diff --git a/Makefile b/Makefile
index 16bda0f..318f212 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@ PYTHON ?= python3
 LOCAL_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills.disabled/yao-meta-skill
 ACTIVE_SKILL_INSTALL_DIR ?= $(HOME)/.agents/skills/yao-meta-skill
 
-.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean
+.PHONY: eval eval-suite route-scorecard route-confusion-check description-optimization judge-blind-eval description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger results-panel regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check sync-local-install sync-active-install test ci-test clean
 
 eval:
 	$(PYTHON) scripts/trigger_eval.py --description-file evals/improved_description.txt --cases evals/trigger_cases.json --baseline-description-file evals/baseline_description.txt
@@ -100,6 +100,9 @@ world-class-ledger-check:
 world-class-intake-check:
 	$(PYTHON) tests/verify_world_class_evidence_intake.py
 
+world-class-claim-guard-check:
+	$(PYTHON) tests/verify_world_class_claim_guard.py
+
 benchmark-reproducibility-check:
 	$(PYTHON) tests/verify_benchmark_reproducibility.py
 
@@ -217,11 +220,11 @@ sync-local-install: package-check
 sync-active-install: package-check
 	$(PYTHON) scripts/sync_local_install.py --install-dir "$(ACTIVE_SKILL_INSTALL_DIR)"
 
-test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check
+test: eval eval-suite route-scorecard route-confusion-check description-optimization description-optimization-check promotion-check yao-cli-check skill-overview-check skill-report-metrics-check skill-report-charts-check skill-ir-check compiler-check output-eval-check output-execution-check output-review-adjudication-check runtime-conformance-check runtime-permission-check trust-check skill-atlas-check registry-audit-check package-verify-check install-simulation-check upgrade-check review-viewer-check review-studio-check skill-os2-audit-check skill-os2-coverage-check world-class-evidence-check world-class-ledger-check world-class-intake-check world-class-claim-guard-check benchmark-reproducibility-check feedback-check adoption-drift-check telemetry-import-check telemetry-emit-check telemetry-hooks-check telemetry-native-host-check review-waivers-check review-annotations-check baseline-compare-check reference-scan-check github-benchmark-scan-check intent-confidence-check reference-synthesis-check output-risk-profile-check artifact-design-profile-check prompt-quality-profile-check system-model-check iteration-directions-check description-drift-history iteration-ledger regression-history context-reports portability-report portability-check failure-regression-check package-check package-failure-check security-boundary-check local-install-sync-check snapshot-check validate lint governance-check resource-boundary-check quality-check
 
 ci-test:
 	$(PYTHON) scripts/ci_test.py
 
 clean:
-	rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_skill_overview tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_skill_os2_audit tests/tmp_skill_os2_coverage tests/tmp_world_class_evidence tests/tmp_world_class_evidence_ledger tests/tmp_world_class_evidence_intake tests/tmp_benchmark_reproducibility tests/tmp_feedback tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_telemetry_native_host tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md
+	rm -rf dist tests/tmp tests/tmp_snapshot tests/tmp_cli tests/tmp_skill_overview tests/tmp_skill_report_metrics tests/tmp_skill_report_charts tests/tmp_skill_ir tests/tmp_compile_skill tests/tmp_output_eval tests/tmp_output_execution tests/tmp_output_review_adjudication tests/tmp_conformance tests/tmp_runtime_permission tests/tmp_trust tests/tmp_skill_atlas tests/tmp_registry tests/tmp_package_verification tests/tmp_install_simulation tests/tmp_upgrade_check tests/tmp_reference_scan tests/tmp_iteration_directions tests/tmp_review_viewer tests/tmp_review_studio tests/tmp_skill_os2_audit tests/tmp_skill_os2_coverage tests/tmp_world_class_evidence tests/tmp_world_class_evidence_ledger tests/tmp_world_class_evidence_intake tests/tmp_world_class_claim_guard tests/tmp_benchmark_reproducibility tests/tmp_feedback tests/tmp_adoption_drift tests/tmp_telemetry_import tests/tmp_telemetry_emit tests/tmp_telemetry_hooks tests/tmp_telemetry_native_host tests/tmp_review_waivers tests/tmp_review_annotations tests/tmp_github_benchmark_scan tests/tmp_intent_confidence tests/tmp_reference_synthesis tests/tmp_output_risk_profile tests/tmp_artifact_design_profile tests/tmp_prompt_quality_profile tests/tmp_system_model tests/tmp_security tests/tmp_baseline_compare.json tests/tmp_baseline_compare.md
 	find . -type d -name __pycache__ -prune -exec rm -rf {} +
diff --git a/README.md b/README.md
index 825758e..f12a8b5 100644
--- a/README.md
+++ b/README.md
@@ -28,6 +28,7 @@ It turns rough workflows, transcripts, prompts, notes, and runbooks into reusabl
 - a world-class evidence plan that turns remaining provider, human, native-permission, and real-client telemetry gaps into executable evidence tasks
 - a world-class evidence ledger that records which external and human evidence is accepted or still pending without treating planned work as proof
 - a world-class evidence intake contract that validates external and human evidence packets for provenance, privacy, artifact refs, and anti-overclaim rules before ledger review
+- a world-class claim guard that scans public claim surfaces and blocks premature completed/true claims while the evidence ledger still has pending external or human evidence
 - a benchmark reproducibility manifest that checks methodology sections, required artifacts, failure disclosure, and reproduction commands
 - Output Eval Lab evidence with assertion grading, execution/timing/token evidence, a blind A/B review pack, a separate answer key, and reviewer adjudication reports
 - a runtime permission probe report that checks packaged target adapters for explicit permission metadata, native-enforcement flags, metadata fallback notes, and residual risks
@@ -139,6 +140,11 @@ python3 scripts/yao.py registry-audit .
 python3 scripts/yao.py package-verify . --package-dir dist --require-zip
 python3 scripts/yao.py install-simulate . --package-dir dist
 python3 scripts/yao.py upgrade-check . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json
+python3 scripts/yao.py world-class-evidence .
+python3 scripts/yao.py world-class-ledger .
+python3 scripts/yao.py world-class-intake .
+python3 scripts/yao.py world-class-claim-guard .
+python3 scripts/yao.py benchmark-reproducibility .
 ```
 
 ## Local Development Source
@@ -287,6 +293,7 @@ Full reports: [reports/eval_suite.json](reports/eval_suite.json) and [reports/fa
 - remaining world-class evidence tasks are published in [reports/world_class_evidence_plan.md](reports/world_class_evidence_plan.md)
 - current world-class evidence acceptance state is published in [reports/world_class_evidence_ledger.md](reports/world_class_evidence_ledger.md)
 - world-class evidence intake readiness is published in [reports/world_class_evidence_intake.md](reports/world_class_evidence_intake.md)
+- world-class public claim guard status is published in [reports/world_class_claim_guard.md](reports/world_class_claim_guard.md)
 - benchmark reproducibility evidence is published in [reports/benchmark_reproducibility.md](reports/benchmark_reproducibility.md)
 - target compiler evidence is published in [reports/compiled_targets.md](reports/compiled_targets.md)
 - registry package metadata and audit status are published in [reports/registry_audit.md](reports/registry_audit.md)
@@ -403,7 +410,7 @@ Utility scripts that make the meta-skill operational:
 - `run_description_optimization_suite.py`: runs description optimization across the root skill and governed examples, then writes reusable reports and optional drift snapshots with calibration and family summaries
 - `promotion_checker.py`: applies promotion policy to current description candidates, writes promotion decisions, builds candidate registries, and emits iteration bundles with review stubs
 - `create_iteration_snapshot.py`: freezes the current promotion decision into a versioned release snapshot with review, route, and context evidence
-- `yao.py`: unified authoring CLI that exposes init, validate, optimize-description, promote-check, review, release-snapshot, workspace-flow, report, skill-ir, compile-skill, output-exec, output-review, skill-os2-audit, skill-os2-coverage, world-class-evidence, world-class-ledger, world-class-intake, benchmark-reproducibility, telemetry-emit, telemetry-hooks, telemetry-import, package, registry-audit, package-verify, install-simulate, upgrade-check, review-waivers, and test as one entrypoint
+- `yao.py`: unified authoring CLI that exposes init, validate, optimize-description, promote-check, review, release-snapshot, workspace-flow, report, skill-ir, compile-skill, output-exec, output-review, skill-os2-audit, skill-os2-coverage, world-class-evidence, world-class-ledger, world-class-intake, world-class-claim-guard, benchmark-reproducibility, telemetry-emit, telemetry-hooks, telemetry-import, package, registry-audit, package-verify, install-simulate, upgrade-check, review-waivers, and test as one entrypoint
 - `render_description_drift_history.py`: turns description-optimization snapshots into a readable drift-history report
 - `build_confusion_matrix.py`: scores route confusion across tracked sibling skills and `no_route` cases, then writes a route scorecard and optional milestone snapshot
 - `render_iteration_ledger.py`: compresses regression milestones, description optimization drift, and route scorecards into one iteration-facing ledger
@@ -417,6 +424,7 @@ Utility scripts that make the meta-skill operational:
 - `render_world_class_evidence_plan.py`: renders executable evidence tasks for remaining world-class gaps without treating planned external work as completed evidence
 - `render_world_class_evidence_ledger.py`: renders a machine-checkable ledger for current world-class evidence acceptance, anti-overclaim guards, provenance requirements, and privacy contracts
 - `render_world_class_evidence_intake.py`: validates world-class external and human evidence packets against provenance, privacy, artifact, and anti-overclaim requirements before ledger review
+- `render_world_class_claim_guard.py`: scans README, docs, and reports for premature world-class completion claims while accepted evidence is still pending
 - `render_benchmark_reproducibility.py`: renders methodology, artifact, failure-disclosure, and reproduction-command evidence for public benchmark claims
 - `cross_packager.py`: builds client-specific export artifacts from Skill IR plus neutral metadata, with explicit platform contracts and validation
 - `render_portability_report.py`: scores cross-environment portability from neutral metadata, degradation rules, and consumer validation coverage
diff --git a/registry/index.json b/registry/index.json
index b22a503..51a39cd 100644
--- a/registry/index.json
+++ b/registry/index.json
@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+      "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
     }
   ]
 }
diff --git a/registry/packages/yao-meta-skill.json b/registry/packages/yao-meta-skill.json
index 6a7c5bb..91b38b6 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": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1",
-    "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+    "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15",
+    "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
   },
   "compatibility": {
     "openai": "pass",
@@ -48,7 +48,7 @@
   },
   "distribution": {
     "archive_verified": true,
-    "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
+    "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
     "package_verification": "reports/package_verification.json",
     "install_simulated": true,
     "install_simulation": "reports/install_simulation.json"
diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json
index b9db34c..afc182e 100644
--- a/reports/benchmark_reproducibility.json
+++ b/reports/benchmark_reproducibility.json
@@ -3,13 +3,12 @@
   "ok": true,
   "generated_at": "2026-06-14",
   "skill_dir": ".",
-  "commit": "60995ed569b1c99aa6f6ae2b4406e04327202beb",
+  "commit": "c1c85093d1ea67954d414789f96c87bbc3964868",
   "git_status": {
     "available": true,
     "dirty": true,
-    "changed_file_count": 56,
+    "changed_file_count": 42,
     "sample": [
-      " M .gitignore",
       " M Makefile",
       " M README.md",
       " M registry/index.json",
@@ -20,17 +19,18 @@
       " M reports/context_budget.json",
       " M reports/install_simulation.json",
       " M reports/output_execution_runs.json",
-      " M reports/output_execution_runs.md"
+      " M reports/output_execution_runs.md",
+      " M reports/package_verification.json"
     ]
   },
   "summary": {
     "reproducibility_ready": true,
     "methodology_complete": true,
-    "required_artifact_count": 18,
+    "required_artifact_count": 19,
     "missing_artifact_count": 0,
     "output_case_count": 5,
     "failure_disclosure_count": 3,
-    "command_count": 17,
+    "command_count": 18,
     "command_executed_count": 10,
     "timing_observed_count": 10,
     "model_executed_count": 0,
@@ -42,7 +42,7 @@
     "world_class_task_count": 4,
     "world_class_ledger_pending_count": 4,
     "working_tree_dirty": true,
-    "changed_file_count": 56
+    "changed_file_count": 42
   },
   "methodology": {
     "path": "reports/benchmark_methodology.md",
@@ -115,8 +115,8 @@
       "label": "output_execution",
       "path": "reports/output_execution_runs.json",
       "exists": true,
-      "bytes": 7967,
-      "sha256": "8c40546b610c75ebb6dcee431cec4f603431c0c45ff49dcdc947473749c2f03e"
+      "bytes": 7966,
+      "sha256": "5a1eaa33c1cb916aa0962a9e826e97fc53fd9ca9bd6aa298ff91aa2068ff3415"
     },
     {
       "label": "blind_review",
@@ -150,36 +150,36 @@
       "label": "trust_report",
       "path": "reports/security_trust_report.json",
       "exists": true,
-      "bytes": 85082,
-      "sha256": "097f2a477efcc62b35ec8e94e2b800f7af6c207ad36fa096257972d0865a9dce"
+      "bytes": 86196,
+      "sha256": "1faacec874dd129b1d03cd53f93ee0abcb77fe6b5fbac7ab9726da23699ff4c1"
     },
     {
       "label": "registry_audit",
       "path": "reports/registry_audit.json",
       "exists": true,
       "bytes": 3183,
-      "sha256": "5c606b5a3b54bbdc814dc67a331d1c66756a9be25d16791bc53dd21ef19e07ec"
+      "sha256": "c796a29122c32df656421f25eb2fa13726c7dffd85c676d9c9218673777cb18c"
     },
     {
       "label": "package_verification",
       "path": "reports/package_verification.json",
       "exists": true,
       "bytes": 19325,
-      "sha256": "8dab6035e72ceda3756677d1ffa60aa7ad862c1af311899bb8a8dab198b750d7"
+      "sha256": "224f5f71478530766baac79902cf19da4abb800e256273168fbd9e51d763ff4d"
     },
     {
       "label": "install_simulation",
       "path": "reports/install_simulation.json",
       "exists": true,
       "bytes": 8557,
-      "sha256": "3b1456caa214bb0056943e110dbd0b2182faa5068b3a8fdb4272e9d8b38f759a"
+      "sha256": "ae7cccad47924b9f4e2572ae32a9f68209dead4741c982d81446d8ea8474b822"
     },
     {
       "label": "skill_os2_audit",
       "path": "reports/skill_os2_audit.json",
       "exists": true,
       "bytes": 13946,
-      "sha256": "5b7c9427a3403d989651fad9cfe38e9dc2c859513fb6c3bd7a5574a7656883a2"
+      "sha256": "3f1c6fdf7b52a365d9f458797a444b70aa34acffe78f24b4c08b4a428db5e32b"
     },
     {
       "label": "world_class_evidence_plan",
@@ -201,6 +201,13 @@
       "exists": true,
       "bytes": 1775,
       "sha256": "124b9239d7f35022735090712aadf2bf1d4dfba28f6bcf18f956fa0a73fe4482"
+    },
+    {
+      "label": "world_class_claim_guard",
+      "path": "reports/world_class_claim_guard.json",
+      "exists": true,
+      "bytes": 7809,
+      "sha256": "7365f6cd85b89326816590cd2403b1210e9afba45f0bc3ca1af6b4a07299b9ad"
     }
   ],
   "missing_artifacts": [],
@@ -285,6 +292,11 @@
       "command": "python3 scripts/yao.py world-class-intake .",
       "evidence": "reports/world_class_evidence_intake.json"
     },
+    {
+      "label": "world-class claim guard",
+      "command": "python3 scripts/yao.py world-class-claim-guard .",
+      "evidence": "reports/world_class_claim_guard.json"
+    },
     {
       "label": "full ci",
       "command": "make ci-test",
diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md
index 8a1e10a..4e31574 100644
--- a/reports/benchmark_reproducibility.md
+++ b/reports/benchmark_reproducibility.md
@@ -1,22 +1,22 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-06-14`
-Commit: `60995ed569b1c99aa6f6ae2b4406e04327202beb`
+Commit: `c1c85093d1ea67954d414789f96c87bbc3964868`
 Working tree dirty at generation: `true`
 
 ## Summary
 
 - reproducibility ready: `true`
 - methodology complete: `true`
-- required artifacts: `18`
+- required artifacts: `19`
 - missing artifacts: `0`
 - output cases: `5`
 - disclosed failure cases: `3`
-- reproduction commands: `17`
+- reproduction commands: `18`
 - provider evidence complete: `false`
 - human review complete: `false`
 - world-class ready: `false`
-- changed files at generation: `56`
+- changed files at generation: `42`
 
 This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete.
