frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
00a0a1f0c68117192e31bb084e842c949cbb7db0
yao-meta-skill/reports/evidence_consistency.json
T
YAO 31ce04c655 Split meta skill CLI and review gates 
Merge the beta-ready Yao Meta Skill architecture, report, evidence gate, and release-boundary updates.\n\nRelease boundary: beta/public testing is allowed; formal world-class, fully reviewed, or superiority claims remain blocked until the pending evidence gates are accepted.
2026-06-17 18:43:02 +08:00

3612 lines
148 KiB
JSON
Raw Blame History

{
"schema_version": "1.0",
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"summary": {
"check_count": 39,
"pass_count": 39,
"warn_count": 0,
"fail_count": 0,
"decision": "consistent"
},
"status_counts": {
"pass": 39,
"warn": 0,
"fail": 0
},
"checks": [
{
"key": "required-report-artifacts",
"label": "Required report artifacts are readable",
"status": "pass",
"expected": "all required JSON and Markdown reports exist and parse",
"actual": "all readable",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json",
"reports/skill-interpretation.json",
"reports/adoption_drift_report.json",
"reports/world_class_evidence_ledger.json",
"reports/world_class_evidence_plan.json",
"reports/world_class_evidence_intake.json",
"reports/world_class_evidence_preflight.json",
"reports/world_class_submission_review.json",
"reports/world_class_operator_runbook.json",
"reports/skill_os2_coverage.json",
"reports/review-studio.json",
"reports/package_verification.json",
"reports/install_simulation.json",
"reports/security_trust_report.json",
"reports/context_budget.json",
"reports/world_class_claim_guard.json",
"reports/skill-os-2-review.md"
],
"detail": "The consistency gate can only be trusted when every source JSON report parses and every source Markdown report is readable."
},
{
"key": "release-evidence-flow-covers-first-class-reports",
"label": "Release evidence flow covers first-class reports",
"status": "pass",
"expected": {
"AGENTS.md": true,
"source_refresh_section": true,
"clean_lock_section": true,
"source_refresh_commands": {
"python3 scripts/run_output_execution.py --runner-command '[\"python3\",\"scripts/local_output_eval_runner.py\"]'": true,
"python3 scripts/compile_skill.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/cross_packager.py . --platform openai --platform claude --platform generic --platform vscode --expectations evals/packaging_expectations.json --output-dir dist --zip": true,
"python3 scripts/simulate_install.py . --package-dir dist --install-root dist/install-simulation --output-json reports/install_simulation.json --output-md reports/install_simulation.md --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/trust_check.py . --output-json reports/security_trust_report.json --output-md reports/security_trust_report.md": true,
"python3 scripts/registry_audit.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/verify_package.py . --package-dir dist --expectations evals/packaging_expectations.json --registry-json reports/registry_audit.json --output-json reports/package_verification.json --output-md reports/package_verification.md --require-zip --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/upgrade_check.py . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json --current-package-json reports/registry_audit.json --output-json reports/upgrade_check.json --output-md reports/upgrade_check.md --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_adoption_drift_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_architecture_maintainability.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/python_compat_check.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/probe_runtime_permissions.py . --package-dir dist": true,
"python3 scripts/render_review_waivers.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_annotations.py .": true,
"python3 scripts/build_skill_atlas.py --workspace-root . --output-dir skill_atlas --report-html reports/skill_atlas.html --report-json reports/skill_atlas.json --today \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_plan.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_ledger.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_intake.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_submission_review.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_operator_runbook.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_claim_guard.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_daily_skillops_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_weekly_curator_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_os2_audit.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_os2_coverage.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_context_reports.py --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_benchmark_reproducibility.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_overview.py .": true,
"python3 scripts/render_skill_interpretation.py .": true,
"python3 scripts/render_review_viewer.py .": true,
"python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true,
"python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true
},
"clean_lock_commands": {
"python3 scripts/render_context_reports.py --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_benchmark_reproducibility.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_daily_skillops_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_weekly_curator_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_overview.py .": true,
"python3 scripts/render_skill_interpretation.py .": true,
"python3 scripts/render_review_viewer.py .": true,
"python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true,
"python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true
}
},
"actual": {
"AGENTS.md": true,
"source_refresh_section": true,
"clean_lock_section": true,
"source_refresh_commands": {
"python3 scripts/run_output_execution.py --runner-command '[\"python3\",\"scripts/local_output_eval_runner.py\"]'": true,
"python3 scripts/compile_skill.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/cross_packager.py . --platform openai --platform claude --platform generic --platform vscode --expectations evals/packaging_expectations.json --output-dir dist --zip": true,
"python3 scripts/simulate_install.py . --package-dir dist --install-root dist/install-simulation --output-json reports/install_simulation.json --output-md reports/install_simulation.md --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/trust_check.py . --output-json reports/security_trust_report.json --output-md reports/security_trust_report.md": true,
"python3 scripts/registry_audit.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/verify_package.py . --package-dir dist --expectations evals/packaging_expectations.json --registry-json reports/registry_audit.json --output-json reports/package_verification.json --output-md reports/package_verification.md --require-zip --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/upgrade_check.py . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json --current-package-json reports/registry_audit.json --output-json reports/upgrade_check.json --output-md reports/upgrade_check.md --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_adoption_drift_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_architecture_maintainability.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/python_compat_check.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/probe_runtime_permissions.py . --package-dir dist": true,
"python3 scripts/render_review_waivers.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_annotations.py .": true,
"python3 scripts/build_skill_atlas.py --workspace-root . --output-dir skill_atlas --report-html reports/skill_atlas.html --report-json reports/skill_atlas.json --today \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_plan.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_ledger.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_evidence_intake.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_submission_review.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_operator_runbook.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_world_class_claim_guard.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_daily_skillops_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_weekly_curator_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_os2_audit.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_os2_coverage.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_context_reports.py --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_benchmark_reproducibility.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_overview.py .": true,
"python3 scripts/render_skill_interpretation.py .": true,
"python3 scripts/render_review_viewer.py .": true,
"python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true,
"python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true
},
"clean_lock_commands": {
"python3 scripts/render_context_reports.py --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_benchmark_reproducibility.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_daily_skillops_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_weekly_curator_report.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_skill_overview.py .": true,
"python3 scripts/render_skill_interpretation.py .": true,
"python3 scripts/render_review_viewer.py .": true,
"python3 scripts/render_world_class_preflight.py . --generated-at \"$GENERATED_AT\"": true,
"python3 scripts/render_review_studio.py . --output-html reports/review-studio.html --output-json reports/review-studio.json": true,
"python3 scripts/render_evidence_consistency.py . --generated-at \"$GENERATED_AT\"": true
}
},
"paths": [
"AGENTS.md",
"reports/output_execution_runs.json",
"reports/install_simulation.json",
"reports/security_trust_report.json",
"reports/registry_audit.json",
"reports/package_verification.json",
"reports/upgrade_check.json",
"reports/adoption_drift_report.json",
"reports/architecture_maintainability.json",
"reports/python_compatibility.json",
"reports/runtime_permission_probes.json",
"reports/review_waivers.json",
"reports/review_annotations.json",
"reports/skill_atlas.json",
"reports/skill_os2_audit.json",
"reports/skill_os2_coverage.json",
"reports/context_budget.json",
"reports/context_budget_summary.json",
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json",
"reports/skill-interpretation.json",
"reports/review-viewer.json",
"reports/world_class_evidence_preflight.json",
"reports/skillops/daily",
"reports/skillops/weekly",
"reports/review-studio.json",
"reports/evidence_consistency.json"
],
"detail": "Release refresh and clean-lock instructions must regenerate every first-class report before evidence consistency can be trusted."
