item for item in payload["gates"] if item["key"] == "review-waivers")
     assert waivers_gate["status"] == "warn", waivers_gate
-    assert "2 warning gates still need reviewer decision" in waivers_gate["detail"], waivers_gate
+    assert "1 warning gates still need reviewer decision" in waivers_gate["detail"], waivers_gate
     assert "reports/review_waivers.json" in waivers_gate["evidence"], waivers_gate
     world_class_gate = next(item for item in payload["gates"] if item["key"] == "world-class-evidence")
     assert world_class_gate["status"] == "warn", world_class_gate
@@ -392,18 +391,10 @@ def main() -> None:
     assert full_payload["evidence_paths"]["runtime_permissions"] == "reports/runtime_permission_probes.md", full_payload["evidence_paths"]
     assert full_payload["data"]["python_compatibility"]["summary"]["target_python"] == "3.11", full_payload["data"]["python_compatibility"]
     assert full_payload["data"]["python_compatibility"]["summary"]["issue_count"] == 0, full_payload["data"]["python_compatibility"]
-    assert full_payload["data"]["architecture_maintainability"]["summary"]["hotspot_count"] == 1, full_payload["data"]["architecture_maintainability"]
+    assert full_payload["data"]["architecture_maintainability"]["summary"]["hotspot_count"] == 0, full_payload["data"]["architecture_maintainability"]
     assert full_payload["data"]["architecture_maintainability"]["summary"]["blocker_count"] == 0, full_payload["data"]["architecture_maintainability"]
     action_keys = {item["gate_key"] for item in full_payload["review_actions"]}
-    assert action_keys == {"output-lab", "architecture-maintainability", "review-waivers", "world-class-evidence"}, full_payload["review_actions"]
-    architecture_action = next(item for item in full_payload["review_actions"] if item["gate_key"] == "architecture-maintainability")
-    assert {item["path"] for item in architecture_action["source_refs"]} >= {
-        "reports/architecture_maintainability.md",
-        "scripts/yao.py",
-        "scripts/render_review_studio.py",
-        "scripts/render_review_viewer.py",
-    }, architecture_action
-    assert all(item["exists"] for item in architecture_action["source_refs"]), architecture_action
+    assert action_keys == {"output-lab", "review-waivers", "world-class-evidence"}, full_payload["review_actions"]
     world_class_action = next(item for item in full_payload["review_actions"] if item["gate_key"] == "world-class-evidence")
     assert {item["path"] for item in world_class_action["source_refs"]} >= {
         "reports/world_class_evidence_ledger.md",
@@ -527,7 +518,7 @@ def main() -> None:
     assert "架构维护" in html, html
     assert "Arch Debt" in html, html
     assert "reports/architecture_maintainability.md" in html, html
-    assert "处理大文件和 CLI command surface 的维护性热点" in html, html
+    assert "0 hotspots" in html, html
     assert "kv-grid" in html, html
     assert "案例数" in html, html
     assert "命令执行" in html, html
diff --git a/tests/verify_yao_cli.py b/tests/verify_yao_cli.py
index f24bb07..c5002cd 100644
--- a/tests/verify_yao_cli.py
+++ b/tests/verify_yao_cli.py
@@ -217,7 +217,7 @@ def main() -> None:
         "2026-06-14",
     )
     assert architecture_result["ok"], architecture_result
-    assert architecture_result["payload"]["summary"]["hotspot_count"] == 1, architecture_result
+    assert architecture_result["payload"]["summary"]["hotspot_count"] == 0, architecture_result
     assert architecture_result["payload"]["summary"]["blocker_count"] == 0, architecture_result
     assert 30 <= architecture_result["payload"]["summary"]["command_handler_count"] < 50, architecture_result