 
@@ -40,19 +40,20 @@ This report proves local benchmark reproducibility only. It keeps external provi
 | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
 | output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
 | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
-| output_execution | `reports/output_execution_runs.json` | present | `8c40546b610c` |
+| output_execution | `reports/output_execution_runs.json` | present | `5a1eaa33c1cb` |
 | 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 | `097f2a477efc` |
-| registry_audit | `reports/registry_audit.json` | present | `5c606b5a3b54` |
-| package_verification | `reports/package_verification.json` | present | `8dab6035e72c` |
-| install_simulation | `reports/install_simulation.json` | present | `3b1456caa214` |
-| skill_os2_audit | `reports/skill_os2_audit.json` | present | `5b7c9427a340` |
+| trust_report | `reports/security_trust_report.json` | present | `1faacec874dd` |
+| registry_audit | `reports/registry_audit.json` | present | `c796a29122c3` |
+| package_verification | `reports/package_verification.json` | present | `224f5f714785` |
+| install_simulation | `reports/install_simulation.json` | present | `ae7cccad4792` |
+| skill_os2_audit | `reports/skill_os2_audit.json` | present | `3f1c6fdf7b52` |
 | 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` |
+| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `7365f6cd85b8` |
 
 ## Reproduction Commands
 
@@ -88,6 +89,8 @@ This report proves local benchmark reproducibility only. It keeps external provi
   - evidence: `reports/world_class_evidence_ledger.json`
 - `python3 scripts/yao.py world-class-intake .`
   - evidence: `reports/world_class_evidence_intake.json`
+- `python3 scripts/yao.py world-class-claim-guard .`
+  - evidence: `reports/world_class_claim_guard.json`
 - `make ci-test`
   - evidence: `CI target output`
 
diff --git a/reports/compiled_targets.json b/reports/compiled_targets.json
index e4f188d..1ee317e 100644
--- a/reports/compiled_targets.json
+++ b/reports/compiled_targets.json
@@ -197,6 +197,7 @@
             "scripts/render_social_preview.py",
             "scripts/render_system_model.py",
             "scripts/render_telemetry_hook_recipes.py",
+            "scripts/render_world_class_claim_guard.py",
             "scripts/render_world_class_evidence_intake.py",
             "scripts/render_world_class_evidence_ledger.py",
             "scripts/render_world_class_evidence_plan.py",
@@ -223,8 +224,7 @@
             "scripts/verify_package.py",
             "scripts/yao.py",
             "scripts/yao_cli_config.py",
-            "scripts/yao_cli_parser.py",
-            "scripts/yao_cli_telemetry.py"
+            "scripts/yao_cli_parser.py"
           ],
           "assets": [
             "templates/basic_skill.md.j2",
@@ -383,7 +383,7 @@
             },
             "file_write": {
               "required": true,
-              "script_count": 57,
+              "script_count": 58,
               "scripts": [
                 "scripts/adjudicate_output_review.py",
                 "scripts/build_confusion_matrix.py",
@@ -429,6 +429,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -479,14 +480,14 @@
           },
           "help_smoke": {
             "enabled": true,
-            "checked_count": 70,
+            "checked_count": 71,
             "failed_count": 0,
             "failed_scripts": []
           },
           "trust_summary": {
             "secret_findings": 0,
             "network_script_count": 3,
-            "file_write_script_count": 57,
+            "file_write_script_count": 58,
             "subprocess_script_count": 8,
             "interactive_script_count": 0,
             "help_smoke_failed_count": 0
@@ -508,7 +509,7 @@
           ],
           "capability_counts": {
             "network": 3,
-            "file_write": 57,
+            "file_write": 58,
             "subprocess": 8,
             "interactive": 0
           },
@@ -621,7 +622,7 @@
           },
           "file_write": {
             "required": true,
-            "script_count": 57,
+            "script_count": 58,
             "scripts": [
               "scripts/adjudicate_output_review.py",
               "scripts/build_confusion_matrix.py",
@@ -667,6 +668,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -717,14 +719,14 @@
         },
         "help_smoke": {
           "enabled": true,
-          "checked_count": 70,
+          "checked_count": 71,
           "failed_count": 0,
           "failed_scripts": []
         },
         "trust_summary": {
           "secret_findings": 0,
           "network_script_count": 3,
-          "file_write_script_count": 57,
+          "file_write_script_count": 58,
           "subprocess_script_count": 8,
           "interactive_script_count": 0,
           "help_smoke_failed_count": 0
@@ -744,7 +746,7 @@
         ],
         "capability_counts": {
           "network": 3,
-          "file_write": 57,
+          "file_write": 58,
           "subprocess": 8,
           "interactive": 0
         },
@@ -1030,6 +1032,7 @@
             "scripts/render_social_preview.py",
             "scripts/render_system_model.py",
             "scripts/render_telemetry_hook_recipes.py",
+            "scripts/render_world_class_claim_guard.py",
             "scripts/render_world_class_evidence_intake.py",
             "scripts/render_world_class_evidence_ledger.py",
             "scripts/render_world_class_evidence_plan.py",
@@ -1056,8 +1059,7 @@
             "scripts/verify_package.py",
             "scripts/yao.py",
             "scripts/yao_cli_config.py",
-            "scripts/yao_cli_parser.py",
-            "scripts/yao_cli_telemetry.py"
+            "scripts/yao_cli_parser.py"
           ],
           "assets": [
             "templates/basic_skill.md.j2",
@@ -1216,7 +1218,7 @@
             },
             "file_write": {
               "required": true,
-              "script_count": 57,
+              "script_count": 58,
               "scripts": [
                 "scripts/adjudicate_output_review.py",
                 "scripts/build_confusion_matrix.py",
@@ -1262,6 +1264,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -1312,14 +1315,14 @@
           },
           "help_smoke": {
             "enabled": true,
-            "checked_count": 70,
+            "checked_count": 71,
             "failed_count": 0,
             "failed_scripts": []
           },
           "trust_summary": {
             "secret_findings": 0,
             "network_script_count": 3,
-            "file_write_script_count": 57,
+            "file_write_script_count": 58,
             "subprocess_script_count": 8,
             "interactive_script_count": 0,
             "help_smoke_failed_count": 0
@@ -1341,7 +1344,7 @@
           ],
           "capability_counts": {
             "network": 3,
-            "file_write": 57,
+            "file_write": 58,
             "subprocess": 8,
             "interactive": 0
           },
@@ -1454,7 +1457,7 @@
           },
           "file_write": {
             "required": true,
-            "script_count": 57,
+            "script_count": 58,
             "scripts": [
               "scripts/adjudicate_output_review.py",
               "scripts/build_confusion_matrix.py",
@@ -1500,6 +1503,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -1550,14 +1554,14 @@
         },
         "help_smoke": {
           "enabled": true,
-          "checked_count": 70,
+          "checked_count": 71,
           "failed_count": 0,
           "failed_scripts": []
         },
         "trust_summary": {
           "secret_findings": 0,
           "network_script_count": 3,
-          "file_write_script_count": 57,
+          "file_write_script_count": 58,
           "subprocess_script_count": 8,
           "interactive_script_count": 0,
           "help_smoke_failed_count": 0
@@ -1577,7 +1581,7 @@
         ],
         "capability_counts": {
           "network": 3,
-          "file_write": 57,
+          "file_write": 58,
           "subprocess": 8,
           "interactive": 0
         },
@@ -1863,6 +1867,7 @@
             "scripts/render_social_preview.py",
             "scripts/render_system_model.py",
             "scripts/render_telemetry_hook_recipes.py",
+            "scripts/render_world_class_claim_guard.py",
             "scripts/render_world_class_evidence_intake.py",
             "scripts/render_world_class_evidence_ledger.py",
             "scripts/render_world_class_evidence_plan.py",
@@ -1889,8 +1894,7 @@
             "scripts/verify_package.py",
             "scripts/yao.py",
             "scripts/yao_cli_config.py",
-            "scripts/yao_cli_parser.py",
-            "scripts/yao_cli_telemetry.py"
+            "scripts/yao_cli_parser.py"
           ],
           "assets": [
             "templates/basic_skill.md.j2",
@@ -2049,7 +2053,7 @@
             },
             "file_write": {
               "required": true,
-              "script_count": 57,
+              "script_count": 58,
               "scripts": [
                 "scripts/adjudicate_output_review.py",
                 "scripts/build_confusion_matrix.py",
@@ -2095,6 +2099,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -2145,14 +2150,14 @@
           },
           "help_smoke": {
             "enabled": true,
-            "checked_count": 70,
+            "checked_count": 71,
             "failed_count": 0,
             "failed_scripts": []
           },
           "trust_summary": {
             "secret_findings": 0,
             "network_script_count": 3,
-            "file_write_script_count": 57,
+            "file_write_script_count": 58,
             "subprocess_script_count": 8,
             "interactive_script_count": 0,
             "help_smoke_failed_count": 0
@@ -2174,7 +2179,7 @@
           ],
           "capability_counts": {
             "network": 3,
-            "file_write": 57,
+            "file_write": 58,
             "subprocess": 8,
             "interactive": 0
           },
@@ -2280,7 +2285,7 @@
           },
           "file_write": {
             "required": true,
-            "script_count": 57,
+            "script_count": 58,
             "scripts": [
               "scripts/adjudicate_output_review.py",
               "scripts/build_confusion_matrix.py",
@@ -2326,6 +2331,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -2376,14 +2382,14 @@
         },
         "help_smoke": {
           "enabled": true,
-          "checked_count": 70,
+          "checked_count": 71,
           "failed_count": 0,
           "failed_scripts": []
         },
         "trust_summary": {
           "secret_findings": 0,
           "network_script_count": 3,
-          "file_write_script_count": 57,
+          "file_write_script_count": 58,
           "subprocess_script_count": 8,
           "interactive_script_count": 0,
           "help_smoke_failed_count": 0
@@ -2403,7 +2409,7 @@
         ],
         "capability_counts": {
           "network": 3,
-          "file_write": 57,
+          "file_write": 58,
           "subprocess": 8,
           "interactive": 0
         },
@@ -2680,6 +2686,7 @@
             "scripts/render_social_preview.py",
             "scripts/render_system_model.py",
             "scripts/render_telemetry_hook_recipes.py",
+            "scripts/render_world_class_claim_guard.py",
             "scripts/render_world_class_evidence_intake.py",
             "scripts/render_world_class_evidence_ledger.py",
             "scripts/render_world_class_evidence_plan.py",
@@ -2706,8 +2713,7 @@
             "scripts/verify_package.py",
             "scripts/yao.py",
             "scripts/yao_cli_config.py",
-            "scripts/yao_cli_parser.py",
-            "scripts/yao_cli_telemetry.py"
+            "scripts/yao_cli_parser.py"
           ],
           "assets": [
             "templates/basic_skill.md.j2",
@@ -2866,7 +2872,7 @@
             },
             "file_write": {
               "required": true,
-              "script_count": 57,
+              "script_count": 58,
               "scripts": [
                 "scripts/adjudicate_output_review.py",
                 "scripts/build_confusion_matrix.py",
@@ -2912,6 +2918,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -2962,14 +2969,14 @@
           },
           "help_smoke": {
             "enabled": true,
-            "checked_count": 70,
+            "checked_count": 71,
             "failed_count": 0,
             "failed_scripts": []
           },
           "trust_summary": {
             "secret_findings": 0,
             "network_script_count": 3,
-            "file_write_script_count": 57,
+            "file_write_script_count": 58,
             "subprocess_script_count": 8,
             "interactive_script_count": 0,
             "help_smoke_failed_count": 0
@@ -2991,7 +2998,7 @@
           ],
           "capability_counts": {
             "network": 3,
-            "file_write": 57,
+            "file_write": 58,
             "subprocess": 8,
             "interactive": 0
           },
@@ -3097,7 +3104,7 @@
           },
           "file_write": {
             "required": true,
-            "script_count": 57,
+            "script_count": 58,
             "scripts": [
               "scripts/adjudicate_output_review.py",
               "scripts/build_confusion_matrix.py",
@@ -3143,6 +3150,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -3193,14 +3201,14 @@
         },
         "help_smoke": {
           "enabled": true,
-          "checked_count": 70,
+          "checked_count": 71,
           "failed_count": 0,
           "failed_scripts": []
         },
         "trust_summary": {
           "secret_findings": 0,
           "network_script_count": 3,
-          "file_write_script_count": 57,
+          "file_write_script_count": 58,
           "subprocess_script_count": 8,
           "interactive_script_count": 0,
           "help_smoke_failed_count": 0
@@ -3220,7 +3228,7 @@
         ],
         "capability_counts": {
           "network": 3,
-          "file_write": 57,
+          "file_write": 58,
           "subprocess": 8,
           "interactive": 0
         },
@@ -3497,6 +3505,7 @@
             "scripts/render_social_preview.py",
             "scripts/render_system_model.py",
             "scripts/render_telemetry_hook_recipes.py",
+            "scripts/render_world_class_claim_guard.py",
             "scripts/render_world_class_evidence_intake.py",
             "scripts/render_world_class_evidence_ledger.py",
             "scripts/render_world_class_evidence_plan.py",
@@ -3523,8 +3532,7 @@
             "scripts/verify_package.py",
             "scripts/yao.py",
             "scripts/yao_cli_config.py",
-            "scripts/yao_cli_parser.py",
-            "scripts/yao_cli_telemetry.py"
+            "scripts/yao_cli_parser.py"
           ],
           "assets": [
             "templates/basic_skill.md.j2",
@@ -3683,7 +3691,7 @@
             },
             "file_write": {
               "required": true,
-              "script_count": 57,
+              "script_count": 58,
               "scripts": [
                 "scripts/adjudicate_output_review.py",
                 "scripts/build_confusion_matrix.py",
@@ -3729,6 +3737,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -3779,14 +3788,14 @@
           },
           "help_smoke": {
             "enabled": true,
-            "checked_count": 70,
+            "checked_count": 71,
             "failed_count": 0,
             "failed_scripts": []
           },
           "trust_summary": {
             "secret_findings": 0,
             "network_script_count": 3,
-            "file_write_script_count": 57,
+            "file_write_script_count": 58,
             "subprocess_script_count": 8,
             "interactive_script_count": 0,
             "help_smoke_failed_count": 0
@@ -3808,7 +3817,7 @@
           ],
           "capability_counts": {
             "network": 3,
-            "file_write": 57,
+            "file_write": 58,
             "subprocess": 8,
             "interactive": 0
           },
@@ -3918,7 +3927,7 @@
           },
           "file_write": {
             "required": true,
-            "script_count": 57,
+            "script_count": 58,
             "scripts": [
               "scripts/adjudicate_output_review.py",
               "scripts/build_confusion_matrix.py",
@@ -3964,6 +3973,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -4014,14 +4024,14 @@
         },
         "help_smoke": {
           "enabled": true,
-          "checked_count": 70,
+          "checked_count": 71,
           "failed_count": 0,
           "failed_scripts": []
         },
         "trust_summary": {
           "secret_findings": 0,
           "network_script_count": 3,
-          "file_write_script_count": 57,
+          "file_write_script_count": 58,
           "subprocess_script_count": 8,
           "interactive_script_count": 0,
           "help_smoke_failed_count": 0
@@ -4041,7 +4051,7 @@
         ],
         "capability_counts": {
           "network": 3,
-          "file_write": 57,
+          "file_write": 58,
           "subprocess": 8,
           "interactive": 0
         },
diff --git a/reports/context_budget.json b/reports/context_budget.json
index 4cd021d..bebfd5b 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": 1040839,
+    "other_text_tokens": 1051179,
     "estimated_initial_load_tokens": 944,
-    "estimated_total_text_tokens": 1041590,
-    "relevant_file_count": 447,
+    "estimated_total_text_tokens": 1051930,
+    "relevant_file_count": 453,
     "unused_resource_dirs": [],
     "quality_signal_points": 130,
     "quality_density": 137.7
diff --git a/reports/install_simulation.json b/reports/install_simulation.json
index 985e1e5..0b86616 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": 539,
+    "archive_entry_count": 543,
     "archive_extracted": true,
     "entrypoint_loaded": true,
     "manifest_loaded": true,
diff --git a/reports/output_execution_runs.json b/reports/output_execution_runs.json
index 2fc97d4..8c4c735 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": 28.19,
+      "duration_ms": 28.37,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -62,7 +62,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.31,
+      "duration_ms": 27.79,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -85,7 +85,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.17,
+      "duration_ms": 28.28,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -113,7 +113,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.25,
+      "duration_ms": 28.12,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -136,7 +136,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 28.36,
+      "duration_ms": 27.94,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -164,7 +164,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.79,
+      "duration_ms": 28.3,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -187,7 +187,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.53,
+      "duration_ms": 27.54,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -214,7 +214,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.87,
+      "duration_ms": 27.72,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -237,7 +237,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.84,
+      "duration_ms": 28.27,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
@@ -266,7 +266,7 @@
       "execution_mode": "command",
       "model_executed": false,
       "command_executed": true,
-      "duration_ms": 27.76,
+      "duration_ms": 28.16,
       "provider": "local-output-eval-runner",
       "model": "",
       "usage": {
diff --git a/reports/output_execution_runs.md b/reports/output_execution_runs.md
index eceebbe..e41c4bd 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 | 28.19 | 33 | 0.0 | pass |
-| skill-package-contract | with_skill | command | local-output-eval-runner | 28.31 | 73 | 100.0 | pass |
-| output-eval-expectation | baseline | command | local-output-eval-runner | 28.17 | 36 | 0.0 | pass |
-| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.25 | 80 | 100.0 | pass |
-| ir-before-packaging | baseline | command | local-output-eval-runner | 28.36 | 33 | 0.0 | pass |
-| ir-before-packaging | with_skill | command | local-output-eval-runner | 27.79 | 80 | 100.0 | pass |
-| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.53 | 36 | 0.0 | pass |
-| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.87 | 65 | 100.0 | pass |
-| file-backed-governed-package | baseline | command | local-output-eval-runner | 27.84 | 37 | 0.0 | pass |
-| file-backed-governed-package | with_skill | command | local-output-eval-runner | 27.76 | 98 | 100.0 | pass |
+| skill-package-contract | baseline | command | local-output-eval-runner | 28.37 | 33 | 0.0 | pass |
+| skill-package-contract | with_skill | command | local-output-eval-runner | 27.79 | 73 | 100.0 | pass |
+| output-eval-expectation | baseline | command | local-output-eval-runner | 28.28 | 36 | 0.0 | pass |
+| output-eval-expectation | with_skill | command | local-output-eval-runner | 28.12 | 80 | 100.0 | pass |
+| ir-before-packaging | baseline | command | local-output-eval-runner | 27.94 | 33 | 0.0 | pass |
+| ir-before-packaging | with_skill | command | local-output-eval-runner | 28.3 | 80 | 100.0 | pass |
+| near-neighbor-boundary | baseline | command | local-output-eval-runner | 27.54 | 36 | 0.0 | pass |
+| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 27.72 | 65 | 100.0 | pass |
+| file-backed-governed-package | baseline | command | local-output-eval-runner | 28.27 | 37 | 0.0 | pass |
+| file-backed-governed-package | with_skill | command | local-output-eval-runner | 28.16 | 98 | 100.0 | pass |
 
 ## Next Fixes
 
diff --git a/reports/package_verification.json b/reports/package_verification.json
index 388c595..8daeeb2 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": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
-    "archive_entry_count": 539,
+    "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
+    "archive_entry_count": 543,
     "failure_count": 0,
     "warning_count": 0
   },