},
{
"key": "review-studio-gate-action-mirror",
"label": "Review Studio gates mirror review actions",
"status": "pass",
"expected": {
"non_pass_gate_keys": [
"output-lab",
"review-waivers",
"world-class-evidence"
],
"action_gate_keys": [
"output-lab",
"review-waivers",
"world-class-evidence"
],
"pass_gate_action_ids_empty": true,
"gate_action_mirrors": {
"output-lab": {
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-output-lab",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"review-waivers": {
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-review-waivers",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"world-class-evidence": {
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-world-class-evidence",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
}
}
},
"actual": {
"non_pass_gate_keys": [
"output-lab",
"review-waivers",
"world-class-evidence"
],
"action_gate_keys": [
"output-lab",
"review-waivers",
"world-class-evidence"
],
"pass_gate_action_ids_empty": true,
"gate_action_mirrors": {
"output-lab": {
"review_action_id": "review-action-output-lab",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-output-lab",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"review-waivers": {
"review_action_id": "review-action-review-waivers",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-review-waivers",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
},
"world-class-evidence": {
"review_action_id": "review-action-world-class-evidence",
"review_action_status": "warn",
"title_present": true,
"next_step_present": true,
"reason_present": true,
"source_ref_present": true,
"verification_command_present": true,
"top_level_action_id": "review-action-world-class-evidence",
"top_level_action_status": "warn",
"top_level_title_present": true,
"top_level_next_step_present": true,
"top_level_reason_present": true,
"top_level_source_ref_present": true,
"top_level_verification_command_present": true
}
}
},
"paths": [
"reports/review-studio.json"
],
"detail": "Every non-pass Review Studio gate must have exactly one top-level review action and a gate-local action summary with source refs and a verification command."
},
{
"key": "review-studio-context-budget-mirror",
"label": "Review Studio mirrors context budget governance",
"status": "pass",
"expected": {
"status": "pass",
"detail": "initial load 998/1000; deferred 525864/120000; top deferred scripts 464561; resource governance governed; quality density 140.3",
"evidence": "reports/context_budget.json"
},
"actual": {
"status": "pass",
"detail": "initial load 998/1000; deferred 525864/120000; top deferred scripts 464561; resource governance governed; quality density 140.3",
"evidence": "reports/context_budget.json"
},
"paths": [
"reports/context_budget.json",
"reports/review-studio.json"
],
"detail": "Review Studio must not keep stale context warnings after context reports prove large deferred resources are governed."
},
{
"key": "benchmark-release-lock-self-consistency",
"label": "Benchmark release lock matches source dirty state",
"status": "pass",
"expected": true,
"actual": true,
"paths": [
"reports/benchmark_reproducibility.json"
],
"detail": "The benchmark release lock must be blocked by source changes, while generated evidence artifacts are tracked as generation context."
},
{
"key": "benchmark-clean-worktree-release-lock",
"label": "Clean worktree keeps a clean benchmark release lock",
"status": "pass",
"expected": "checked only when git is available and the current worktree is clean",
"actual": {
"available": true,
"clean": false,
"changed_file_count": 27
},
"paths": [
"reports/benchmark_reproducibility.json"
],
"detail": "Dirty or non-git worktrees cannot prove final release-lock freshness, so this check is advisory until the final clean-lock pass."
},
{
"key": "skill-ir-evidence-path-contract",
"label": "Human-facing reports expose the canonical Skill IR artifact",
"status": "pass",
"expected": {
"overview_source_path": "skill-ir/examples/yao-meta-skill.json",
"interpretation_source_path": "skill-ir/examples/yao-meta-skill.json",
"review_studio_evidence_path": "skill-ir/examples/yao-meta-skill.json",
"overview_deliverable": true,
"interpretation_deliverable": true,
"exists": true,
"schema_version": "2.0.0"
},
"actual": {
"overview_source_path": "skill-ir/examples/yao-meta-skill.json",
"interpretation_source_path": "skill-ir/examples/yao-meta-skill.json",
"review_studio_evidence_path": "skill-ir/examples/yao-meta-skill.json",
"overview_deliverable": true,
"interpretation_deliverable": true,
"exists": true,
"schema_version": "2.0.0"
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json",
"reports/review-studio.json",
"skill-ir/examples/yao-meta-skill.json"
],
"detail": "Skill IR is the 2.0 platform-neutral semantic source, so user-facing reports must link to the artifact that actually exists."
},
{
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
"actual": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
],
"detail": "Human-facing reports must point to the same benchmark release-lock commit."
},
{
"key": "overview-benchmark-summary",
"label": "overview embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"beta_test_ready": true,
"beta_test_blocker_count": 0,
"beta_test_deferred_evidence_count": 4,
"public_claim_ready": false,
"public_claim_blocker_count": 3
},
"actual": {
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"beta_test_ready": true,
"beta_test_blocker_count": 0,
"beta_test_deferred_evidence_count": 4,
"public_claim_ready": false,
"public_claim_blocker_count": 3
},
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "overview-adoption-summary",
"label": "overview embeds adoption drift summary fields",
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
},
"source_types": {
"manual": 1
}
},
"actual": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
},
"source_types": {
"manual": 1
}
},
"paths": [
"reports/adoption_drift_report.json",
"reports/skill-overview.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "overview-world-class-ledger-summary",
"label": "overview embeds world-class ledger summary fields",
"status": "pass",
"expected": {
"ledger_entry_count": 4,
"accepted_count": 0,
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
"actual": {
"ledger_entry_count": 4,
"accepted_count": 0,
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/skill-overview.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "overview-world-class-readiness",
"label": "overview derives readiness from the ledger",
"status": "pass",
"expected": {
"ready": false,
"decision": "evidence-pending",
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 11
},
"actual": {
"ready": false,
"decision": "evidence-pending",
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 11
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/skill-overview.json"
],
"detail": "Readiness summaries must be derived from the evidence ledger, not hand-maintained copy."
},
{
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
"actual": "e79050ed12d057811d7d13ab7d8bcc5a06af76d4",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
],
"detail": "Human-facing reports must point to the same benchmark release-lock commit."
},
{
"key": "interpretation-benchmark-summary",
"label": "interpretation embeds benchmark summary fields",
"status": "pass",
"expected": {
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"beta_test_ready": true,
"beta_test_blocker_count": 0,
"beta_test_deferred_evidence_count": 4,
"public_claim_ready": false,
"public_claim_blocker_count": 3
},
"actual": {
"release_lock_ready": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "5a99ef3133b0148cd5bbc1cd85fad4830bf34ca2bbac709f1e1fea2f810b1257",
"archive_sha256": "7db44f059844b71930ea8194a72ba1a316116ca970620de5550d60616e8f23c2",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"beta_test_ready": true,
"beta_test_blocker_count": 0,
"beta_test_deferred_evidence_count": 4,
"public_claim_ready": false,
"public_claim_blocker_count": 3
},
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "interpretation-adoption-summary",
"label": "interpretation embeds adoption drift summary fields",
"status": "pass",
"expected": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
},
"source_types": {
"manual": 1
}
},
"actual": {
"event_count": 1,
"adoption_sample_count": 0,
"activation_count": 0,
"accepted_count": 0,
"adoption_rate": 0,
"risk_band": "low",
"event_types": {
"review_event": 1
},
"source_types": {
"manual": 1
}
},
"paths": [
"reports/adoption_drift_report.json",
"reports/skill-interpretation.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "interpretation-world-class-ledger-summary",
"label": "interpretation embeds world-class ledger summary fields",
"status": "pass",
"expected": {
"ledger_entry_count": 4,
"accepted_count": 0,
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
"actual": {
"ledger_entry_count": 4,
"accepted_count": 0,
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"decision": "evidence-pending"
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/skill-interpretation.json"
],
"detail": "Selected summary fields must match exactly across generated reports."
},
{
"key": "interpretation-world-class-readiness",
"label": "interpretation derives readiness from the ledger",
"status": "pass",
"expected": {
"ready": false,
"decision": "evidence-pending",
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 11
},
"actual": {
"ready": false,
"decision": "evidence-pending",
"pending_count": 4,
"accepted_count": 0,
"source_check_count": 19,
"source_pass_count": 11
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/skill-interpretation.json"
],
"detail": "Readiness summaries must be derived from the evidence ledger, not hand-maintained copy."
},
{
"key": "overview-interpretation-lockstep-scorecard",
"label": "Overview and interpretation share scorecard",
"status": "pass",
"expected": {
"completeness_score": {
"label": "完整度",
"score": 100,
"reasons": [
"SKILL.md 已存在，是 Skill 的入口。",
"README.md 已存在，便于人工阅读。",
"agents/interface.yaml 已存在，便于跨平台适配。",
"manifest.json 已存在，生命周期信息可追踪。",
"reports/ 已存在，生成证据可以随包体迁移。"
]
},
"trigger_score": {
"label": "触发清晰",
"score": 100,
"reasons": [
"frontmatter description 已存在，具备基础路由面。",
"description 有足够长度说明任务边界。",
"description 已包含使用场景或排除边界信号。",
"evals/ 已存在，可承载触发样例或质量检查。",
"intent-confidence 报告已生成，可辅助判断触发稳定性。"
]
},
"evidence_score": {
"label": "证据充分",
"score": 100,
"reasons": [
"已生成 20 / 20 类报告证据。",
"skill-ir.json 已存在。",
"compiled_targets.json 已存在。",
"intent-dialogue.json 已存在。"
]
},
"maintainability_score": {
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 339 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
"evals/ 已承载可迁移检查。"
]
},
"portability_score": {
"label": "可迁移性",
"score": 100,
"reasons": [
"agents/interface.yaml 已存在。",
"manifest.json 已存在。",
"目标平台或 adapter target 已声明。",
"入口文件未发现明显私有绝对路径。"
]
},
"context_cost": {
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 339 个词/字，references 约 16934 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
}
},
"actual": {
"completeness_score": {
"label": "完整度",
"score": 100,
"reasons": [
"SKILL.md 已存在，是 Skill 的入口。",
"README.md 已存在，便于人工阅读。",
"agents/interface.yaml 已存在，便于跨平台适配。",
"manifest.json 已存在，生命周期信息可追踪。",
"reports/ 已存在，生成证据可以随包体迁移。"
]
},
"trigger_score": {
"label": "触发清晰",
"score": 100,
"reasons": [
"frontmatter description 已存在，具备基础路由面。",
"description 有足够长度说明任务边界。",
"description 已包含使用场景或排除边界信号。",
"evals/ 已存在，可承载触发样例或质量检查。",
"intent-confidence 报告已生成，可辅助判断触发稳定性。"
]
},
"evidence_score": {
"label": "证据充分",
"score": 100,
"reasons": [
"已生成 20 / 20 类报告证据。",
"skill-ir.json 已存在。",
"compiled_targets.json 已存在。",
"intent-dialogue.json 已存在。"
]
},
"maintainability_score": {
"label": "可维护性",
"score": 100,
"reasons": [
"SKILL.md 约 339 个词/字。",
"入口文件保持克制，可维护性较好。",
"references/ 已承载扩展指导。",
"scripts/ 已承载确定性逻辑。",
"evals/ 已承载可迁移检查。"
]
},
"portability_score": {
"label": "可迁移性",
"score": 100,
"reasons": [
"agents/interface.yaml 已存在。",
"manifest.json 已存在。",
"目标平台或 adapter target 已声明。",
"入口文件未发现明显私有绝对路径。"
]
},
"context_cost": {
"label": "上下文成本",
"score": 42,
"reasons": [
"入口约 339 个词/字，references 约 16934 个词/字。",
"分数越高代表上下文成本越低。",
"上下文成本偏高，建议压缩入口或拆分 references。"
]
}
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-capability-profile",
"label": "Overview and interpretation share capability_profile",
"status": "pass",
"expected": {
"archetype": "governed",
"task_family": "Execution operation",
"maturity": "governed",
"trigger_strength": "手动触发 + description 路由",
"reuse_scope": "跨平台",
"matrix": {
"execution_certainty": 72,
"knowledge_density": 80
}
},
"actual": {
"archetype": "governed",
"task_family": "Execution operation",
"maturity": "governed",
"trigger_strength": "手动触发 + description 路由",
"reuse_scope": "跨平台",
"matrix": {
"execution_certainty": 72,
"knowledge_density": 80
}
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-principle-model",
"label": "Overview and interpretation share principle_model",
"status": "pass",
"expected": {
"nodes": [
{
"title": "意图澄清",
"body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
},
{
"title": "边界路由",
"body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
},
{
"title": "资产分层",
"body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
},
{
"title": "证据回路",
"body": "Ask only the highest-leverage clarification before adding package weight."