diff --git a/reports/package_verification.md b/reports/package_verification.md
index 8faff25..d52707b 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: `b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094`
+- Archive SHA256: `55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404`
 - Failures: `0`
 - Warnings: `0`
 
diff --git a/reports/registry_audit.json b/reports/registry_audit.json
index f039f90..e1a2508 100644
--- a/reports/registry_audit.json
+++ b/reports/registry_audit.json
@@ -21,8 +21,8 @@
     "trust_level": "local",
     "license": "MIT",
     "checksums": {
-      "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1",
-      "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+      "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15",
+      "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
     },
     "compatibility": {
       "openai": "pass",
@@ -53,7 +53,7 @@
     },
     "distribution": {
       "archive_verified": true,
-      "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
+      "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
       "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": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+        "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
       }
     ]
   },
diff --git a/reports/registry_audit.md b/reports/registry_audit.md
index 541f603..254fa3c 100644
--- a/reports/registry_audit.md
+++ b/reports/registry_audit.md
@@ -6,8 +6,8 @@
 - Maturity: `governed`
 - Owner: `Yao Team`
 - License: `MIT`
-- Package SHA256: `9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1`
-- Archive SHA256: `b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094`
+- Package SHA256: `81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15`
+- Archive SHA256: `55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404`
 - Install simulated: `True`
 
 ## Compatibility
diff --git a/reports/review-studio.html b/reports/review-studio.html
index 9777087..d9f385a 100644
--- a/reports/review-studio.html
+++ b/reports/review-studio.html
@@ -292,12 +292,12 @@
 
     <section>
       <h2>核心指标</h2>
-      <div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review 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>80 scripts scanned; secrets found</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>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>539 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>81 scripts scanned; secrets found</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>66 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>543 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; 80 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>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>
+      <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; 81 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>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">
@@ -307,7 +307,7 @@
 
     <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>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='../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">
@@ -323,7 +323,7 @@
       </div>
       <div class="panel">
         <h2>证据路径</h2>
-        <ul class="evidence"><li><strong>skill_overview</strong><span>reports/skill-overview.html</span></li><li><strong>review_viewer</strong><span>reports/review-viewer.html</span></li><li><strong>output_eval</strong><span>reports/output_quality_scorecard.md</span></li><li><strong>output_execution</strong><span>reports/output_execution_runs.md</span></li><li><strong>output_blind_review</strong><span>reports/output_blind_review_pack.md</span></li><li><strong>output_review_decisions</strong><span>reports/output_review_decisions.json</span></li><li><strong>output_review_adjudication</strong><span>reports/output_review_adjudication.md</span></li><li><strong>benchmark_reproducibility</strong><span>reports/benchmark_reproducibility.md</span></li><li><strong>skill_os2_coverage</strong><span>reports/skill_os2_coverage.md</span></li><li><strong>runtime_conformance</strong><span>reports/conformance_matrix.md</span></li><li><strong>trust_report</strong><span>reports/security_trust_report.md</span></li><li><strong>permission_policy</strong><span>security/permission_policy.md</span></li><li><strong>runtime_permissions</strong><span>reports/runtime_permission_probes.md</span></li><li><strong>skill_atlas</strong><span>reports/skill_atlas.html</span></li><li><strong>compiled_targets</strong><span>reports/compiled_targets.md</span></li><li><strong>adoption_drift</strong><span>reports/adoption_drift_report.md</span></li><li><strong>review_waivers</strong><span>reports/review_waivers.md</span></li><li><strong>review_annotations</strong><span>reports/review_annotations.md</span></li><li><strong>world_class_evidence_plan</strong><span>reports/world_class_evidence_plan.md</span></li><li><strong>world_class_evidence_ledger</strong><span>reports/world_class_evidence_ledger.md</span></li><li><strong>world_class_evidence_intake</strong><span>reports/world_class_evidence_intake.md</span></li><li><strong>registry_audit</strong><span>reports/registry_audit.md</span></li><li><strong>package_verification</strong><span>reports/package_verification.md</span></li><li><strong>install_simulation</strong><span>reports/install_simulation.md</span></li><li><strong>upgrade_check</strong><span>reports/upgrade_check.md</span></li><li><strong>migration</strong><span>docs/migration-v2.md</span></li></ul>
+        <ul class="evidence"><li><strong>skill_overview</strong><span>reports/skill-overview.html</span></li><li><strong>review_viewer</strong><span>reports/review-viewer.html</span></li><li><strong>output_eval</strong><span>reports/output_quality_scorecard.md</span></li><li><strong>output_execution</strong><span>reports/output_execution_runs.md</span></li><li><strong>output_blind_review</strong><span>reports/output_blind_review_pack.md</span></li><li><strong>output_review_decisions</strong><span>reports/output_review_decisions.json</span></li><li><strong>output_review_adjudication</strong><span>reports/output_review_adjudication.md</span></li><li><strong>benchmark_reproducibility</strong><span>reports/benchmark_reproducibility.md</span></li><li><strong>skill_os2_coverage</strong><span>reports/skill_os2_coverage.md</span></li><li><strong>runtime_conformance</strong><span>reports/conformance_matrix.md</span></li><li><strong>trust_report</strong><span>reports/security_trust_report.md</span></li><li><strong>permission_policy</strong><span>security/permission_policy.md</span></li><li><strong>runtime_permissions</strong><span>reports/runtime_permission_probes.md</span></li><li><strong>skill_atlas</strong><span>reports/skill_atlas.html</span></li><li><strong>compiled_targets</strong><span>reports/compiled_targets.md</span></li><li><strong>adoption_drift</strong><span>reports/adoption_drift_report.md</span></li><li><strong>review_waivers</strong><span>reports/review_waivers.md</span></li><li><strong>review_annotations</strong><span>reports/review_annotations.md</span></li><li><strong>world_class_evidence_plan</strong><span>reports/world_class_evidence_plan.md</span></li><li><strong>world_class_evidence_ledger</strong><span>reports/world_class_evidence_ledger.md</span></li><li><strong>world_class_evidence_intake</strong><span>reports/world_class_evidence_intake.md</span></li><li><strong>world_class_claim_guard</strong><span>reports/world_class_claim_guard.md</span></li><li><strong>registry_audit</strong><span>reports/registry_audit.md</span></li><li><strong>package_verification</strong><span>reports/package_verification.md</span></li><li><strong>install_simulation</strong><span>reports/install_simulation.md</span></li><li><strong>upgrade_check</strong><span>reports/upgrade_check.md</span></li><li><strong>migration</strong><span>docs/migration-v2.md</span></li></ul>
       </div>
     </section>
 
@@ -363,7 +363,7 @@
     </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>80</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>9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1</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>81</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>81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15</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>
 
@@ -413,14 +413,19 @@
       <div class="panel"><h2>入口边界</h2><p>intake 只校验证据包格式、来源、隐私和反过度声明；只有 ledger 看到真实 provider、真人、原生权限或真实客户端结果后，world-class 才能进入完成审计。</p></div>
     </section>
 
+    <section class="twocol">
+      <div class="panel"><h2>声明守卫</h2><dl class='kv-grid'><div><dt>台账可声明</dt><dd>否</dd></div><div><dt>台账待补</dt><dd>4</dd></div><div><dt>声明面</dt><dd>66</dd></div><div><dt>违规数</dt><dd>0</dd></div><div><dt>Overclaim Guard Active</dt><dd>是</dd></div></dl></div>
+      <div class="panel"><h2>声明边界</h2><p>claim guard 扫描 README、docs 和 reports 中的完成态表述；ledger 未 ready 时，任何英文完成断言、true 状态声明或中文完成态都会阻断发布审查。</p></div>
+    </section>
+
     <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>b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094</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>55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404</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>539</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>b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094</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>543</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>55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404</code></dd></div></dl></div>
     </section>
 
     <section class="twocol">
diff --git a/reports/review-studio.json b/reports/review-studio.json
index f38b8bb..1992456 100644
--- a/reports/review-studio.json
+++ b/reports/review-studio.json
@@ -59,7 +59,7 @@
       "key": "trust-report",
       "label": "信任报告",
       "status": "pass",
-      "detail": "0 secrets; 80 scripts; 3 network-capable scripts; 0 help smoke failures",
+      "detail": "0 secrets; 81 scripts; 3 network-capable scripts; 0 help smoke failures",
       "evidence": "reports/security_trust_report.json",
       "link": "security_trust_report.md"
     },
@@ -281,6 +281,14 @@
           "exists": true,
           "link": "world_class_evidence_intake.md"
         },
+        {
+          "path": "reports/world_class_claim_guard.md",
+          "label": "world-class claim guard",
+          "kind": "report",
+          "line": 1,
+          "exists": true,
+          "link": "world_class_claim_guard.md"
+        },
         {
           "path": "evidence/world_class/intake.schema.json",
           "label": "evidence intake schema",
@@ -365,6 +373,7 @@
     "world_class_evidence_plan": "reports/world_class_evidence_plan.md",
     "world_class_evidence_ledger": "reports/world_class_evidence_ledger.md",
     "world_class_evidence_intake": "reports/world_class_evidence_intake.md",
+    "world_class_claim_guard": "reports/world_class_claim_guard.md",
     "registry_audit": "reports/registry_audit.md",
     "package_verification": "reports/package_verification.md",
     "install_simulation": "reports/install_simulation.md",
@@ -810,7 +819,7 @@
             "path": "scripts",
             "label": "Deterministic helpers or local tooling",
             "kind": "folder",
-            "file_count": 80
+            "file_count": 81
           },
           {
             "path": "evals",
@@ -822,10 +831,10 @@
             "path": "reports",
             "label": "Generated evidence and overview artifacts",
             "kind": "folder",
-            "file_count": 189
+            "file_count": 191
           }
         ],
-        "file_count": 333,
+        "file_count": 336,
         "folder_count": 4,
         "distribution": [
           {
@@ -850,7 +859,7 @@
           },
           {
             "label": "scripts",
-            "value": 80
+            "value": 81
           },
           {
             "label": "evals",
@@ -858,7 +867,7 @@
           },
           {
             "label": "reports",
-            "value": 189
+            "value": 191
           }
         ]
       },
@@ -979,7 +988,7 @@
           "path": "scripts",
           "label": "Deterministic helpers or local tooling",
           "kind": "folder",
-          "file_count": 80
+          "file_count": 81
         },
         {
           "path": "evals",
@@ -991,7 +1000,7 @@
           "path": "reports",
           "label": "Generated evidence and overview artifacts",
           "kind": "folder",
-          "file_count": 189
+          "file_count": 191
         }
       ],
       "strengths": [
@@ -1263,11 +1272,11 @@
         "summary": {
           "reproducibility_ready": true,
           "methodology_complete": true,
-          "required_artifact_count": 18,
+          "required_artifact_count": 19,
           "missing_artifact_count": 0,
           "output_case_count": 5,
           "failure_disclosure_count": 3,
-          "command_count": 17,
+          "command_count": 18,
           "command_executed_count": 10,
           "timing_observed_count": 10,
           "model_executed_count": 0,
@@ -1279,9 +1288,9 @@
           "world_class_task_count": 4,
           "world_class_ledger_pending_count": 4,
           "working_tree_dirty": true,
-          "changed_file_count": 56
+          "changed_file_count": 42
         },
-        "commit": "60995ed569b1c99aa6f6ae2b4406e04327202beb",
+        "commit": "c1c85093d1ea67954d414789f96c87bbc3964868",
         "missing_artifacts": [],
         "limitations": [
           "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -1356,8 +1365,8 @@
         "failures": []
       },
       "trust_security": {
-        "scanned_files": 164,
-        "script_count": 80,
+        "scanned_files": 165,
+        "script_count": 81,
         "internal_module_count": 10,
         "secret_findings": 0,
         "dependency_files": [
@@ -1366,18 +1375,18 @@
         "network_script_count": 3,
         "network_policy_covered_count": 3,
         "network_policy_missing_count": 0,
-        "file_write_script_count": 57,
+        "file_write_script_count": 58,
         "permission_required_count": 3,
         "permission_approved_count": 3,
         "permission_missing_count": 0,
         "permission_invalid_count": 0,
         "permission_expired_count": 0,
-        "help_smoke_checked_count": 70,
+        "help_smoke_checked_count": 71,
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 164,
-        "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+        "package_hash_file_count": 165,
+        "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
       },
       "skill_atlas": {
         "skill_count": 12,
@@ -1415,8 +1424,8 @@
           "trust_level": "local",
           "license": "MIT",
           "checksums": {
-            "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1",
-            "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+            "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15",
+            "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
           },
           "compatibility": {
             "openai": "pass",
@@ -1447,7 +1456,7 @@
           },
           "distribution": {
             "archive_verified": true,
-            "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
+            "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
             "package_verification": "reports/package_verification.json",
             "install_simulated": true,
             "install_simulation": "reports/install_simulation.json"
@@ -1463,8 +1472,8 @@
           "target_count": 4,
           "adapter_count": 4,
           "archive_present": true,
-          "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
-          "archive_entry_count": 539,
+          "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
+          "archive_entry_count": 543,
           "failure_count": 0,
           "warning_count": 0
         },
@@ -1475,7 +1484,7 @@
         "ok": true,
         "summary": {
           "archive_present": true,
-          "archive_entry_count": 539,
+          "archive_entry_count": 543,
           "archive_extracted": true,
           "entrypoint_loaded": true,
           "manifest_loaded": true,
@@ -1542,12 +1551,12 @@
             {
               "field": "archive_sha256",
               "from": "",
-              "to": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+              "to": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
             },
             {
               "field": "package_sha256",
               "from": "0000000000000000000000000000000000000000000000000000000000000000",
-              "to": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+              "to": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
             }
           ]
         },
@@ -3664,7 +3673,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 28.19,
+          "duration_ms": 28.37,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3692,7 +3701,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 28.31,
+          "duration_ms": 27.79,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3715,7 +3724,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 28.17,
+          "duration_ms": 28.28,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3743,7 +3752,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 28.25,
+          "duration_ms": 28.12,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3766,7 +3775,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 28.36,
+          "duration_ms": 27.94,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3794,7 +3803,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 27.79,
+          "duration_ms": 28.3,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3817,7 +3826,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 27.53,
+          "duration_ms": 27.54,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3844,7 +3853,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 27.87,
+          "duration_ms": 27.72,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3867,7 +3876,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 27.84,
+          "duration_ms": 28.27,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -3896,7 +3905,7 @@
           "execution_mode": "command",
           "model_executed": false,
           "command_executed": true,
-          "duration_ms": 27.76,
+          "duration_ms": 28.16,
           "provider": "local-output-eval-runner",
           "model": "",
           "usage": {
@@ -4327,7 +4336,7 @@
           "label": "Trust Security",
           "status": "pass",
           "objective": "Scripts, dependencies, permissions, secrets, and package hash are reviewable for team distribution.",
-          "current": "80 scripts; secrets 0; help failures 0",
+          "current": "81 scripts; secrets 0; help failures 0",
           "command": "python3 scripts/yao.py trust .",
           "test": "python3 tests/verify_trust_check.py",
           "evidence": [
@@ -4401,7 +4410,7 @@
           "label": "Registry Distribution",
           "status": "pass",
           "objective": "Skill packages are installable, versioned, checksumed, and upgrade-reviewable.",
-          "current": "archive entries 539; install failures 0",
+          "current": "archive entries 543; 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": [
@@ -4510,7 +4519,7 @@
           "label": "Benchmark Methodology",
           "status": "pass",
           "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
-          "current": "18 required artifacts checked",
+          "current": "19 required artifacts checked",
           "command": "make ci-test",
           "test": "tests/verify_benchmark_reproducibility.py",
           "evidence": [
@@ -5018,6 +5027,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -5044,8 +5054,7 @@
                 "scripts/verify_package.py",
                 "scripts/yao.py",
                 "scripts/yao_cli_config.py",
-                "scripts/yao_cli_parser.py",
-                "scripts/yao_cli_telemetry.py"
+                "scripts/yao_cli_parser.py"
               ],
               "assets": [
                 "templates/basic_skill.md.j2",
@@ -5204,7 +5213,7 @@
                 },
                 "file_write": {
                   "required": true,
-                  "script_count": 57,
+                  "script_count": 58,
                   "scripts": [
                     "scripts/adjudicate_output_review.py",
                     "scripts/build_confusion_matrix.py",
@@ -5250,6 +5259,7 @@
                     "scripts/render_social_preview.py",
                     "scripts/render_system_model.py",
                     "scripts/render_telemetry_hook_recipes.py",
+                    "scripts/render_world_class_claim_guard.py",
                     "scripts/render_world_class_evidence_intake.py",
                     "scripts/render_world_class_evidence_ledger.py",
                     "scripts/render_world_class_evidence_plan.py",
@@ -5300,14 +5310,14 @@
               },
               "help_smoke": {
                 "enabled": true,
-                "checked_count": 70,
+                "checked_count": 71,
                 "failed_count": 0,
                 "failed_scripts": []
               },
               "trust_summary": {
                 "secret_findings": 0,
                 "network_script_count": 3,
-                "file_write_script_count": 57,
+                "file_write_script_count": 58,
                 "subprocess_script_count": 8,
                 "interactive_script_count": 0,
                 "help_smoke_failed_count": 0
@@ -5329,7 +5339,7 @@
               ],
               "capability_counts": {
                 "network": 3,
-                "file_write": 57,
+                "file_write": 58,
                 "subprocess": 8,
                 "interactive": 0
               },
@@ -5442,7 +5452,7 @@
               },
               "file_write": {
                 "required": true,
-                "script_count": 57,
+                "script_count": 58,
                 "scripts": [