},
{
"title": "漂移观察",
"body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
},
{
"title": "杠杆升级",
"body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
}
],
"layers": [
"入口层",
"参考层",
"脚本层",
"评估层",
"报告层"
]
},
"actual": {
"nodes": [
{
"title": "意图澄清",
"body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
},
{
"title": "边界路由",
"body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
},
{
"title": "资产分层",
"body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
},
{
"title": "证据回路",
"body": "Ask only the highest-leverage clarification before adding package weight."
},
{
"title": "漂移观察",
"body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
},
{
"title": "杠杆升级",
"body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
}
],
"layers": [
"入口层",
"参考层",
"脚本层",
"评估层",
"报告层"
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-contract-boundary",
"label": "Overview and interpretation share contract_boundary",
"status": "pass",
"expected": {
"trigger": {
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
"activation": "manual",
"execution": "inline",
"shell": "bash"
},
"inputs": [
"rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
"an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
"target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
"benchmark references, local constraints, desired maturity tier, and review standards"
],
"outputs": [
"A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
"结构化 Skill 目录，共 8 类关键资产。"
],
"should_trigger": [
"把重复流程沉淀为可复用的 agent skill。",
"把分散提示词、对话记录或操作规范整理为稳定能力。",
"团队复用前，需要明确触发边界、质量证据和维护责任。"
],
"should_not_trigger": [
"只需要一次性回答、没有复用价值的临时请求。",
"要求直接执行相邻任务，而不是沉淀或使用这个 Skill。",
"缺少必要事实且用户不允许澄清的场景。"
],
"boundary_cards": [
{
"label": "Owned",
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
},
{
"label": "Adjacent",
"body": "相邻任务需要先确认是否应转为独立 Skill。"
},
{
"label": "Excluded",
"body": "不替代人工事实核查，也不静默扩大职责。"
}
]
},
"actual": {
"trigger": {
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
"activation": "manual",
"execution": "inline",
"shell": "bash"
},
"inputs": [
"rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
"an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
"target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
"benchmark references, local constraints, desired maturity tier, and review standards"
],
"outputs": [
"A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
"结构化 Skill 目录，共 8 类关键资产。"
],
"should_trigger": [
"把重复流程沉淀为可复用的 agent skill。",
"把分散提示词、对话记录或操作规范整理为稳定能力。",
"团队复用前，需要明确触发边界、质量证据和维护责任。"
],
"should_not_trigger": [
"只需要一次性回答、没有复用价值的临时请求。",
"要求直接执行相邻任务，而不是沉淀或使用这个 Skill。",
"缺少必要事实且用户不允许澄清的场景。"
],
"boundary_cards": [
{
"label": "Owned",
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution."
},
{
"label": "Adjacent",
"body": "相邻任务需要先确认是否应转为独立 Skill。"
},
{
"label": "Excluded",
"body": "不替代人工事实核查，也不静默扩大职责。"
}
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-quality-review",
"label": "Overview and interpretation share quality_review",
"status": "pass",
"expected": {
"strengths": [
"触发面保持精简，并锚定在 frontmatter description。",
"已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
"已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
"已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
"已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
"只把重复且稳定的步骤沉淀为脚本。",
"每次升级后重新生成报告并检查分数原因。"
],
"artifact_design": {
"design_system": "metric editorial",
"highlights": [
"Metric-first dashboard with stable dimensions, short labels, visible deltas, and narrative callouts only where they change interpretation.",
"Avoid paragraph-heavy table cells.",
"Keep charts tied to one analytical question each.",
"Preserve stable color meaning across metrics and entities."
]
},
"prompt_quality": {
"overall_quality_score": 89.0,
"highlights": [
"Primary prompt task family: Execution operation.",
"Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
"Completeness: 100/100.",
"Clarity: 85/100."
]
},
"system_model": {
"stability": {
"score": 100,
"band": "system-ready"
},
"highlights": [
"Stability: system-ready (100/100).",
"Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
"Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
"Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
]
}
},
"actual": {
"strengths": [
"触发面保持精简，并锚定在 frontmatter description。",
"已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
"已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
"已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
"已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
],
"gaps": [
"上下文成本需要补强：入口约 339 个词/字，references 约 16934 个词/字。"
],
"recommendations": [
"先改触发边界，再扩展工作流。",
"只把重复且稳定的步骤沉淀为脚本。",
"每次升级后重新生成报告并检查分数原因。"
],
"artifact_design": {
"design_system": "metric editorial",
"highlights": [
"Metric-first dashboard with stable dimensions, short labels, visible deltas, and narrative callouts only where they change interpretation.",
"Avoid paragraph-heavy table cells.",
"Keep charts tied to one analytical question each.",
"Preserve stable color meaning across metrics and entities."
]
},
"prompt_quality": {
"overall_quality_score": 89.0,
"highlights": [
"Primary prompt task family: Execution operation.",
"Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
"Completeness: 100/100.",
"Clarity: 85/100."
]
},
"system_model": {
"stability": {
"score": 100,
"band": "system-ready"
},
"highlights": [
"Stability: system-ready (100/100).",
"Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
"Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
"Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
]
}
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-risk-governance",
"label": "Overview and interpretation share risk_governance",
"status": "pass",
"expected": {
"risks": [
{
"name": "误触发风险",
"impact": 3,
"probability": 1,
"signal": "frontmatter description 已存在，具备基础路由面。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "输出漂移风险",
"impact": 2,
"probability": 1,
"signal": "已生成 20 / 20 类报告证据。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "证据不足风险",
"impact": 3,
"probability": 1,
"signal": "已生成 20 / 20 类报告证据。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 339 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "跨平台迁移风险",
"impact": 3,
"probability": 1,
"signal": "agents/interface.yaml 已存在。",
"response": "先补证据和边界，再增加包体复杂度。"
}
],
"risk_families": [
{
"key": "markdown_readability",
"label": "Markdown readability",
"matched_keywords": [
"md",
"report",
"doc"
],
"score": 3,
"risks": [
"Tables can render as dense grids with weak hierarchy or poor mobile readability.",
"Long bullets can make the output look complete while hiding the actual decision logic.",
"Mixed heading levels can reduce scanability."
],
"constraints": [
"Use tables only when comparison is the main job; otherwise prefer compact cards or grouped bullets.",
"Keep table cells short and move explanations below the table.",
"Use heading levels consistently and keep each section anchored to a user-facing outcome."
],
"self_repair": [
"Preview whether each table still reads well when columns are narrow.",
"Convert any table with paragraph-length cells into bullets or cards."
]
},
{
"key": "citation_clutter",
"label": "Citation and footnote clutter",
"matched_keywords": [
"source",
"reference"
],
"score": 2,
"risks": [
"Footnote markers or dense citation notes can interrupt the reading flow.",
"Evidence can be over-attached to obvious statements and under-attached to risky claims.",
"Source notes may become more prominent than the tutorial itself."
],
"constraints": [
"Attach citations only to claims that need evidence, not to every sentence.",
"Group source notes at the end of a section when inline markers would hurt readability.",
"Keep the main sentence readable without requiring the reader to chase a footnote."
],
"self_repair": [
"Remove decorative citations that do not support a material claim.",
"Move repeated source explanations into one compact source note."
]
},
{
"key": "visual_capture",
"label": "Screenshot and visual capture",
"matched_keywords": [
"capture"
],
"score": 1,
"risks": [
"Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
"Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
"Image descriptions can omit the action-relevant region."
],
"constraints": [
"Never invent a screenshot; state when visual evidence is missing.",
"Record the source, viewport, and crop intent for any screenshot-dependent output.",
"Describe what the reader should inspect in the image, not just that an image exists."
],
"self_repair": [
"Check that every screenshot reference points to a real provided or generated asset.",
"Reword any visual instruction that depends on an unseen screen state."
]
},
{
"key": "code_or_command_safety",
"label": "Code and command safety",
"matched_keywords": [
"script"
],
"score": 1,
"risks": [
"Commands can omit environment assumptions, working directory, or rollback notes.",
"Code snippets can look runnable while missing required inputs.",
"Error handling can be either absent or over-engineered."
],
"constraints": [
"Name the working directory, required inputs, and expected output for each command.",
"Mark destructive or external side-effect operations explicitly.",
"Prefer the smallest runnable snippet over broad framework code."
],
"self_repair": [
"Scan each command for cwd, input, output, and side-effect assumptions.",
"Remove speculative error handling that is not tied to a real failure mode."
]
},
{
"key": "tone_and_specificity",
"label": "Tone and specificity",
"matched_keywords": [
"summary"
],
"score": 1,
"risks": [
"Headings and summaries can drift into generic, interchangeable language.",
"The output can sound polished but lose the user's actual taste, audience, or scenario.",
"Strong claims can appear without examples or constraints."
],
"constraints": [
"Anchor titles and summaries in the user's audience, object, and concrete outcome.",
"Avoid placeholder phrases such as comprehensive guide, ultimate solution, or key insights unless the source demands them.",
"Preserve one distinctive phrase, constraint, or standard from the user's input."
],
"self_repair": [
"Replace generic title candidates with scenario-specific alternatives.",
"Delete any polished sentence that could fit almost any project unchanged."
]
}
],
"human_judgment_boundary": [
"Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
"Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
"Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
]
},
"actual": {
"risks": [
{
"name": "误触发风险",
"impact": 3,
"probability": 1,
"signal": "frontmatter description 已存在，具备基础路由面。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "输出漂移风险",
"impact": 2,
"probability": 1,
"signal": "已生成 20 / 20 类报告证据。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "证据不足风险",
"impact": 3,
"probability": 1,
"signal": "已生成 20 / 20 类报告证据。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "包体膨胀风险",
"impact": 2,
"probability": 1,
"signal": "SKILL.md 约 339 个词/字。",
"response": "先补证据和边界，再增加包体复杂度。"
},
{
"name": "跨平台迁移风险",
"impact": 3,
"probability": 1,
"signal": "agents/interface.yaml 已存在。",
"response": "先补证据和边界，再增加包体复杂度。"
}
],
"risk_families": [
{
"key": "markdown_readability",
"label": "Markdown readability",
"matched_keywords": [
"md",
"report",
"doc"
],
"score": 3,
"risks": [
"Tables can render as dense grids with weak hierarchy or poor mobile readability.",
"Long bullets can make the output look complete while hiding the actual decision logic.",
"Mixed heading levels can reduce scanability."
],
"constraints": [
"Use tables only when comparison is the main job; otherwise prefer compact cards or grouped bullets.",
"Keep table cells short and move explanations below the table.",
"Use heading levels consistently and keep each section anchored to a user-facing outcome."
],
"self_repair": [
"Preview whether each table still reads well when columns are narrow.",
"Convert any table with paragraph-length cells into bullets or cards."
]
},
{
"key": "citation_clutter",
"label": "Citation and footnote clutter",
"matched_keywords": [
"source",
"reference"
],
"score": 2,
"risks": [
"Footnote markers or dense citation notes can interrupt the reading flow.",
"Evidence can be over-attached to obvious statements and under-attached to risky claims.",
"Source notes may become more prominent than the tutorial itself."
],
"constraints": [
"Attach citations only to claims that need evidence, not to every sentence.",
"Group source notes at the end of a section when inline markers would hurt readability.",
"Keep the main sentence readable without requiring the reader to chase a footnote."
],
"self_repair": [
"Remove decorative citations that do not support a material claim.",
"Move repeated source explanations into one compact source note."
]
},
{
"key": "visual_capture",
"label": "Screenshot and visual capture",
"matched_keywords": [
"capture"
],
"score": 1,
"risks": [
"Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
"Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
"Image descriptions can omit the action-relevant region."
],
"constraints": [
"Never invent a screenshot; state when visual evidence is missing.",
"Record the source, viewport, and crop intent for any screenshot-dependent output.",
"Describe what the reader should inspect in the image, not just that an image exists."
],
"self_repair": [
"Check that every screenshot reference points to a real provided or generated asset.",
"Reword any visual instruction that depends on an unseen screen state."
]
},
{
"key": "code_or_command_safety",
"label": "Code and command safety",
"matched_keywords": [
"script"
],
"score": 1,
"risks": [
"Commands can omit environment assumptions, working directory, or rollback notes.",
"Code snippets can look runnable while missing required inputs.",
"Error handling can be either absent or over-engineered."
],
"constraints": [
"Name the working directory, required inputs, and expected output for each command.",
"Mark destructive or external side-effect operations explicitly.",
"Prefer the smallest runnable snippet over broad framework code."