                   "scripts/adjudicate_output_review.py",
                   "scripts/build_confusion_matrix.py",
@@ -5488,6 +5498,7 @@
                   "scripts/render_social_preview.py",
                   "scripts/render_system_model.py",
                   "scripts/render_telemetry_hook_recipes.py",
+                  "scripts/render_world_class_claim_guard.py",
                   "scripts/render_world_class_evidence_intake.py",
                   "scripts/render_world_class_evidence_ledger.py",
                   "scripts/render_world_class_evidence_plan.py",
@@ -5538,14 +5549,14 @@
             },
             "help_smoke": {
               "enabled": true,
-              "checked_count": 70,
+              "checked_count": 71,
               "failed_count": 0,
               "failed_scripts": []
             },
             "trust_summary": {
               "secret_findings": 0,
               "network_script_count": 3,
-              "file_write_script_count": 57,
+              "file_write_script_count": 58,
               "subprocess_script_count": 8,
               "interactive_script_count": 0,
               "help_smoke_failed_count": 0
@@ -5565,7 +5576,7 @@
             ],
             "capability_counts": {
               "network": 3,
-              "file_write": 57,
+              "file_write": 58,
               "subprocess": 8,
               "interactive": 0
             },
@@ -5851,6 +5862,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -5877,8 +5889,7 @@
                 "scripts/verify_package.py",
                 "scripts/yao.py",
                 "scripts/yao_cli_config.py",
-                "scripts/yao_cli_parser.py",
-                "scripts/yao_cli_telemetry.py"
+                "scripts/yao_cli_parser.py"
               ],
               "assets": [
                 "templates/basic_skill.md.j2",
@@ -6037,7 +6048,7 @@
                 },
                 "file_write": {
                   "required": true,
-                  "script_count": 57,
+                  "script_count": 58,
                   "scripts": [
                     "scripts/adjudicate_output_review.py",
                     "scripts/build_confusion_matrix.py",
@@ -6083,6 +6094,7 @@
                     "scripts/render_social_preview.py",
                     "scripts/render_system_model.py",
                     "scripts/render_telemetry_hook_recipes.py",
+                    "scripts/render_world_class_claim_guard.py",
                     "scripts/render_world_class_evidence_intake.py",
                     "scripts/render_world_class_evidence_ledger.py",
                     "scripts/render_world_class_evidence_plan.py",
@@ -6133,14 +6145,14 @@
               },
               "help_smoke": {
                 "enabled": true,
-                "checked_count": 70,
+                "checked_count": 71,
                 "failed_count": 0,
                 "failed_scripts": []
               },
               "trust_summary": {
                 "secret_findings": 0,
                 "network_script_count": 3,
-                "file_write_script_count": 57,
+                "file_write_script_count": 58,
                 "subprocess_script_count": 8,
                 "interactive_script_count": 0,
                 "help_smoke_failed_count": 0
@@ -6162,7 +6174,7 @@
               ],
               "capability_counts": {
                 "network": 3,
-                "file_write": 57,
+                "file_write": 58,
                 "subprocess": 8,
                 "interactive": 0
               },
@@ -6275,7 +6287,7 @@
               },
               "file_write": {
                 "required": true,
-                "script_count": 57,
+                "script_count": 58,
                 "scripts": [
                   "scripts/adjudicate_output_review.py",
                   "scripts/build_confusion_matrix.py",
@@ -6321,6 +6333,7 @@
                   "scripts/render_social_preview.py",
                   "scripts/render_system_model.py",
                   "scripts/render_telemetry_hook_recipes.py",
+                  "scripts/render_world_class_claim_guard.py",
                   "scripts/render_world_class_evidence_intake.py",
                   "scripts/render_world_class_evidence_ledger.py",
                   "scripts/render_world_class_evidence_plan.py",
@@ -6371,14 +6384,14 @@
             },
             "help_smoke": {
               "enabled": true,
-              "checked_count": 70,
+              "checked_count": 71,
               "failed_count": 0,
               "failed_scripts": []
             },
             "trust_summary": {
               "secret_findings": 0,
               "network_script_count": 3,
-              "file_write_script_count": 57,
+              "file_write_script_count": 58,
               "subprocess_script_count": 8,
               "interactive_script_count": 0,
               "help_smoke_failed_count": 0
@@ -6398,7 +6411,7 @@
             ],
             "capability_counts": {
               "network": 3,
-              "file_write": 57,
+              "file_write": 58,
               "subprocess": 8,
               "interactive": 0
             },
@@ -6684,6 +6697,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -6710,8 +6724,7 @@
                 "scripts/verify_package.py",
                 "scripts/yao.py",
                 "scripts/yao_cli_config.py",
-                "scripts/yao_cli_parser.py",
-                "scripts/yao_cli_telemetry.py"
+                "scripts/yao_cli_parser.py"
               ],
               "assets": [
                 "templates/basic_skill.md.j2",
@@ -6870,7 +6883,7 @@
                 },
                 "file_write": {
                   "required": true,
-                  "script_count": 57,
+                  "script_count": 58,
                   "scripts": [
                     "scripts/adjudicate_output_review.py",
                     "scripts/build_confusion_matrix.py",
@@ -6916,6 +6929,7 @@
                     "scripts/render_social_preview.py",
                     "scripts/render_system_model.py",
                     "scripts/render_telemetry_hook_recipes.py",
+                    "scripts/render_world_class_claim_guard.py",
                     "scripts/render_world_class_evidence_intake.py",
                     "scripts/render_world_class_evidence_ledger.py",
                     "scripts/render_world_class_evidence_plan.py",
@@ -6966,14 +6980,14 @@
               },
               "help_smoke": {
                 "enabled": true,
-                "checked_count": 70,
+                "checked_count": 71,
                 "failed_count": 0,
                 "failed_scripts": []
               },
               "trust_summary": {
                 "secret_findings": 0,
                 "network_script_count": 3,
-                "file_write_script_count": 57,
+                "file_write_script_count": 58,
                 "subprocess_script_count": 8,
                 "interactive_script_count": 0,
                 "help_smoke_failed_count": 0
@@ -6995,7 +7009,7 @@
               ],
               "capability_counts": {
                 "network": 3,
-                "file_write": 57,
+                "file_write": 58,
                 "subprocess": 8,
                 "interactive": 0
               },
@@ -7101,7 +7115,7 @@
               },
               "file_write": {
                 "required": true,
-                "script_count": 57,
+                "script_count": 58,
                 "scripts": [
                   "scripts/adjudicate_output_review.py",
                   "scripts/build_confusion_matrix.py",
@@ -7147,6 +7161,7 @@
                   "scripts/render_social_preview.py",
                   "scripts/render_system_model.py",
                   "scripts/render_telemetry_hook_recipes.py",
+                  "scripts/render_world_class_claim_guard.py",
                   "scripts/render_world_class_evidence_intake.py",
                   "scripts/render_world_class_evidence_ledger.py",
                   "scripts/render_world_class_evidence_plan.py",
@@ -7197,14 +7212,14 @@
             },
             "help_smoke": {
               "enabled": true,
-              "checked_count": 70,
+              "checked_count": 71,
               "failed_count": 0,
               "failed_scripts": []
             },
             "trust_summary": {
               "secret_findings": 0,
               "network_script_count": 3,
-              "file_write_script_count": 57,
+              "file_write_script_count": 58,
               "subprocess_script_count": 8,
               "interactive_script_count": 0,
               "help_smoke_failed_count": 0
@@ -7224,7 +7239,7 @@
             ],
             "capability_counts": {
               "network": 3,
-              "file_write": 57,
+              "file_write": 58,
               "subprocess": 8,
               "interactive": 0
             },
@@ -7501,6 +7516,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -7527,8 +7543,7 @@
                 "scripts/verify_package.py",
                 "scripts/yao.py",
                 "scripts/yao_cli_config.py",
-                "scripts/yao_cli_parser.py",
-                "scripts/yao_cli_telemetry.py"
+                "scripts/yao_cli_parser.py"
               ],
               "assets": [
                 "templates/basic_skill.md.j2",
@@ -7687,7 +7702,7 @@
                 },
                 "file_write": {
                   "required": true,
-                  "script_count": 57,
+                  "script_count": 58,
                   "scripts": [
                     "scripts/adjudicate_output_review.py",
                     "scripts/build_confusion_matrix.py",
@@ -7733,6 +7748,7 @@
                     "scripts/render_social_preview.py",
                     "scripts/render_system_model.py",
                     "scripts/render_telemetry_hook_recipes.py",
+                    "scripts/render_world_class_claim_guard.py",
                     "scripts/render_world_class_evidence_intake.py",
                     "scripts/render_world_class_evidence_ledger.py",
                     "scripts/render_world_class_evidence_plan.py",
@@ -7783,14 +7799,14 @@
               },
               "help_smoke": {
                 "enabled": true,
-                "checked_count": 70,
+                "checked_count": 71,
                 "failed_count": 0,
                 "failed_scripts": []
               },
               "trust_summary": {
                 "secret_findings": 0,
                 "network_script_count": 3,
-                "file_write_script_count": 57,
+                "file_write_script_count": 58,
                 "subprocess_script_count": 8,
                 "interactive_script_count": 0,
                 "help_smoke_failed_count": 0
@@ -7812,7 +7828,7 @@
               ],
               "capability_counts": {
                 "network": 3,
-                "file_write": 57,
+                "file_write": 58,
                 "subprocess": 8,
                 "interactive": 0
               },
@@ -7918,7 +7934,7 @@
               },
               "file_write": {
                 "required": true,
-                "script_count": 57,
+                "script_count": 58,
                 "scripts": [
                   "scripts/adjudicate_output_review.py",
                   "scripts/build_confusion_matrix.py",
@@ -7964,6 +7980,7 @@
                   "scripts/render_social_preview.py",
                   "scripts/render_system_model.py",
                   "scripts/render_telemetry_hook_recipes.py",
+                  "scripts/render_world_class_claim_guard.py",
                   "scripts/render_world_class_evidence_intake.py",
                   "scripts/render_world_class_evidence_ledger.py",
                   "scripts/render_world_class_evidence_plan.py",
@@ -8014,14 +8031,14 @@
             },
             "help_smoke": {
               "enabled": true,
-              "checked_count": 70,
+              "checked_count": 71,
               "failed_count": 0,
               "failed_scripts": []
             },
             "trust_summary": {
               "secret_findings": 0,
               "network_script_count": 3,
-              "file_write_script_count": 57,
+              "file_write_script_count": 58,
               "subprocess_script_count": 8,
               "interactive_script_count": 0,
               "help_smoke_failed_count": 0
@@ -8041,7 +8058,7 @@
             ],
             "capability_counts": {
               "network": 3,
-              "file_write": 57,
+              "file_write": 58,
               "subprocess": 8,
               "interactive": 0
             },
@@ -8318,6 +8335,7 @@
                 "scripts/render_social_preview.py",
                 "scripts/render_system_model.py",
                 "scripts/render_telemetry_hook_recipes.py",
+                "scripts/render_world_class_claim_guard.py",
                 "scripts/render_world_class_evidence_intake.py",
                 "scripts/render_world_class_evidence_ledger.py",
                 "scripts/render_world_class_evidence_plan.py",
@@ -8344,8 +8362,7 @@
                 "scripts/verify_package.py",
                 "scripts/yao.py",
                 "scripts/yao_cli_config.py",
-                "scripts/yao_cli_parser.py",
-                "scripts/yao_cli_telemetry.py"
+                "scripts/yao_cli_parser.py"
               ],
               "assets": [
                 "templates/basic_skill.md.j2",
@@ -8504,7 +8521,7 @@
                 },
                 "file_write": {
                   "required": true,
-                  "script_count": 57,
+                  "script_count": 58,
                   "scripts": [
                     "scripts/adjudicate_output_review.py",
                     "scripts/build_confusion_matrix.py",
@@ -8550,6 +8567,7 @@
                     "scripts/render_social_preview.py",
                     "scripts/render_system_model.py",
                     "scripts/render_telemetry_hook_recipes.py",
+                    "scripts/render_world_class_claim_guard.py",
                     "scripts/render_world_class_evidence_intake.py",
                     "scripts/render_world_class_evidence_ledger.py",
                     "scripts/render_world_class_evidence_plan.py",
@@ -8600,14 +8618,14 @@
               },
               "help_smoke": {
                 "enabled": true,
-                "checked_count": 70,
+                "checked_count": 71,
                 "failed_count": 0,
                 "failed_scripts": []
               },
               "trust_summary": {
                 "secret_findings": 0,
                 "network_script_count": 3,
-                "file_write_script_count": 57,
+                "file_write_script_count": 58,
                 "subprocess_script_count": 8,
                 "interactive_script_count": 0,
                 "help_smoke_failed_count": 0
@@ -8629,7 +8647,7 @@
               ],
               "capability_counts": {
                 "network": 3,
-                "file_write": 57,
+                "file_write": 58,
                 "subprocess": 8,
                 "interactive": 0
               },
@@ -8739,7 +8757,7 @@
               },
               "file_write": {
                 "required": true,
-                "script_count": 57,
+                "script_count": 58,
                 "scripts": [
                   "scripts/adjudicate_output_review.py",
                   "scripts/build_confusion_matrix.py",
@@ -8785,6 +8803,7 @@
                   "scripts/render_social_preview.py",
                   "scripts/render_system_model.py",
                   "scripts/render_telemetry_hook_recipes.py",
+                  "scripts/render_world_class_claim_guard.py",
                   "scripts/render_world_class_evidence_intake.py",
                   "scripts/render_world_class_evidence_ledger.py",
                   "scripts/render_world_class_evidence_plan.py",
@@ -8835,14 +8854,14 @@
             },
             "help_smoke": {
               "enabled": true,
-              "checked_count": 70,
+              "checked_count": 71,
               "failed_count": 0,
               "failed_scripts": []
             },
             "trust_summary": {
               "secret_findings": 0,
               "network_script_count": 3,
-              "file_write_script_count": 57,
+              "file_write_script_count": 58,
               "subprocess_script_count": 8,
               "interactive_script_count": 0,
               "help_smoke_failed_count": 0
@@ -8862,7 +8881,7 @@
             ],
             "capability_counts": {
               "network": 3,
-              "file_write": 57,
+              "file_write": 58,
               "subprocess": 8,
               "interactive": 0
             },
@@ -9534,8 +9553,8 @@
       "ok": true,
       "skill_dir": ".",
       "summary": {
-        "scanned_files": 164,
-        "script_count": 80,
+        "scanned_files": 165,
+        "script_count": 81,
         "internal_module_count": 10,
         "secret_findings": 0,
         "dependency_files": [
@@ -9544,18 +9563,18 @@
         "network_script_count": 3,
         "network_policy_covered_count": 3,
         "network_policy_missing_count": 0,
-        "file_write_script_count": 57,
+        "file_write_script_count": 58,
         "permission_required_count": 3,
         "permission_approved_count": 3,
         "permission_missing_count": 0,
         "permission_invalid_count": 0,
         "permission_expired_count": 0,
-        "help_smoke_checked_count": 70,
+        "help_smoke_checked_count": 71,
         "help_smoke_failed_count": 0,
         "interactive_script_count": 0,
         "package_hash_scope": "source-contract-without-generated-reports",
-        "package_hash_file_count": 164,
-        "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+        "package_hash_file_count": 165,
+        "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
       },
       "failures": [],
       "warnings": [],
@@ -10306,6 +10325,20 @@
           "network_urls": [],
           "network_hosts": []
         },
+        {
+          "path": "scripts/render_world_class_claim_guard.py",
+          "interface": "cli",
+          "interface_declared": true,
+          "interface_reason": "Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists.",
+          "has_argparse": true,
+          "has_main_guard": true,
+          "uses_input": false,
+          "uses_network": false,
+          "uses_file_write": true,
+          "uses_subprocess": false,
+          "network_urls": [],
+          "network_hosts": []
+        },
         {
           "path": "scripts/render_world_class_evidence_intake.py",
           "interface": "cli",
@@ -10729,9 +10762,9 @@
       "help_smoke": {
         "enabled": true,
         "timeout_seconds": 5.0,
-        "candidate_count": 70,
-        "checked_count": 70,
-        "passed_count": 70,
+        "candidate_count": 71,
+        "checked_count": 71,
+        "passed_count": 71,
         "failed_count": 0,
         "skipped_count": 10,
         "failed_scripts": [],
@@ -11256,6 +11289,16 @@
             "stdout_excerpt": "usage: render_telemetry_hook_recipes.py [-h] [--output-json OUTPUT_JSON]\n                                        [--output-md OUTPUT_MD]\n                                        [--output-jsonl OUTPUT_JSONL]\n                                 ",
             "stderr_excerpt": ""
           },
+          {
+            "path": "scripts/render_world_class_claim_guard.py",
+            "command": "python3 scripts/render_world_class_claim_guard.py --help",
+            "returncode": 0,
+            "timed_out": false,
+            "passed": true,
+            "has_help_text": true,
+            "stdout_excerpt": "usage: render_world_class_claim_guard.py [-h] [--claim-surface CLAIM_SURFACE]\n                                         [--output-json OUTPUT_JSON]\n                                         [--output-md OUTPUT_MD]\n                            ",
+            "stderr_excerpt": ""
+          },
           {
             "path": "scripts/render_world_class_evidence_intake.py",
             "command": "python3 scripts/render_world_class_evidence_intake.py --help",
@@ -11576,6 +11619,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -11656,10 +11700,10 @@
         "context_budget_tier": "production",
         "context_budget_limit": 1000,
         "skill_body_tokens": 751,
-        "other_text_tokens": 1040839,
+        "other_text_tokens": 1051179,
         "estimated_initial_load_tokens": 944,
-        "estimated_total_text_tokens": 1041590,
-        "relevant_file_count": 447,
+        "estimated_total_text_tokens": 1051930,
+        "relevant_file_count": 453,
         "unused_resource_dirs": [],
         "quality_signal_points": 130,
         "quality_density": 137.7
@@ -12575,6 +12619,7 @@
               "scripts/render_social_preview.py",
               "scripts/render_system_model.py",
               "scripts/render_telemetry_hook_recipes.py",
+              "scripts/render_world_class_claim_guard.py",
               "scripts/render_world_class_evidence_intake.py",
               "scripts/render_world_class_evidence_ledger.py",
               "scripts/render_world_class_evidence_plan.py",
@@ -13925,6 +13970,322 @@
         "markdown": "reports/world_class_evidence_intake.md"
       }
     },
+    "world_class_claim_guard": {
+      "schema_version": "1.0",
+      "ok": true,
+      "generated_at": "2026-06-14",
+      "skill_dir": ".",
+      "summary": {
+        "ledger_ready_to_claim_world_class": false,
+        "ledger_pending_count": 4,
+        "claim_surface_count": 66,
+        "violation_count": 0,
+        "overclaim_guard_active": true,
+        "decision": "claim-guard-pass-evidence-pending"
+      },
+      "rules": [
+        {
+          "key": "ready-to-claim-true",
+          "reason": "ready_to_claim_world_class cannot be true while ledger evidence is pending.",
+          "pattern": "ready[\\s_-]*to[\\s_-]*claim[\\s_-]*world[\\s_-]*class\\s*[:=]\\s*`?true`?"