],
"self_repair": [
"Scan each command for cwd, input, output, and side-effect assumptions.",
"Remove speculative error handling that is not tied to a real failure mode."
]
},
{
"key": "tone_and_specificity",
"label": "Tone and specificity",
"matched_keywords": [
"summary"
],
"score": 1,
"risks": [
"Headings and summaries can drift into generic, interchangeable language.",
"The output can sound polished but lose the user's actual taste, audience, or scenario.",
"Strong claims can appear without examples or constraints."
],
"constraints": [
"Anchor titles and summaries in the user's audience, object, and concrete outcome.",
"Avoid placeholder phrases such as comprehensive guide, ultimate solution, or key insights unless the source demands them.",
"Preserve one distinctive phrase, constraint, or standard from the user's input."
],
"self_repair": [
"Replace generic title candidates with scenario-specific alternatives.",
"Delete any polished sentence that could fit almost any project unchanged."
]
}
],
"human_judgment_boundary": [
"Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
"Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
"Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-world-class-readiness",
"label": "Overview and interpretation share world_class_readiness",
"status": "pass",
"expected": {
"ready": false,
"decision": "evidence-pending",
"entry_count": 4,
"pending_count": 4,
"accepted_count": 0,
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 11,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
{
"key": "provider-holdout",
"label_zh": "提供商留出",
"label_en": "Provider Holdout",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "缺少真实 provider 模型运行和 token metadata。",
"summary_en": "Missing a real provider model run and token metadata.",
"blocked_checks": []
},
{
"key": "human-adjudication",
"label_zh": "人工盲评",
"label_en": "Human Adjudication",
"category": "human",
"category_zh": "人工证据",
"category_en": "Human evidence",
"status": "pending",
"summary_zh": "盲评 pair 仍待真实 reviewer 决策。",
"summary_en": "Blind-review pairs still need real reviewer decisions.",
"blocked_checks": [
"No pending decisions",
"Judgments complete",
"Reviewer metadata"
]
},
{
"key": "native-permission-enforcement",
"label_zh": "原生权限",
"label_en": "Native Permission",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "原生 runtime enforcement 仍待目标客户端或外部安装器证明。",
"summary_en": "Native runtime enforcement still needs target-client or external-installer proof.",
"blocked_checks": [
"Native enforcement"
]
},
{
"key": "native-client-telemetry",
"label_zh": "原生遥测",
"label_en": "Native Telemetry",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
]
}
]
},
"actual": {
"ready": false,
"decision": "evidence-pending",
"entry_count": 4,
"pending_count": 4,
"accepted_count": 0,
"external_pending_count": 3,
"human_pending_count": 1,
"source_check_count": 19,
"source_pass_count": 11,
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
"entries": [
{
"key": "provider-holdout",
"label_zh": "提供商留出",
"label_en": "Provider Holdout",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "缺少真实 provider 模型运行和 token metadata。",
"summary_en": "Missing a real provider model run and token metadata.",
"blocked_checks": []
},
{
"key": "human-adjudication",
"label_zh": "人工盲评",
"label_en": "Human Adjudication",
"category": "human",
"category_zh": "人工证据",
"category_en": "Human evidence",
"status": "pending",
"summary_zh": "盲评 pair 仍待真实 reviewer 决策。",
"summary_en": "Blind-review pairs still need real reviewer decisions.",
"blocked_checks": [
"No pending decisions",
"Judgments complete",
"Reviewer metadata"
]
},
{
"key": "native-permission-enforcement",
"label_zh": "原生权限",
"label_en": "Native Permission",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "原生 runtime enforcement 仍待目标客户端或外部安装器证明。",
"summary_en": "Native runtime enforcement still needs target-client or external-installer proof.",
"blocked_checks": [
"Native enforcement"
]
},
{
"key": "native-client-telemetry",
"label_zh": "原生遥测",
"label_en": "Native Telemetry",
"category": "external",
"category_zh": "外部证据",
"category_en": "External evidence",
"status": "pending",
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
"summary_en": "Real external-client metadata-only events have not been imported yet.",
"blocked_checks": [
"External events",
"Adoption sample"
]
}
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-package-assets",
"label": "Overview and interpretation share package_assets",
"status": "pass",
"expected": {
"entries": [
{
"path": "SKILL.md",
"label": "Skill entrypoint",
"kind": "file",
"file_count": 1
},
{
"path": "README.md",
"label": "Human-readable usage guide",
"kind": "file",
"file_count": 1
},
{
"path": "agents/interface.yaml",
"label": "Neutral interface metadata",
"kind": "file",
"file_count": 1
},
{
"path": "manifest.json",
"label": "Lifecycle and portability metadata",
"kind": "file",
"file_count": 1
},
{
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 153
},
{
"path": "evals",
"label": "Trigger and quality checks",
"kind": "folder",
"file_count": 29
},
{
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 235
}
],
"file_count": 456,
"folder_count": 4,
"distribution": [
{
"label": "SKILL.md",
"value": 1
},
{
"label": "README.md",
"value": 1
},
{
"label": "agents/interface.yaml",
"value": 1
},
{
"label": "manifest.json",
"value": 1
},
{
"label": "references",
"value": 35
},
{
"label": "scripts",
"value": 153
},
{
"label": "evals",
"value": 29
},
{
"label": "reports",
"value": 235
}
]
},
"actual": {
"entries": [
{
"path": "SKILL.md",
"label": "Skill entrypoint",
"kind": "file",
"file_count": 1
},
{
"path": "README.md",
"label": "Human-readable usage guide",
"kind": "file",
"file_count": 1
},
{
"path": "agents/interface.yaml",
"label": "Neutral interface metadata",
"kind": "file",
"file_count": 1
},
{
"path": "manifest.json",
"label": "Lifecycle and portability metadata",
"kind": "file",
"file_count": 1
},
{
"path": "references",
"label": "Extended guidance and reusable notes",
"kind": "folder",
"file_count": 35
},
{
"path": "scripts",
"label": "Deterministic helpers or local tooling",
"kind": "folder",
"file_count": 153
},
{
"path": "evals",
"label": "Trigger and quality checks",
"kind": "folder",
"file_count": 29
},
{
"path": "reports",
"label": "Generated evidence and overview artifacts",
"kind": "folder",
"file_count": 235
}
],
"file_count": 456,
"folder_count": 4,
"distribution": [
{
"label": "SKILL.md",
"value": 1
},
{
"label": "README.md",
"value": 1
},
{
"label": "agents/interface.yaml",
"value": 1
},
{
"label": "manifest.json",
"value": 1
},
{
"label": "references",
"value": 35
},
{
"label": "scripts",
"value": 153
},
{
"label": "evals",
"value": 29
},
{
"label": "reports",
"value": 235
}
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-interpretation-lockstep-iteration-roadmap",
"label": "Overview and interpretation share iteration_roadmap",
"status": "pass",
"expected": {
"items": [
{
"title": "补齐世界证据",
"why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
"actions": [
"补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
"补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
"按 ledger 总量继续补齐 4 项待补证据（外部 3 项、人工 1 项；未展开 2 项），并保持 claim guard 为 pending 状态。"
],
"unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
"source": "world_class_evidence_ledger"
},
{
"title": "Borrow one proven pattern on purpose",
"why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
"actions": [
"Read the strongest pattern from obra/superpowers.",
"Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
"Record what you will not borrow so the package stays light."
],
"unlocks": "A cleaner package shape with less accidental over-design."
},
{
"title": "Harden portability semantics",
"why": "The skill already signals reuse across environments, so contract clarity matters early.",
"actions": [
"Confirm activation mode, execution context, and trust assumptions.",
"Add or review degradation strategy for non-native targets.",
"Package the skill once to verify adapter expectations."
],
"unlocks": "Safer cross-environment reuse with less target drift."
}
]
},
"actual": {
"items": [
{
"title": "补齐世界证据",
"why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
"actions": [
"补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
"补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
"按 ledger 总量继续补齐 4 项待补证据（外部 3 项、人工 1 项；未展开 2 项），并保持 claim guard 为 pending 状态。"
],
"unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
"source": "world_class_evidence_ledger"
},
{
"title": "Borrow one proven pattern on purpose",
"why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
"actions": [
"Read the strongest pattern from obra/superpowers.",
"Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
"Record what you will not borrow so the package stays light."
],
"unlocks": "A cleaner package shape with less accidental over-design."
},
{
"title": "Harden portability semantics",
"why": "The skill already signals reuse across environments, so contract clarity matters early.",
"actions": [
"Confirm activation mode, execution context, and trust assumptions.",
"Add or review degradation strategy for non-native targets.",
"Package the skill once to verify adapter expectations."
],
"unlocks": "Safer cross-environment reuse with less target drift."
}
]
},
"paths": [
"reports/skill-overview.json",
"reports/skill-interpretation.json"
],
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
},
{
"key": "overview-html-contract",
"label": "overview has a stable HTML contract",
"status": "pass",
"expected": {
"schema_version": "2.0",
"default_language": "zh-CN",
"layout": "kami-white-audit-v2",
"html_report": "reports/skill-overview.html",
"html_exists": true
},
"actual": {
"schema_version": "2.0",
"default_language": "zh-CN",
"layout": "kami-white-audit-v2",
"html_report": "reports/skill-overview.html",
"html_exists": true
},
"paths": [
"reports/skill-overview.json",
"reports/skill-overview.html"
],
"detail": "Report output paths and language defaults are part of the user-facing contract."
},
{
"key": "interpretation-html-contract",
"label": "interpretation has a stable HTML contract",
"status": "pass",
"expected": {
"schema_version": "2.0",
"default_language": "zh-CN",
"layout": "kami-white-audit-v2",
"html_report": "reports/skill-interpretation.html",
"html_exists": true
},
"actual": {
"schema_version": "2.0",
"default_language": "zh-CN",
"layout": "kami-white-audit-v2",
"html_report": "reports/skill-interpretation.html",
"html_exists": true
},
"paths": [
"reports/skill-interpretation.json",
"reports/skill-interpretation.html"
],
"detail": "Report output paths and language defaults are part of the user-facing contract."
},
{
"key": "coverage-world-class-boundary",
"label": "Coverage report mirrors world-class evidence boundary",
"status": "pass",
"expected": {
"world_class_evidence_pending_count": 4,
"public_world_class_ready": false
},
"actual": {
"world_class_evidence_pending_count": 4,
"public_world_class_ready": false
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/skill_os2_coverage.json"
],
"detail": "Blueprint coverage can be locally complete while public world-class evidence remains pending."
},
{
"key": "benchmark-world-class-boundary",
"label": "Benchmark report mirrors world-class evidence boundary",
"status": "pass",
"expected": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"public_claim_ready": false
},
"actual": {
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 19,
"world_class_source_pass_count": 11,
"world_class_source_blocked_count": 8,
"public_claim_ready": false
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/benchmark_reproducibility.json"
],
"detail": "Benchmark reproducibility must not overstate public claim readiness."
},
{
"key": "benchmark-beta-public-claim-split",
"label": "Benchmark separates beta testing from public claims",
"status": "pass",
"expected": {
"beta_test_ready": true,
"public_claim_ready": false,
"human_review_complete": false,
"beta_release_ready": true,
"beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
"deferred_evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"deferred_human_review": true
},
"actual": {
"beta_test_ready": true,
"public_claim_ready": false,
"human_review_complete": false,
"beta_release_ready": true,
"beta_release_scope": "beta/public test release without superiority, fully-reviewed, or world-class claims",
"deferred_evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"deferred_human_review": true
},
"paths": [
"reports/benchmark_reproducibility.json",
"reports/world_class_evidence_ledger.json"
],
"detail": "Beta/public testing may proceed with human blind review deferred, but public world-class or superiority claims must remain blocked."
},
{
"key": "preflight-world-class-boundary",
"label": "Preflight mirrors ledger without accepting evidence",
"status": "pass",
"expected": {
"pending_count": 4,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
},
"actual": {
"pending_count": 4,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"ready_to_claim_world_class": false,
"preflight_counts_as_evidence": false,
"credential_value_exposed": false
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/world_class_evidence_preflight.json"
],
"detail": "Collection preflight may help operators gather evidence, but it must not print secrets or change world-class readiness."