+        },
+        {
+          "key": "world-class-ready-true",
+          "reason": "world-class readiness cannot be claimed before accepted external and human evidence exists.",
+          "pattern": "(public\\s+)?world[\\s_-]*class[\\s_-]*ready\\s*[:=]\\s*`?true`?"
+        },
+        {
+          "key": "json-world-class-ready-true",
+          "reason": "machine-readable claim fields must remain false until the ledger is ready.",
+          "pattern": "\"(?:ready_to_claim_world_class|world_class_ready|public_world_class_ready)\"\\s*:\\s*true"
+        },
+        {
+          "key": "completion-phrase",
+          "reason": "completion language is blocked until the world-class ledger is accepted.",
+          "pattern": "(public\\s+)?world[\\s_-]*class\\s+(?:complete|completed|achieved|certified)"
+        },
+        {
+          "key": "zh-completion-phrase",
+          "reason": "中文完成态表述必须等到 ledger ready 后才能出现。",
+          "pattern": "世界级(?:已完成|完成|已达成|达成|准备就绪|可声明|认证通过)"
+        }
+      ],
+      "scanned_surfaces": [
+        {
+          "path": "README.md",
+          "violation_count": 0
+        },
+        {
+          "path": "SKILL.md",
+          "violation_count": 0
+        },
+        {
+          "path": "docs/README.fr-FR.md",
+          "violation_count": 0
+        },
+        {
+          "path": "docs/README.ja-JP.md",
+          "violation_count": 0
+        },
+        {
+          "path": "docs/README.ru-RU.md",
+          "violation_count": 0
+        },
+        {
+          "path": "docs/README.zh-CN.md",
+          "violation_count": 0
+        },
+        {
+          "path": "docs/migration-v2.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/adoption_drift_report.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/artifact-design-profile.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/baseline-compare.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/benchmark_methodology.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/benchmark_reproducibility.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/candidate_registry.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/compiled_targets.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/conformance_matrix.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/context_budget.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/description_drift_history.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/description_optimization.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/description_optimization_suite.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/family_summary.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/feishu-ranking-pattern-analysis-2026-04-01.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/github-benchmark-scan.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/install_simulation.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/intent-confidence.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/intent-dialogue.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration-directions.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/governed-incident-command/bundle.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/governed-incident-command/review.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/team-frontend-review/bundle.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/team-frontend-review/review.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/yao-meta-skill/bundle.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_bundles/yao-meta-skill/review.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/iteration_ledger.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/output-risk-profile.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/output_blind_review_pack.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/output_execution_runs.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/output_quality_scorecard.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/output_review_adjudication.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/package_verification.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/portability_score.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/promotion_decisions.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/prompt-quality-profile.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/reference-scan.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/reference-synthesis.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/registry_audit.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/regression_history.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/review-studio.html",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/review-viewer.html",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/review_annotations.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/review_waivers.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/route_scorecard.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/runtime_permission_probes.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/security_trust_report.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill-os-2-review.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill-overview-v2-plan.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill-overview.html",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill_atlas.html",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill_os2_audit.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/skill_os2_coverage.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/system-model.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/telemetry_hook_recipes.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/upgrade_check.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/world_class_evidence_intake.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/world_class_evidence_ledger.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/world_class_evidence_plan.md",
+          "violation_count": 0
+        },
+        {
+          "path": "reports/yao-deploy-bridge-skill-research-plan.md",
+          "violation_count": 0
+        }
+      ],
+      "violations": [],
+      "source_ledger": {
+        "json": "reports/world_class_evidence_ledger.json",
+        "markdown": "reports/world_class_evidence_ledger.md"
+      },
+      "artifacts": {
+        "json": "reports/world_class_claim_guard.json",
+        "markdown": "reports/world_class_claim_guard.md"
+      }
+    },
     "registry": {
       "ok": true,
       "schema_version": "2.0",
@@ -13948,8 +14309,8 @@
         "trust_level": "local",
         "license": "MIT",
         "checksums": {
-          "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1",
-          "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+          "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15",
+          "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
         },
         "compatibility": {
           "openai": "pass",
@@ -13980,7 +14341,7 @@
         },
         "distribution": {
           "archive_verified": true,
-          "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
+          "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
           "package_verification": "reports/package_verification.json",
           "install_simulated": true,
           "install_simulation": "reports/install_simulation.json"
@@ -14005,7 +14366,7 @@
               "vscode"
             ],
             "package_metadata": "registry/packages/yao-meta-skill.json",
-            "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+            "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
           }
         ]
       },
@@ -14028,8 +14389,8 @@
         "target_count": 4,
         "adapter_count": 4,
         "archive_present": true,
-        "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
-        "archive_entry_count": 539,
+        "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
+        "archive_entry_count": 543,
         "failure_count": 0,
         "warning_count": 0
       },
@@ -14694,7 +15055,7 @@
       "installed_skill_dir": "[temporary-install-root]/yao-meta-skill",
       "summary": {
         "archive_present": true,
-        "archive_entry_count": 539,
+        "archive_entry_count": 543,
         "archive_extracted": true,
         "entrypoint_loaded": true,
         "manifest_loaded": true,
@@ -15036,12 +15397,12 @@
           {
             "field": "archive_sha256",
             "from": "",
-            "to": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+            "to": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
           },
           {
             "field": "package_sha256",
             "from": "0000000000000000000000000000000000000000000000000000000000000000",
-            "to": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+            "to": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
           }
         ]
       },
diff --git a/reports/security_trust_report.json b/reports/security_trust_report.json
index ecb4634..4a4742f 100644
--- a/reports/security_trust_report.json
+++ b/reports/security_trust_report.json
@@ -2,8 +2,8 @@
   "ok": true,
   "skill_dir": ".",
   "summary": {
-    "scanned_files": 164,
-    "script_count": 80,
+    "scanned_files": 165,
+    "script_count": 81,
     "internal_module_count": 10,
     "secret_findings": 0,
     "dependency_files": [
@@ -12,18 +12,18 @@
     "network_script_count": 3,
     "network_policy_covered_count": 3,
     "network_policy_missing_count": 0,
-    "file_write_script_count": 57,
+    "file_write_script_count": 58,
     "permission_required_count": 3,
     "permission_approved_count": 3,
     "permission_missing_count": 0,
     "permission_invalid_count": 0,
     "permission_expired_count": 0,
-    "help_smoke_checked_count": 70,
+    "help_smoke_checked_count": 71,
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 164,
-    "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+    "package_hash_file_count": 165,
+    "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
   },
   "failures": [],
   "warnings": [],
@@ -774,6 +774,20 @@
       "network_urls": [],
       "network_hosts": []
     },
+    {
+      "path": "scripts/render_world_class_claim_guard.py",
+      "interface": "cli",
+      "interface_declared": true,
+      "interface_reason": "Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists.",
+      "has_argparse": true,
+      "has_main_guard": true,
+      "uses_input": false,
+      "uses_network": false,
+      "uses_file_write": true,
+      "uses_subprocess": false,
+      "network_urls": [],
+      "network_hosts": []
+    },
     {
       "path": "scripts/render_world_class_evidence_intake.py",
       "interface": "cli",
@@ -1197,9 +1211,9 @@
   "help_smoke": {
     "enabled": true,
     "timeout_seconds": 5.0,
-    "candidate_count": 70,
-    "checked_count": 70,
-    "passed_count": 70,
+    "candidate_count": 71,
+    "checked_count": 71,
+    "passed_count": 71,
     "failed_count": 0,
     "skipped_count": 10,
     "failed_scripts": [],
@@ -1724,6 +1738,16 @@
         "stdout_excerpt": "usage: render_telemetry_hook_recipes.py [-h] [--output-json OUTPUT_JSON]\n                                        [--output-md OUTPUT_MD]\n                                        [--output-jsonl OUTPUT_JSONL]\n                                 ",
         "stderr_excerpt": ""
       },
+      {
+        "path": "scripts/render_world_class_claim_guard.py",
+        "command": "python3 scripts/render_world_class_claim_guard.py --help",
+        "returncode": 0,
+        "timed_out": false,
+        "passed": true,
+        "has_help_text": true,
+        "stdout_excerpt": "usage: render_world_class_claim_guard.py [-h] [--claim-surface CLAIM_SURFACE]\n                                         [--output-json OUTPUT_JSON]\n                                         [--output-md OUTPUT_MD]\n                            ",
+        "stderr_excerpt": ""
+      },
       {
         "path": "scripts/render_world_class_evidence_intake.py",
         "command": "python3 scripts/render_world_class_evidence_intake.py --help",
@@ -2044,6 +2068,7 @@
           "scripts/render_social_preview.py",
           "scripts/render_system_model.py",
           "scripts/render_telemetry_hook_recipes.py",
+          "scripts/render_world_class_claim_guard.py",
           "scripts/render_world_class_evidence_intake.py",
           "scripts/render_world_class_evidence_ledger.py",
           "scripts/render_world_class_evidence_plan.py",
diff --git a/reports/security_trust_report.md b/reports/security_trust_report.md
index 3528dae..d6edab7 100644
--- a/reports/security_trust_report.md
+++ b/reports/security_trust_report.md
@@ -1,22 +1,22 @@
 # Security Trust Report
 
 - OK: `True`
-- Scanned files: `164`
-- Scripts: `80`
+- Scanned files: `165`
+- Scripts: `81`
 - Internal script modules: `10`
 - Secret findings: `0`
 - Network-capable scripts: `3`
 - Network policy covered scripts: `3`
 - Network policy missing scripts: `0`
-- File-write scripts: `57`
+- File-write scripts: `58`
 - Permission approvals: `3 / 3`
 - Permission approval gaps: `0`
-- CLI help smoke checked: `70`
+- CLI help smoke checked: `71`
 - CLI help smoke failures: `0`
 - Interactive scripts: `0`
 - Package hash scope: `source-contract-without-generated-reports`
-- Package hash files: `164`
-- Package SHA256: `9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1`
+- Package hash files: `165`
+- Package SHA256: `81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15`
 
 ## Failures
 
@@ -54,8 +54,8 @@
 
 - Enabled: `True`
 - Timeout seconds: `5.0`
-- Checked scripts: `70`
-- Passed scripts: `70`
+- Checked scripts: `71`
+- Passed scripts: `71`
 - Failed scripts: `none`
 
 ## Script Surface
@@ -114,6 +114,7 @@
 | scripts/render_social_preview.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/render_system_model.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
 | scripts/render_telemetry_hook_recipes.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
+| scripts/render_world_class_claim_guard.py | cli | True | True | True | False | False | True | False | Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists. |
 | scripts/render_world_class_evidence_intake.py | cli | True | True | True | False | False | True | False | Validates world-class human and external evidence intake packets before ledger review. |
 | scripts/render_world_class_evidence_ledger.py | cli | True | True | True | False | False | True | False | Renders a machine-checkable ledger for world-class external and human evidence gaps. |
 | scripts/render_world_class_evidence_plan.py | cli | False | True | True | False | False | True | False | Default CLI classification; add SCRIPT_INTERFACE for internal modules. |
diff --git a/reports/skill-overview.html b/reports/skill-overview.html
index fe750e8..e23e663 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="0.9 99.1" 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="0.9 99.1" stroke-dashoffset="-0.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.9 99.1" stroke-dashoffset="-1.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.9 99.1" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="27.6 72.4" stroke-dashoffset="-3.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="69.0 31.0" stroke-dashoffset="-31.0" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">333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="0.9 99.1" 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="0.9 99.1" stroke-dashoffset="-0.9" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#D0DCE9" stroke-width="24" stroke-dasharray="0.9 99.1" stroke-dashoffset="-1.7" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#E4ECF5" stroke-width="24" stroke-dasharray="0.9 99.1" stroke-dashoffset="-2.6" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#e8e6dc" stroke-width="24" stroke-dasharray="27.4 72.6" stroke-dashoffset="-3.4" pathLength="100" transform="rotate(-90 130 130)"/><circle cx="130" cy="130" r="70" fill="none" stroke="#504e49" stroke-width="24" stroke-dasharray="69.2 30.8" stroke-dashoffset="-30.8" pathLength="100" transform="rotate(-90 130 130)"/><text x="130" y="136" text-anchor="middle">336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 e8264cd..6b4a26d 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": 80
+        "file_count": 81
       },
       {
         "path": "evals",
@@ -448,10 +448,10 @@
         "path": "reports",
         "label": "Generated evidence and overview artifacts",
         "kind": "folder",
-        "file_count": 189
+        "file_count": 191
       }
     ],
-    "file_count": 333,
+    "file_count": 336,
     "folder_count": 4,
     "distribution": [
       {
@@ -476,7 +476,7 @@
       },
       {
         "label": "scripts",
-        "value": 80
+        "value": 81
       },
       {
         "label": "evals",
@@ -484,7 +484,7 @@
       },
       {
         "label": "reports",
-        "value": 189
+        "value": 191
       }
     ]
   },
@@ -605,7 +605,7 @@
       "path": "scripts",
       "label": "Deterministic helpers or local tooling",
       "kind": "folder",
-      "file_count": 80
+      "file_count": 81
     },
     {
       "path": "evals",
@@ -617,7 +617,7 @@
       "path": "reports",
       "label": "Generated evidence and overview artifacts",
       "kind": "folder",
-      "file_count": 189
+      "file_count": 191
     }
   ],
   "strengths": [
@@ -889,11 +889,11 @@
     "summary": {
       "reproducibility_ready": true,
       "methodology_complete": true,
-      "required_artifact_count": 18,
+      "required_artifact_count": 19,
       "missing_artifact_count": 0,
       "output_case_count": 5,
       "failure_disclosure_count": 3,
-      "command_count": 17,
+      "command_count": 18,
       "command_executed_count": 10,
       "timing_observed_count": 10,
       "model_executed_count": 0,
@@ -905,9 +905,9 @@
       "world_class_task_count": 4,
       "world_class_ledger_pending_count": 4,
       "working_tree_dirty": true,
-      "changed_file_count": 56
+      "changed_file_count": 42
     },
-    "commit": "60995ed569b1c99aa6f6ae2b4406e04327202beb",
+    "commit": "c1c85093d1ea67954d414789f96c87bbc3964868",
     "missing_artifacts": [],
     "limitations": [
       "Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
@@ -982,8 +982,8 @@
     "failures": []
   },
   "trust_security": {
-    "scanned_files": 164,
-    "script_count": 80,
+    "scanned_files": 165,
+    "script_count": 81,
     "internal_module_count": 10,
     "secret_findings": 0,
     "dependency_files": [
@@ -992,18 +992,18 @@
     "network_script_count": 3,
     "network_policy_covered_count": 3,
     "network_policy_missing_count": 0,
-    "file_write_script_count": 57,
+    "file_write_script_count": 58,
     "permission_required_count": 3,
     "permission_approved_count": 3,
     "permission_missing_count": 0,
     "permission_invalid_count": 0,
     "permission_expired_count": 0,
-    "help_smoke_checked_count": 70,
+    "help_smoke_checked_count": 71,
     "help_smoke_failed_count": 0,
     "interactive_script_count": 0,
     "package_hash_scope": "source-contract-without-generated-reports",
-    "package_hash_file_count": 164,
-    "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+    "package_hash_file_count": 165,
+    "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
   },
   "skill_atlas": {
     "skill_count": 12,
@@ -1041,8 +1041,8 @@
       "trust_level": "local",
       "license": "MIT",
       "checksums": {
-        "package_sha256": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1",
-        "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+        "package_sha256": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15",
+        "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
       },
       "compatibility": {
         "openai": "pass",
@@ -1073,7 +1073,7 @@
       },
       "distribution": {
         "archive_verified": true,
-        "archive_sha256": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
+        "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
         "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": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094",
-      "archive_entry_count": 539,
+      "archive_sha256": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404",
+      "archive_entry_count": 543,
       "failure_count": 0,
       "warning_count": 0
     },
@@ -1101,7 +1101,7 @@
     "ok": true,
     "summary": {
       "archive_present": true,
-      "archive_entry_count": 539,
+      "archive_entry_count": 543,
       "archive_extracted": true,
       "entrypoint_loaded": true,
       "manifest_loaded": true,
@@ -1168,12 +1168,12 @@
         {
           "field": "archive_sha256",
           "from": "",
-          "to": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+          "to": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
         },
         {
           "field": "package_sha256",
           "from": "0000000000000000000000000000000000000000000000000000000000000000",
-          "to": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+          "to": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
         }
       ]
     },
diff --git a/reports/skill_atlas.json b/reports/skill_atlas.json
index 67c555b..beb28a4 100644
--- a/reports/skill_atlas.json
+++ b/reports/skill_atlas.json
@@ -116,6 +116,7 @@
           "scripts/render_social_preview.py",
           "scripts/render_system_model.py",
           "scripts/render_telemetry_hook_recipes.py",
+          "scripts/render_world_class_claim_guard.py",
           "scripts/render_world_class_evidence_intake.py",
           "scripts/render_world_class_evidence_ledger.py",
           "scripts/render_world_class_evidence_plan.py",
diff --git a/reports/skill_os2_audit.json b/reports/skill_os2_audit.json
index 2239a51..03fb479 100644
--- a/reports/skill_os2_audit.json
+++ b/reports/skill_os2_audit.json
@@ -145,7 +145,7 @@
       "key": "benchmark-reproducibility",
       "label": "Benchmark Reproducibility",
       "status": "pass",
-      "current": "artifacts 18; missing 0; failures 3",
+      "current": "artifacts 19; missing 0; failures 3",
       "target": "Public methodology, reproducible commands, required artifacts, and failure disclosure are machine-checkable",
       "evidence": [
         {
@@ -197,7 +197,7 @@
       "key": "trust-security",
       "label": "Trust Security",
       "status": "pass",
-      "current": "secrets 0; scripts 80; help failures 0",
+      "current": "secrets 0; scripts 81; 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 539; install failures 0; permission failures 0",
+      "current": "zip entries 543; install failures 0; permission failures 0",
       "target": "Package metadata, archive checksum, package verification, and install simulation pass",
       "evidence": [
         {
diff --git a/reports/skill_os2_audit.md b/reports/skill_os2_audit.md
index 2f74282..f5416a7 100644
--- a/reports/skill_os2_audit.md
+++ b/reports/skill_os2_audit.md
@@ -21,13 +21,13 @@ Generated at: `2026-06-14`
 | Output Eval Lab | pass | 5 cases; delta 100.0; exec 10; blind 5 | with-skill/baseline, assertions, execution evidence, blind A/B, failure taxonomy | Add more real-file and adversarial holdout cases as usage grows. |
 | Provider Holdout | external-required | model-executed 0; token-observed 0 | At least one real provider-backed holdout run with observed model/timing/token metadata | Run provider-backed holdout cases with real credentials and commit only aggregate evidence. |
 | 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 18; 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. |
+| Benchmark Reproducibility | pass | artifacts 19; 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 80; 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 81; 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 539; install failures 0; permission failures 0 | Package metadata, archive checksum, package verification, and install simulation pass | Regenerate registry after package verification so checksums stay aligned. |
+| Registry Distribution | pass | zip entries 543; 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 90 | 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 9fc8843..442d260 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": "80 scripts; secrets 0; help failures 0",
+      "current": "81 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 539; install failures 0",
+      "current": "archive entries 543; 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": [
@@ -305,7 +305,7 @@
       "label": "Benchmark Methodology",
       "status": "pass",
       "objective": "Recommended Skill OS 2.0 implementation PR from the upgrade plan.",
-      "current": "18 required artifacts checked",
+      "current": "19 required artifacts checked",
       "command": "make ci-test",
       "test": "tests/verify_benchmark_reproducibility.py",
       "evidence": [
diff --git a/reports/skill_os2_coverage.md b/reports/skill_os2_coverage.md
index e9187b8..472f1e3 100644
--- a/reports/skill_os2_coverage.md
+++ b/reports/skill_os2_coverage.md
@@ -21,9 +21,9 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
 | Skill IR | `pass` | schema 2.0.0; targets 5 | `python3 scripts/yao.py skill-ir .` | `python3 tests/verify_skill_ir.py` |
 | Output Eval Lab | `pass` | 5 cases; delta 100.0; execution 10 | `python3 scripts/yao.py output-exec . && python3 scripts/yao.py output-review .` | `python3 tests/verify_output_eval_lab.py` |
 | Runtime Conformance | `pass` | 5/5 targets pass | `python3 scripts/yao.py conformance .` | `python3 tests/verify_conformance_suite.py` |
-| Trust Security | `pass` | 80 scripts; secrets 0; help failures 0 | `python3 scripts/yao.py trust .` | `python3 tests/verify_trust_check.py` |
+| Trust Security | `pass` | 81 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 539; install failures 0 | `python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip && python3 scripts/yao.py registry-audit .` | `python3 tests/verify_registry_audit.py` |
+| Registry Distribution | `pass` | archive entries 543; 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` | 14 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` |
 
@@ -31,7 +31,7 @@ This report maps the Skill OS 2.0 upgrade blueprint to concrete local artifacts,
 
 | Item | Status | Current | Command | Test |
 | --- | --- | --- | --- | --- |
-| Benchmark Methodology | `pass` | 18 required artifacts checked | `make ci-test` | `tests/verify_benchmark_reproducibility.py` |
+| Benchmark Methodology | `pass` | 19 required artifacts checked | `make ci-test` | `tests/verify_benchmark_reproducibility.py` |
 | Output Eval Schema | `pass` | 5 output cases | `make ci-test` | `tests/verify_output_eval_lab.py` |
 | Output Eval Runner | `pass` | delta 100.0 | `make ci-test` | `tests/verify_output_eval_lab.py` |
 | Output Quality Scorecard | `pass` | gate pass True | `make ci-test` | `tests/verify_output_eval_lab.py` |
diff --git a/reports/upgrade_check.json b/reports/upgrade_check.json
index 4415ab8..ce93695 100644
--- a/reports/upgrade_check.json
+++ b/reports/upgrade_check.json
@@ -70,12 +70,12 @@
       {
         "field": "archive_sha256",
         "from": "",
-        "to": "b68dd2aaecfa1f585fb5b380d89a04adde672e7996b7750b3ecceb8ba2e3d094"
+        "to": "55066438e0934145506d04883e617e340cf09cea824e8764a0d65f54bab6c404"
       },
       {
         "field": "package_sha256",
         "from": "0000000000000000000000000000000000000000000000000000000000000000",
-        "to": "9bbb47aaed8b2b003c68176ab3a8a4c3926493ded7c80be004881254cc113ee1"
+        "to": "81b0f6007b71b949e1fba7079ffd8156fe906c6784eced95fd1f9a30f7f5bc15"
       }
     ]
   },
diff --git a/reports/world_class_claim_guard.json b/reports/world_class_claim_guard.json
new file mode 100644
index 0000000..ca193a2
--- /dev/null
+++ b/reports/world_class_claim_guard.json
@@ -0,0 +1,316 @@
+{
+  "schema_version": "1.0",
+  "ok": true,
+  "generated_at": "2026-06-14",
+  "skill_dir": ".",
+  "summary": {
+    "ledger_ready_to_claim_world_class": false,
+    "ledger_pending_count": 4,
+    "claim_surface_count": 66,
+    "violation_count": 0,
+    "overclaim_guard_active": true,
+    "decision": "claim-guard-pass-evidence-pending"
+  },
+  "rules": [
+    {
+      "key": "ready-to-claim-true",
+      "reason": "ready_to_claim_world_class cannot be true while ledger evidence is pending.",
+      "pattern": "ready[\\s_-]*to[\\s_-]*claim[\\s_-]*world[\\s_-]*class\\s*[:=]\\s*`?true`?"
+    },
+    {
+      "key": "world-class-ready-true",
+      "reason": "world-class readiness cannot be claimed before accepted external and human evidence exists.",
+      "pattern": "(public\\s+)?world[\\s_-]*class[\\s_-]*ready\\s*[:=]\\s*`?true`?"
+    },
+    {
+      "key": "json-world-class-ready-true",
+      "reason": "machine-readable claim fields must remain false until the ledger is ready.",
+      "pattern": "\"(?:ready_to_claim_world_class|world_class_ready|public_world_class_ready)\"\\s*:\\s*true"
+    },
+    {
+      "key": "completion-phrase",
+      "reason": "completion language is blocked until the world-class ledger is accepted.",
+      "pattern": "(public\\s+)?world[\\s_-]*class\\s+(?:complete|completed|achieved|certified)"
+    },
+    {
+      "key": "zh-completion-phrase",
+      "reason": "中文完成态表述必须等到 ledger ready 后才能出现。",
+      "pattern": "世界级(?:已完成|完成|已达成|达成|准备就绪|可声明|认证通过)"
+    }
+  ],
+  "scanned_surfaces": [
+    {
+      "path": "README.md",
+      "violation_count": 0
+    },
+    {
+      "path": "SKILL.md",
+      "violation_count": 0
+    },
+    {
+      "path": "docs/README.fr-FR.md",
+      "violation_count": 0
+    },
+    {
+      "path": "docs/README.ja-JP.md",
+      "violation_count": 0
+    },
+    {
+      "path": "docs/README.ru-RU.md",
+      "violation_count": 0
+    },
+    {
+      "path": "docs/README.zh-CN.md",
+      "violation_count": 0
+    },
+    {
+      "path": "docs/migration-v2.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/adoption_drift_report.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/artifact-design-profile.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/baseline-compare.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/benchmark_methodology.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/benchmark_reproducibility.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/candidate_registry.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/compiled_targets.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/conformance_matrix.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/context_budget.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/description_drift_history.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/description_optimization.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/description_optimization_suite.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/family_summary.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/feishu-ranking-pattern-analysis-2026-04-01.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/github-benchmark-scan.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/install_simulation.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/intent-confidence.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/intent-dialogue.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration-directions.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/governed-incident-command/bundle.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/governed-incident-command/review.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/team-frontend-review/bundle.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/team-frontend-review/review.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/yao-meta-skill/bundle.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_bundles/yao-meta-skill/review.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/iteration_ledger.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/output-risk-profile.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/output_blind_review_pack.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/output_execution_runs.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/output_quality_scorecard.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/output_review_adjudication.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/package_verification.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/portability_score.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/promotion_decisions.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/prompt-quality-profile.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/reference-scan.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/reference-synthesis.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/registry_audit.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/regression_history.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/review-studio.html",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/review-viewer.html",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/review_annotations.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/review_waivers.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/route_scorecard.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/runtime_permission_probes.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/security_trust_report.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill-os-2-review.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill-overview-v2-plan.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill-overview.html",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill_atlas.html",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill_os2_audit.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/skill_os2_coverage.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/system-model.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/telemetry_hook_recipes.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/upgrade_check.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/world_class_evidence_intake.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/world_class_evidence_ledger.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/world_class_evidence_plan.md",
+      "violation_count": 0
+    },
+    {
+      "path": "reports/yao-deploy-bridge-skill-research-plan.md",
+      "violation_count": 0
+    }
+  ],
+  "violations": [],
+  "source_ledger": {
+    "json": "reports/world_class_evidence_ledger.json",
+    "markdown": "reports/world_class_evidence_ledger.md"
+  },
+  "artifacts": {
+    "json": "reports/world_class_claim_guard.json",
+    "markdown": "reports/world_class_claim_guard.md"
+  }
+}
diff --git a/reports/world_class_claim_guard.md b/reports/world_class_claim_guard.md
new file mode 100644
index 0000000..ff12416
--- /dev/null
+++ b/reports/world_class_claim_guard.md
@@ -0,0 +1,30 @@
+# World-Class Claim Guard
+
+Generated at: `2026-06-14`
+
+## Summary
+
+- decision: `claim-guard-pass-evidence-pending`
+- ledger ready to claim world-class: `false`
+- ledger pending evidence: `4`
+- claim surfaces scanned: `66`
+- violations: `0`
+- overclaim guard active: `true`
+
+This guard scans public claim surfaces for completion language that would contradict the world-class evidence ledger. It allows evidence planning and pending-state language, but blocks completion claims until the ledger is ready.
+
+## Violations
+
+| Path | Line | Rule | Excerpt |
+| --- | ---: | --- | --- |
+| `none` | 0 | `none` | none |
+
+## Rules
+
+| Rule | Reason |
+| --- | --- |
+| `ready-to-claim-true` | ready_to_claim_world_class cannot be true while ledger evidence is pending. |
+| `world-class-ready-true` | world-class readiness cannot be claimed before accepted external and human evidence exists. |
+| `json-world-class-ready-true` | machine-readable claim fields must remain false until the ledger is ready. |
+| `completion-phrase` | completion language is blocked until the world-class ledger is accepted. |
+| `zh-completion-phrase` | 中文完成态表述必须等到 ledger ready 后才能出现。 |
diff --git a/scripts/ci_test.py b/scripts/ci_test.py
index dd37198..b9cd606 100644
--- a/scripts/ci_test.py
+++ b/scripts/ci_test.py
@@ -53,6 +53,7 @@ DEFAULT_TARGETS = [
     "world-class-evidence-check",
     "world-class-ledger-check",
     "world-class-intake-check",
+    "world-class-claim-guard-check",
     "benchmark-reproducibility-check",
     "feedback-check",
     "adoption-drift-check",
diff --git a/scripts/render_benchmark_reproducibility.py b/scripts/render_benchmark_reproducibility.py
index b8ec3db..c7b8ccc 100644
--- a/scripts/render_benchmark_reproducibility.py
+++ b/scripts/render_benchmark_reproducibility.py
@@ -40,6 +40,7 @@ REQUIRED_ARTIFACTS = [
     ("world_class_evidence_plan", "reports/world_class_evidence_plan.json"),
     ("world_class_evidence_ledger", "reports/world_class_evidence_ledger.json"),
     ("world_class_evidence_intake", "reports/world_class_evidence_intake.json"),
+    ("world_class_claim_guard", "reports/world_class_claim_guard.json"),
 ]
 
 REPRODUCTION_COMMANDS = [
@@ -123,6 +124,11 @@ REPRODUCTION_COMMANDS = [
         "command": "python3 scripts/yao.py world-class-intake .",
         "evidence": "reports/world_class_evidence_intake.json",
     },
+    {
+        "label": "world-class claim guard",
+        "command": "python3 scripts/yao.py world-class-claim-guard .",
+        "evidence": "reports/world_class_claim_guard.json",
+    },
     {
         "label": "full ci",
         "command": "make ci-test",
diff --git a/scripts/render_review_studio.py b/scripts/render_review_studio.py
index 1a0deba..a9a0d85 100644
--- a/scripts/render_review_studio.py
+++ b/scripts/render_review_studio.py
@@ -138,6 +138,7 @@ def evidence_paths(skill_dir: Path) -> dict[str, str]:
         "world_class_evidence_plan": "reports/world_class_evidence_plan.md",
         "world_class_evidence_ledger": "reports/world_class_evidence_ledger.md",
         "world_class_evidence_intake": "reports/world_class_evidence_intake.md",
+        "world_class_claim_guard": "reports/world_class_claim_guard.md",
         "registry_audit": "reports/registry_audit.md",
         "package_verification": "reports/package_verification.md",
         "install_simulation": "reports/install_simulation.md",
@@ -172,6 +173,7 @@ def load_review_data(skill_dir: Path) -> dict[str, dict[str, Any]]:
         "review_annotations": load_json(reports / "review_annotations.json"),
         "world_class_evidence_ledger": load_json(reports / "world_class_evidence_ledger.json"),
         "world_class_evidence_intake": load_json(reports / "world_class_evidence_intake.json"),
+        "world_class_claim_guard": load_json(reports / "world_class_claim_guard.json"),
         "registry": load_json(reports / "registry_audit.json"),
         "package_verification": load_json(reports / "package_verification.json"),
         "install_simulation": load_json(reports / "install_simulation.json"),
@@ -198,6 +200,7 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
     waivers = data["review_waivers"].get("summary", {})
     annotations = data["review_annotations"].get("summary", {})
     intake = data["world_class_evidence_intake"].get("summary", {})
+    claim_guard = data["world_class_claim_guard"].get("summary", {})
     registry = data["registry"].get("package", {})
     package_verification = data["package_verification"].get("summary", {})
     install_simulation = data["install_simulation"].get("summary", {})
@@ -280,6 +283,11 @@ def insight_cards(data: dict[str, dict[str, Any]]) -> list[dict[str, str]]:
                 f"{intake.get('invalid_submission_count', 0)} invalid"
             ),
         },
+        {
+            "label": "Claim Guard",
+            "value": str(claim_guard.get("violation_count", 0)),
+            "detail": f"{claim_guard.get('claim_surface_count', 0)} public surfaces scanned",
+        },
         {
             "label": "Notes",
             "value": f"{annotations.get('open_count', 0)}/{annotations.get('annotation_count', 0)}",
@@ -485,6 +493,7 @@ ACTION_GUIDANCE: dict[str, dict[str, str]] = {
             {"path": "reports/world_class_evidence_ledger.md", "label": "world-class evidence ledger", "kind": "report", "patterns": ["# World-Class Evidence Ledger"]},
             {"path": "reports/world_class_evidence_plan.md", "label": "world-class evidence plan", "kind": "report", "patterns": ["# World-Class Evidence Plan"]},
             {"path": "reports/world_class_evidence_intake.md", "label": "world-class evidence intake", "kind": "report", "patterns": ["# World-Class Evidence Intake"]},
+            {"path": "reports/world_class_claim_guard.md", "label": "world-class claim guard", "kind": "report", "patterns": ["# World-Class Claim Guard"]},
             {"path": "evidence/world_class/intake.schema.json", "label": "evidence intake schema", "kind": "schema", "patterns": ["Yao World-Class Evidence Intake"]},
             {"path": "evidence/world_class/templates/provider-holdout.intake.json", "label": "provider intake template", "kind": "template", "patterns": ["provider-holdout"]},
             {"path": "evidence/world_class/templates/human-adjudication.intake.json", "label": "human intake template", "kind": "template", "patterns": ["human-adjudication"]},
@@ -710,6 +719,7 @@ def render_html(report: dict[str, Any]) -> str:
     world_class_ledger = report["data"].get("world_class_evidence_ledger", {})
     world_class_summary = world_class_ledger.get("summary", {})
     world_class_intake_summary = report["data"].get("world_class_evidence_intake", {}).get("summary", {})
+    world_class_claim_summary = report["data"].get("world_class_claim_guard", {}).get("summary", {})
     world_class_entries_html = render_world_class_evidence_entries(world_class_ledger)
     annotation_summary = report["data"]["review_annotations"].get("summary", {})
     annotation_caption = (
@@ -844,6 +854,17 @@ def render_html(report: dict[str, Any]) -> str:
         ],
         "world-class evidence intake missing",
     )
+    world_class_claim_panel = render_kv_grid(
+        world_class_claim_summary,
+        [
+            "ledger_ready_to_claim_world_class",
+            "ledger_pending_count",
+            "claim_surface_count",
+            "violation_count",
+            "overclaim_guard_active",
+        ],
+        "world-class claim guard missing",
+    )
     registry_panel = render_kv_grid(
         registry_package_summary(registry_package),
         [
@@ -1032,6 +1053,11 @@ def render_html(report: dict[str, Any]) -> str:
       <div class="panel"><h2>入口边界</h2><p>intake 只校验证据包格式、来源、隐私和反过度声明；只有 ledger 看到真实 provider、真人、原生权限或真实客户端结果后，world-class 才能进入完成审计。</p></div>
     </section>
 
+    <section class="twocol">
+      <div class="panel"><h2>声明守卫</h2>{world_class_claim_panel}</div>
+      <div class="panel"><h2>声明边界</h2><p>claim guard 扫描 README、docs 和 reports 中的完成态表述；ledger 未 ready 时，任何英文完成断言、true 状态声明或中文完成态都会阻断发布审查。</p></div>
+    </section>
+
     <section id="registry" class="twocol">
       <div class="panel"><h2>注册审计</h2><p>{html.escape(gate_details.get('registry-audit', 'registry audit missing'))}</p></div>
       <div class="panel"><h2>包体元数据</h2>{registry_panel}</div>
diff --git a/scripts/render_world_class_claim_guard.py b/scripts/render_world_class_claim_guard.py
new file mode 100644
index 0000000..449d1a9
--- /dev/null
+++ b/scripts/render_world_class_claim_guard.py
@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+import argparse
+import json
+import re
+from datetime import date
+from pathlib import Path
+from typing import Any
+
+from render_world_class_evidence_ledger import build_ledger
+
+
+ROOT = Path(__file__).resolve().parent.parent
+SCRIPT_INTERFACE = "cli"
+SCRIPT_INTERFACE_REASON = "Scans public claim surfaces so world-class completion is not claimed before accepted evidence exists."
+
+FORBIDDEN_WHEN_PENDING = [
+    {
+        "key": "ready-to-claim-true",
+        "pattern": re.compile(r"ready[\s_-]*to[\s_-]*claim[\s_-]*world[\s_-]*class\s*[:=]\s*`?true`?", re.IGNORECASE),
+        "reason": "ready_to_claim_world_class cannot be true while ledger evidence is pending.",
+    },
+    {
+        "key": "world-class-ready-true",
+        "pattern": re.compile(r"(public\s+)?world[\s_-]*class[\s_-]*ready\s*[:=]\s*`?true`?", re.IGNORECASE),
+        "reason": "world-class readiness cannot be claimed before accepted external and human evidence exists.",
+    },
+    {
+        "key": "json-world-class-ready-true",
+        "pattern": re.compile(r'"(?:ready_to_claim_world_class|world_class_ready|public_world_class_ready)"\s*:\s*true', re.IGNORECASE),
+        "reason": "machine-readable claim fields must remain false until the ledger is ready.",
+    },
+    {
+        "key": "completion-phrase",
+        "pattern": re.compile(r"(public\s+)?world[\s_-]*class\s+(?:complete|completed|achieved|certified)", re.IGNORECASE),
+        "reason": "completion language is blocked until the world-class ledger is accepted.",
+    },
+    {
+        "key": "zh-completion-phrase",
+        "pattern": re.compile(r"世界级(?:已完成|完成|已达成|达成|准备就绪|可声明|认证通过)"),
+        "reason": "中文完成态表述必须等到 ledger ready 后才能出现。",
+    },
+]
+
+
+def load_json(path: Path) -> dict[str, Any]:
+    if not path.exists():
+        return {}
+    try:
+        payload = json.loads(path.read_text(encoding="utf-8"))
+    except json.JSONDecodeError:
+        return {}
+    return payload if isinstance(payload, dict) else {}
+
+
+def rel_path(path: Path, root: Path) -> str:
+    try:
+        return str(path.resolve().relative_to(root.resolve()))
+    except ValueError:
+        return str(path.resolve())
+
+
+def resolve_claim_surface(raw_path: str, skill_dir: Path) -> Path:
+    path = Path(raw_path)
+    if not path.is_absolute():
+        path = skill_dir / path
+    return path.resolve()
+
+
+def default_claim_surfaces(skill_dir: Path) -> list[Path]:
+    paths: list[Path] = []
+    for rel in ["README.md", "SKILL.md"]:
+        path = skill_dir / rel
+        if path.exists():
+            paths.append(path)
+    for directory, patterns in [
+        (skill_dir / "docs", ["*.md"]),
+        (skill_dir / "reports", ["*.md", "*.html"]),
+    ]:
+        if not directory.exists():
+            continue
+        for pattern in patterns:
+            paths.extend(
+                path
+                for path in directory.rglob(pattern)
+                if path.is_file()
+                and "release_snapshots" not in path.parts
+                and path.name not in {"world_class_claim_guard.md", "world_class_claim_guard.html"}
+            )
+    return sorted(set(paths), key=lambda item: rel_path(item, skill_dir))
+
+
+def line_matches(path: Path, ledger_ready: bool) -> list[dict[str, Any]]:
+    if ledger_ready:
+        return []
+    violations: list[dict[str, Any]] = []
+    try:
+        lines = path.read_text(encoding="utf-8", errors="replace").splitlines()
+    except OSError:
+        return violations
+    for lineno, line in enumerate(lines, start=1):
+        for rule in FORBIDDEN_WHEN_PENDING:
+            if rule["pattern"].search(line):
+                violations.append(
+                    {
+                        "line": lineno,
+                        "rule": rule["key"],
+                        "reason": rule["reason"],
+                        "excerpt": line.strip()[:240],
+                    }
+                )
+    return violations
+
+
+def build_guard(skill_dir: Path, generated_at: str, claim_surfaces: list[Path] | None = None) -> dict[str, Any]:
+    ledger = build_ledger(skill_dir, generated_at)
+    ledger_ready = ledger.get("summary", {}).get("ready_to_claim_world_class") is True
+    surfaces = claim_surfaces or default_claim_surfaces(skill_dir)
+    scanned = []
+    violations = []
+    for path in surfaces:
+        matches = line_matches(path, ledger_ready)
+        rel = rel_path(path, skill_dir)
+        scanned.append({"path": rel, "violation_count": len(matches)})
+        for match in matches:
+            violations.append({"path": rel, **match})
+    ok = len(violations) == 0
+    return {
+        "schema_version": "1.0",
+        "ok": ok,
+        "generated_at": generated_at,
+        "skill_dir": rel_path(skill_dir, ROOT),
+        "summary": {
+            "ledger_ready_to_claim_world_class": ledger_ready,
+            "ledger_pending_count": ledger.get("summary", {}).get("pending_count", 0),
+            "claim_surface_count": len(scanned),
+            "violation_count": len(violations),
+            "overclaim_guard_active": True,
+            "decision": (
+                "claim-ready"
+                if ledger_ready and ok
+                else ("claim-blocked-overclaim" if violations else "claim-guard-pass-evidence-pending")
+            ),
+        },
+        "rules": [
+            {"key": item["key"], "reason": item["reason"], "pattern": item["pattern"].pattern}
+            for item in FORBIDDEN_WHEN_PENDING
+        ],
+        "scanned_surfaces": scanned,
+        "violations": violations,
+        "source_ledger": {
+            "json": "reports/world_class_evidence_ledger.json",
+            "markdown": "reports/world_class_evidence_ledger.md",
+        },
+        "artifacts": {
+            "json": "reports/world_class_claim_guard.json",
+            "markdown": "reports/world_class_claim_guard.md",
+        },
+    }
+
+
+def render_markdown(report: dict[str, Any]) -> str:
+    summary = report["summary"]
+    lines = [
+        "# World-Class Claim Guard",
+        "",
+        f"Generated at: `{report['generated_at']}`",
+        "",
+        "## Summary",
+        "",
+        f"- decision: `{summary['decision']}`",
+        f"- ledger ready to claim world-class: `{str(summary['ledger_ready_to_claim_world_class']).lower()}`",
+        f"- ledger pending evidence: `{summary['ledger_pending_count']}`",
+        f"- claim surfaces scanned: `{summary['claim_surface_count']}`",
+        f"- violations: `{summary['violation_count']}`",
+        f"- overclaim guard active: `{str(summary['overclaim_guard_active']).lower()}`",
+        "",
+        "This guard scans public claim surfaces for completion language that would contradict the world-class evidence ledger. It allows evidence planning and pending-state language, but blocks completion claims until the ledger is ready.",
+        "",
+        "## Violations",
+        "",
+        "| Path | Line | Rule | Excerpt |",
+        "| --- | ---: | --- | --- |",
+    ]
+    if report["violations"]:
+        for item in report["violations"]:
+            excerpt = str(item["excerpt"]).replace("|", "\\|")
+            lines.append(f"| `{item['path']}` | {item['line']} | `{item['rule']}` | {excerpt} |")
+    else:
+        lines.append("| `none` | 0 | `none` | none |")
+    lines.extend(
+        [
+            "",
+            "## Rules",
+            "",
+            "| Rule | Reason |",
+            "| --- | --- |",
+        ]
+    )
+    for rule in report["rules"]:
+        lines.append(f"| `{rule['key']}` | {rule['reason'].replace('|', '\\|')} |")
+    return "\n".join(lines).rstrip() + "\n"
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Guard public world-class completion claims against the evidence ledger.")
+    parser.add_argument("skill_dir", nargs="?", default=".")
+    parser.add_argument("--claim-surface", action="append", default=[])
+    parser.add_argument("--output-json", default="reports/world_class_claim_guard.json")
+    parser.add_argument("--output-md", default="reports/world_class_claim_guard.md")
+    parser.add_argument("--generated-at", default=date.today().isoformat())
+    args = parser.parse_args()
+
+    skill_dir = Path(args.skill_dir).resolve()
+    claim_surfaces = [resolve_claim_surface(item, skill_dir) for item in args.claim_surface] if args.claim_surface else None
+    report = build_guard(skill_dir, args.generated_at, claim_surfaces)
+    output_json = Path(args.output_json)
+    output_md = Path(args.output_md)
+    if not output_json.is_absolute():
+        output_json = skill_dir / output_json
+    if not output_md.is_absolute():
+        output_md = skill_dir / output_md
+    output_json.parent.mkdir(parents=True, exist_ok=True)
+    output_md.parent.mkdir(parents=True, exist_ok=True)
+    output_json.write_text(json.dumps(report, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+    output_md.write_text(render_markdown(report), encoding="utf-8")
+    print(json.dumps(report, ensure_ascii=False, indent=2))
+    raise SystemExit(0 if report["ok"] else 2)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/review_studio_formatting.py b/scripts/review_studio_formatting.py
index f6b380b..ae000b0 100644
--- a/scripts/review_studio_formatting.py
+++ b/scripts/review_studio_formatting.py
@@ -23,6 +23,7 @@ LABELS = {
     "baseline_pass_rate": "Baseline",
     "breaking_change_count": "破坏变更",
     "case_count": "案例数",
+    "claim_surface_count": "声明面",
     "command_executed_count": "命令执行",
     "compatibility_pass_count": "兼容通过",
     "covered_gate_count": "覆盖 Gate",
@@ -37,6 +38,8 @@ LABELS = {
     "installer_permission_failure_count": "安装权限失败",
     "invalid_submission_count": "无效提交",
     "item_count": "项目数",
+    "ledger_pending_count": "台账待补",
+    "ledger_ready_to_claim_world_class": "台账可声明",
     "license": "License",
     "local_blueprint_ready": "本地蓝图",
     "metadata_fallback_count": "Metadata fallback",
@@ -82,6 +85,7 @@ LABELS = {
     "variant_run_count": "运行数",
     "valid_submission_count": "有效提交",
     "version": "版本",
+    "violation_count": "违规数",
     "warning_count": "警告数",
     "with_skill_pass_rate": "With Skill",
     "world_class_evidence_pending_count": "待补证据",
diff --git a/scripts/yao.py b/scripts/yao.py
index 00640c1..6f0b24f 100644
--- a/scripts/yao.py
+++ b/scripts/yao.py
@@ -468,6 +468,7 @@ def command_report(args: argparse.Namespace) -> int:
             run_script("render_world_class_evidence_plan.py", [str(ROOT)]),
             run_script("render_world_class_evidence_ledger.py", [str(ROOT)]),
             run_script("render_world_class_evidence_intake.py", [str(ROOT)]),
+            run_script("render_world_class_claim_guard.py", [str(ROOT)]),
             run_script("render_benchmark_reproducibility.py", [str(ROOT)]),
             run_script("render_skill_os2_coverage.py", [str(ROOT)]),
         ]
@@ -499,6 +500,7 @@ def command_report(args: argparse.Namespace) -> int:
             "world_class_evidence_plan": "reports/world_class_evidence_plan.json",
             "world_class_evidence_ledger": "reports/world_class_evidence_ledger.json",
             "world_class_evidence_intake": "reports/world_class_evidence_intake.json",
+            "world_class_claim_guard": "reports/world_class_claim_guard.json",
             "benchmark_reproducibility": "reports/benchmark_reproducibility.json",
             "skill_os2_coverage": "reports/skill_os2_coverage.json",
         },
@@ -615,6 +617,22 @@ def command_world_class_intake(args: argparse.Namespace) -> int:
     return 0 if result["ok"] else 2
 
 
+def command_world_class_claim_guard(args: argparse.Namespace) -> int:
+    skill_dir = str(Path(args.skill_dir).resolve())
+    cmd = [skill_dir]
+    for surface in args.claim_surface:
+        cmd.extend(["--claim-surface", surface])
+    if args.output_json:
+        cmd.extend(["--output-json", args.output_json])
+    if args.output_md:
+        cmd.extend(["--output-md", args.output_md])
+    if args.generated_at:
+        cmd.extend(["--generated-at", args.generated_at])
+    result = run_script("render_world_class_claim_guard.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_benchmark_reproducibility(args: argparse.Namespace) -> int:
     skill_dir = str(Path(args.skill_dir).resolve())
     cmd = [skill_dir]
@@ -1252,6 +1270,7 @@ def command_workspace_flow(args: argparse.Namespace) -> int:
             {"phase": "report-refresh", "result": run_script("render_world_class_evidence_plan.py", [str(ROOT)])},
             {"phase": "report-refresh", "result": run_script("render_world_class_evidence_ledger.py", [str(ROOT)])},
             {"phase": "report-refresh", "result": run_script("render_world_class_evidence_intake.py", [str(ROOT)])},
+            {"phase": "report-refresh", "result": run_script("render_world_class_claim_guard.py", [str(ROOT)])},
             {"phase": "report-refresh", "result": run_script("render_benchmark_reproducibility.py", [str(ROOT)])},
             {"phase": "report-refresh", "result": run_script("render_skill_os2_coverage.py", [str(ROOT)])},
         ]
diff --git a/scripts/yao_cli_parser.py b/scripts/yao_cli_parser.py
index f55c1d1..c316d3b 100644
--- a/scripts/yao_cli_parser.py
+++ b/scripts/yao_cli_parser.py
@@ -183,6 +183,17 @@ def build_parser(command_handlers: dict[str, Callable[[argparse.Namespace], int]
     world_class_intake_cmd.add_argument("--generated-at")
     world_class_intake_cmd.set_defaults(func=_handler(command_handlers, "command_world_class_intake"))
 
+    world_class_claim_guard_cmd = subparsers.add_parser(
+        "world-class-claim-guard",
+        help="Scan public claim surfaces for premature world-class completion claims.",
+    )
+    world_class_claim_guard_cmd.add_argument("skill_dir", nargs="?", default=".")
+    world_class_claim_guard_cmd.add_argument("--claim-surface", action="append", default=[])
+    world_class_claim_guard_cmd.add_argument("--output-json")
+    world_class_claim_guard_cmd.add_argument("--output-md")
+    world_class_claim_guard_cmd.add_argument("--generated-at")
+    world_class_claim_guard_cmd.set_defaults(func=_handler(command_handlers, "command_world_class_claim_guard"))
+
     benchmark_reproducibility_cmd = subparsers.add_parser(
         "benchmark-reproducibility",
         help="Render benchmark methodology, artifact, failure-disclosure, and reproduction-command evidence.",
diff --git a/skill-ir/examples/yao-meta-skill.json b/skill-ir/examples/yao-meta-skill.json
index 07ff745..dd4881e 100644
--- a/skill-ir/examples/yao-meta-skill.json
+++ b/skill-ir/examples/yao-meta-skill.json
@@ -160,6 +160,7 @@
       "scripts/render_social_preview.py",
       "scripts/render_system_model.py",
       "scripts/render_telemetry_hook_recipes.py",
+      "scripts/render_world_class_claim_guard.py",
       "scripts/render_world_class_evidence_intake.py",
       "scripts/render_world_class_evidence_ledger.py",
       "scripts/render_world_class_evidence_plan.py",
@@ -186,8 +187,7 @@
       "scripts/verify_package.py",
       "scripts/yao.py",
       "scripts/yao_cli_config.py",
-      "scripts/yao_cli_parser.py",
-      "scripts/yao_cli_telemetry.py"
+      "scripts/yao_cli_parser.py"
     ],
     "assets": [
       "templates/basic_skill.md.j2",
diff --git a/skill_atlas/catalog.json b/skill_atlas/catalog.json
index 18443ab..2931048 100644
--- a/skill_atlas/catalog.json
+++ b/skill_atlas/catalog.json
@@ -72,6 +72,7 @@
         "scripts/render_social_preview.py",
         "scripts/render_system_model.py",
         "scripts/render_telemetry_hook_recipes.py",
+        "scripts/render_world_class_claim_guard.py",
         "scripts/render_world_class_evidence_intake.py",
         "scripts/render_world_class_evidence_ledger.py",
         "scripts/render_world_class_evidence_plan.py",
diff --git a/tests/verify_benchmark_reproducibility.py b/tests/verify_benchmark_reproducibility.py
index 38f44bf..bc97594 100644
--- a/tests/verify_benchmark_reproducibility.py
+++ b/tests/verify_benchmark_reproducibility.py
@@ -40,6 +40,19 @@ def main() -> None:
         text=True,
         check=True,
     )
+    subprocess.run(
+        [
+            sys.executable,
+            str(ROOT / "scripts" / "render_world_class_claim_guard.py"),
+            str(ROOT),
+            "--generated-at",
+            "2026-06-13",
+        ],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        check=True,
+    )
     output_json = TMP / "benchmark_reproducibility.json"
     output_md = TMP / "benchmark_reproducibility.md"
     proc = subprocess.run(
@@ -82,9 +95,11 @@ def main() -> None:
     assert artifacts["reports/world_class_evidence_plan.json"]["exists"], artifacts
     assert artifacts["reports/world_class_evidence_ledger.json"]["exists"], artifacts
     assert artifacts["reports/world_class_evidence_intake.json"]["exists"], artifacts
+    assert artifacts["reports/world_class_claim_guard.json"]["exists"], artifacts
     assert any(command["command"] == "make ci-test" for command in payload["reproduction_commands"]), payload
     assert any(command["command"] == "python3 scripts/yao.py world-class-ledger ." for command in payload["reproduction_commands"]), payload
     assert any(command["command"] == "python3 scripts/yao.py world-class-intake ." for command in payload["reproduction_commands"]), payload
+    assert any(command["command"] == "python3 scripts/yao.py world-class-claim-guard ." for command in payload["reproduction_commands"]), payload
     assert any("provider-backed" in item for item in payload["limitations"]), payload["limitations"]
     markdown = output_md.read_text(encoding="utf-8")
     assert "Benchmark Reproducibility" in markdown, markdown
diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py
index 8e5e97b..d34d2f0 100644
--- a/tests/verify_review_studio.py
+++ b/tests/verify_review_studio.py
@@ -223,6 +223,7 @@ def main() -> None:
         "render_world_class_evidence_plan.py",
         "render_world_class_evidence_ledger.py",
         "render_world_class_evidence_intake.py",
+        "render_world_class_claim_guard.py",
         "render_skill_os2_coverage.py",
     ]:
         subprocess.run(
@@ -335,6 +336,8 @@ def main() -> None:
         assert full_payload["evidence_paths"]["world_class_evidence_ledger"] == "reports/world_class_evidence_ledger.md", full_payload["evidence_paths"]
     if (ROOT / "reports" / "world_class_evidence_intake.md").exists():
         assert full_payload["evidence_paths"]["world_class_evidence_intake"] == "reports/world_class_evidence_intake.md", full_payload["evidence_paths"]
+    if (ROOT / "reports" / "world_class_claim_guard.md").exists():
+        assert full_payload["evidence_paths"]["world_class_claim_guard"] == "reports/world_class_claim_guard.md", full_payload["evidence_paths"]
     assert full_payload["data"]["output_blind_review"]["summary"]["pair_count"] == 5, full_payload["data"]["output_blind_review"]
     assert full_payload["data"]["output_execution"]["summary"]["command_executed_count"] == 10, full_payload["data"]["output_execution"]
     assert full_payload["data"]["output_execution"]["summary"]["recorded_fixture_count"] == 0, full_payload["data"]["output_execution"]
@@ -355,6 +358,7 @@ def main() -> None:
         "reports/world_class_evidence_ledger.md",
         "reports/world_class_evidence_plan.md",
         "reports/world_class_evidence_intake.md",
+        "reports/world_class_claim_guard.md",
         "evidence/world_class/intake.schema.json",
         "evidence/world_class/templates/provider-holdout.intake.json",
         "evidence/world_class/templates/human-adjudication.intake.json",
@@ -365,6 +369,9 @@ def main() -> None:
     assert full_payload["data"]["world_class_evidence_intake"]["summary"]["decision"] == "awaiting-submissions", full_payload["data"]["world_class_evidence_intake"]
     assert full_payload["data"]["world_class_evidence_intake"]["summary"]["template_pass_count"] == 4, full_payload["data"]["world_class_evidence_intake"]
     assert full_payload["data"]["world_class_evidence_intake"]["summary"]["ready_to_claim_world_class"] is False, full_payload["data"]["world_class_evidence_intake"]
+    assert full_payload["data"]["world_class_claim_guard"]["summary"]["decision"] == "claim-guard-pass-evidence-pending", full_payload["data"]["world_class_claim_guard"]
+    assert full_payload["data"]["world_class_claim_guard"]["summary"]["violation_count"] == 0, full_payload["data"]["world_class_claim_guard"]
+    assert full_payload["data"]["world_class_claim_guard"]["summary"]["ledger_pending_count"] == 4, full_payload["data"]["world_class_claim_guard"]
     if full_payload["data"]["skill_os2_coverage"]:
         assert full_payload["data"]["skill_os2_coverage"]["summary"]["local_blueprint_ready"] is True, full_payload["data"]["skill_os2_coverage"]
         assert full_payload["data"]["skill_os2_coverage"]["summary"]["public_world_class_ready"] is False, full_payload["data"]["skill_os2_coverage"]
@@ -427,8 +434,12 @@ def main() -> None:
     assert "证据台账" in html, html
     assert "证据入口" in html, html
     assert "入口边界" in html, html
+    assert "声明守卫" in html, html
+    assert "声明边界" in html, html
     assert "intake 只校验证据包格式、来源、隐私和反过度声明" in html, html
     assert "reports/world_class_evidence_intake.md" in html, html
+    assert "reports/world_class_claim_guard.md" in html, html
+    assert "英文完成断言、true 状态声明或中文完成态" in html, html
     assert "world-evidence-grid" in html, html
     assert "Provider Holdout" in html, html
     assert "Native Permission Enforcement" in html, html
diff --git a/tests/verify_world_class_claim_guard.py b/tests/verify_world_class_claim_guard.py
new file mode 100644
index 0000000..6b5a5e3
--- /dev/null
+++ b/tests/verify_world_class_claim_guard.py
@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+import json
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parent.parent
+SCRIPT = ROOT / "scripts" / "render_world_class_claim_guard.py"
+TMP = ROOT / "tests" / "tmp_world_class_claim_guard"
+
+
+def run_guard(*extra: str, check: bool = True, cwd: Path = ROOT) -> subprocess.CompletedProcess[str]:
+    return subprocess.run(
+        [
+            sys.executable,
+            str(SCRIPT),
+            str(ROOT),
+            "--generated-at",
+            "2026-06-14",
+            *extra,
+        ],
+        cwd=cwd,
+        capture_output=True,
+        text=True,
+        check=check,
+    )
+
+
+def main() -> None:
+    shutil.rmtree(TMP, ignore_errors=True)
+    TMP.mkdir(parents=True, exist_ok=True)
+    output_json = TMP / "world_class_claim_guard.json"
+    output_md = TMP / "world_class_claim_guard.md"
+    proc = run_guard("--output-json", str(output_json), "--output-md", str(output_md))
+    payload = json.loads(proc.stdout)
+    assert payload["schema_version"] == "1.0", payload
+    assert payload["ok"] is True, payload
+    summary = payload["summary"]
+    assert summary["decision"] == "claim-guard-pass-evidence-pending", summary
+    assert summary["ledger_ready_to_claim_world_class"] is False, summary
+    assert summary["ledger_pending_count"] == 4, summary
+    assert summary["claim_surface_count"] >= 10, summary
+    assert summary["violation_count"] == 0, summary
+    assert summary["overclaim_guard_active"] is True, summary
+    assert any(item["path"] == "README.md" for item in payload["scanned_surfaces"]), payload["scanned_surfaces"]
+    markdown = output_md.read_text(encoding="utf-8")
+    assert "World-Class Claim Guard" in markdown, markdown
+    assert "claim-guard-pass-evidence-pending" in markdown, markdown
+    assert "world-class evidence ledger" in markdown, markdown
+
+    safe_surface = TMP / "safe.md"
+    safe_surface.write_text("ready to claim world-class: `false`\nworld-class evidence is pending.\n", encoding="utf-8")
+    safe_proc = run_guard("--claim-surface", str(safe_surface), check=True)
+    safe_payload = json.loads(safe_proc.stdout)
+    assert safe_payload["summary"]["violation_count"] == 0, safe_payload
+
+    unsafe_surface = TMP / "unsafe.md"
+    unsafe_surface.write_text("ready to claim world-class: `true`\n世界级已完成\n", encoding="utf-8")
+    unsafe_proc = run_guard("--claim-surface", str(unsafe_surface), check=False)
+    assert unsafe_proc.returncode == 2, unsafe_proc.stdout
+    unsafe_payload = json.loads(unsafe_proc.stdout)
+    assert unsafe_payload["ok"] is False, unsafe_payload
+    assert unsafe_payload["summary"]["decision"] == "claim-blocked-overclaim", unsafe_payload
+    assert unsafe_payload["summary"]["violation_count"] == 2, unsafe_payload
+    rules = {item["rule"] for item in unsafe_payload["violations"]}
+    assert {"ready-to-claim-true", "zh-completion-phrase"} <= rules, unsafe_payload["violations"]
+
+    relative_unsafe_surface = TMP / "relative-unsafe.md"
+    relative_unsafe_surface.write_text("world-class completed\n", encoding="utf-8")
+    relative_proc = run_guard(
+        "--claim-surface",
+        relative_unsafe_surface.relative_to(ROOT).as_posix(),
+        check=False,
+        cwd=TMP,
+    )
+    assert relative_proc.returncode == 2, relative_proc.stdout
+    relative_payload = json.loads(relative_proc.stdout)
+    assert relative_payload["summary"]["violation_count"] == 1, relative_payload
+    assert relative_payload["violations"][0]["path"] == "tests/tmp_world_class_claim_guard/relative-unsafe.md", relative_payload
+    print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tests/verify_yao_cli.py b/tests/verify_yao_cli.py
index 6783104..a60d544 100644
--- a/tests/verify_yao_cli.py
+++ b/tests/verify_yao_cli.py
@@ -78,6 +78,7 @@ def main() -> None:
     assert "world-class-evidence" in parser_help, parser_help
     assert "world-class-ledger" in parser_help, parser_help
     assert "world-class-intake" in parser_help, parser_help
+    assert "world-class-claim-guard" in parser_help, parser_help
     assert "benchmark-reproducibility" in parser_help, parser_help
     assert "telemetry-import" in parser_help, parser_help
     assert "telemetry-emit" in parser_help, parser_help
@@ -226,6 +227,21 @@ def main() -> None:
     assert world_class_intake_result["payload"]["summary"]["ready_to_claim_world_class"] is False, world_class_intake_result
     assert world_class_ledger_result["payload"]["summary"]["ready_to_claim_world_class"] is False, world_class_ledger_result
 
+    world_class_claim_guard_result = run(
+        "world-class-claim-guard",
+        str(ROOT),
+        "--output-json",
+        str(tmp_root / "world_class_claim_guard.json"),
+        "--output-md",
+        str(tmp_root / "world_class_claim_guard.md"),
+        "--generated-at",
+        "2026-06-14",
+    )
+    assert world_class_claim_guard_result["ok"], world_class_claim_guard_result
+    assert world_class_claim_guard_result["payload"]["summary"]["decision"] == "claim-guard-pass-evidence-pending", world_class_claim_guard_result
+    assert world_class_claim_guard_result["payload"]["summary"]["violation_count"] == 0, world_class_claim_guard_result
+    assert world_class_claim_guard_result["payload"]["summary"]["ledger_pending_count"] == 4, world_class_claim_guard_result
+
     benchmark_reproducibility_result = run(
         "benchmark-reproducibility",
         str(ROOT),
@@ -650,6 +666,7 @@ def main() -> None:
     assert "world_class_evidence_plan" in report_result["payload"]["artifacts"], report_result
     assert "world_class_evidence_ledger" in report_result["payload"]["artifacts"], report_result
     assert "world_class_evidence_intake" in report_result["payload"]["artifacts"], report_result
+    assert "world_class_claim_guard" in report_result["payload"]["artifacts"], report_result
     assert "benchmark_reproducibility" in report_result["payload"]["artifacts"], report_result
     assert "skill_os2_coverage" in report_result["payload"]["artifacts"], report_result
     report_output_execution = json.loads((ROOT / "reports" / "output_execution_runs.json").read_text(encoding="utf-8"))