},
{
"key": "preflight-submission-kit-handoff",
"label": "Preflight exposes a safe submission-kit handoff",
"status": "pass",
"expected": {
"directory": "evidence/world_class/submissions",
"drafts_count_as_evidence": false,
"preflight_counts_submission_as_completion": false,
"html_report": "reports/world_class_evidence_preflight.html",
"html_exists": true,
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions",
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts",
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
"guard_claim": "python3 scripts/yao.py world-class-claim-guard .",
"artifact_prefill_counts_as_evidence": false,
"artifact_role_source": "world-class-submission-kit",
"artifact_role_counts_as_evidence": false,
"artifact_role_prefill_counts_as_evidence": false,
"submission_ref_role_present": true,
"supporting_evidence_role_present": true,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false,
"submission_ref_total_present": true,
"supporting_evidence_total_present": true
},
"actual": {
"directory": "evidence/world_class/submissions",
"drafts_count_as_evidence": false,
"preflight_counts_submission_as_completion": false,
"html_report": "reports/world_class_evidence_preflight.html",
"html_exists": true,
"prepare_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions",
"prepare_prefilled_submission": "python3 scripts/yao.py world-class-submission-kit . --output-dir evidence/world_class/submissions --prefill-artifacts",
"validate_intake": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
"submission_review": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
"refresh_ledger": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
"guard_claim": "python3 scripts/yao.py world-class-claim-guard .",
"artifact_prefill_counts_as_evidence": false,
"artifact_role_source": "world-class-submission-kit",
"artifact_role_counts_as_evidence": false,
"artifact_role_prefill_counts_as_evidence": false,
"submission_ref_role_present": true,
"supporting_evidence_role_present": true,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false,
"submission_ref_total_present": true,
"supporting_evidence_total_present": true
},
"paths": [
"reports/world_class_evidence_preflight.json",
"reports/world_class_evidence_preflight.html"
],
"detail": "Preflight must give operators the exact draft, SHA-prefill, intake, review, ledger, and claim-guard commands without letting drafts, prefill, or submissions count as accepted evidence."
},
{
"key": "review-studio-preflight-artifact-role-handoff",
"label": "Review Studio mirrors preflight artifact roles",
"status": "pass",
"expected": {
"provider-holdout": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 1,
"submission_ref_ready_count": 1,
"supporting_evidence_total_count": 6,
"supporting_evidence_ready_count": 6,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"human-adjudication": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 8,
"supporting_evidence_ready_count": 8,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"native-permission-enforcement": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 11,
"supporting_evidence_ready_count": 11,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"native-client-telemetry": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 6,
"supporting_evidence_ready_count": 6,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
}
},
"actual": {
"provider-holdout": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 1,
"submission_ref_ready_count": 1,
"supporting_evidence_total_count": 6,
"supporting_evidence_ready_count": 6,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"human-adjudication": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 8,
"supporting_evidence_ready_count": 8,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"native-permission-enforcement": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 11,
"supporting_evidence_ready_count": 11,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
},
"native-client-telemetry": {
"role_source": "world-class-submission-kit",
"counts_as_evidence": false,
"artifact_prefill_counts_as_evidence": false,
"submission_ref_total_count": 2,
"submission_ref_ready_count": 2,
"supporting_evidence_total_count": 6,
"supporting_evidence_ready_count": 6,
"submission_ref_copy_to_artifact_refs": true,
"supporting_evidence_copy_to_artifact_refs": false
}
},
"paths": [
"reports/world_class_evidence_preflight.json",
"reports/review-studio.json"
],
"detail": "The Review Studio world-class action card must carry the same submission-ref versus supporting-evidence contract as the preflight handoff."
},
{
"key": "world-class-phase-queue-consistency",
"label": "World-class phase queues mirror repair rows",
"status": "pass",
"expected": {
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 12,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"phase_queue_counts_as_completion": false
},
"top_level_phase_queue": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 4,
"row_count": 4,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"operator with provider credentials",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 8,
"row_count": 8,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"item_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
},
"phase_queue_counts_as_completion": false,
"operator_runbook_summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 12,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"phase_queue_counts_as_completion": false
},
"operator_runbook_top_level_phase_queue": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 4,
"row_count": 4,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"operator with provider credentials",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 8,
"row_count": 8,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"operator_runbook_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
},
"review_studio_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
}
},
"actual": {
"summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 12,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"phase_queue_counts_as_completion": false
},
"top_level_phase_queue": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 4,
"row_count": 4,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"operator with provider credentials",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 8,
"row_count": 8,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"operator_runbook_summary": {
"phase_queue_count": 2,
"phase_queue_blocked_count": 2,
"phase_queue_row_count": 12,
"phase_queue_next_phase": "unblock-access",
"phase_queue_next_action_id": "human-adjudication-precheck-human-reviewer",
"phase_queue_next_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"phase_queue_counts_as_completion": false
},
"operator_runbook_top_level_phase_queue": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 4,
"row_count": 4,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"operator with provider credentials",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 8,
"row_count": 8,
"owners": [
"Browser/Chrome/IDE/provider client integrator",
"human reviewer",
"target client or installer integrator"
],
"evidence_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"item_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
},
"operator_runbook_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
},
"review_studio_phase_queues": {
"provider-holdout": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"operator with provider credentials"
],
"evidence_keys": [
"provider-holdout"
],
"next_action_id": "provider-holdout-precheck-provider-api-key",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"human-adjudication": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-precheck-human-reviewer",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 5,
"row_count": 5,
"owners": [
"human reviewer"
],
"evidence_keys": [
"human-adjudication"
],
"next_action_id": "human-adjudication-source-check-blind_review_attested",
"verification_command": "python3 scripts/yao.py output-review && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-permission-enforcement": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-precheck-native-guard",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"target client or installer integrator"
],
"evidence_keys": [
"native-permission-enforcement"
],
"next_action_id": "native-permission-enforcement-source-check-native_enforcement_count",
"verification_command": "python3 scripts/yao.py runtime-permissions . --package-dir dist && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
],
"native-client-telemetry": [
{
"phase": "unblock-access",
"priority": 20,
"status": "blocked",
"blocked_count": 1,
"row_count": 1,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-precheck-external-client",
"verification_command": "python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
},
{
"phase": "collect-source",
"priority": 40,
"status": "blocked",
"blocked_count": 2,
"row_count": 2,
"owners": [
"Browser/Chrome/IDE/provider client integrator"
],
"evidence_keys": [
"native-client-telemetry"
],
"next_action_id": "native-client-telemetry-source-check-adoption_sample_count",
"verification_command": "python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl && python3 scripts/yao.py world-class-preflight . --submissions-dir evidence/world_class/submissions",
"counts_as_completion": false
}
]
},
"phase_queue_counts_as_completion": false
},
"paths": [
"reports/world_class_evidence_preflight.json",
"reports/world_class_operator_runbook.json",
"reports/review-studio.json"
],
"detail": "Phase queues must be derived from repair rows in preflight and mirrored into the operator runbook and Review Studio without counting queue guidance as completion evidence."
},
{
"key": "review-studio-no-overclaim",
"label": "Review Studio does not overclaim pending world-class evidence",
"status": "pass",
"expected": false,
"actual": false,
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/review-studio.json"
],
"detail": "When world-class evidence is pending, Review Studio must stay in a review or warning posture."
},
{
"key": "claim-guard-package-runtime-surface",
"label": "Claim guard covers package and runtime claim surfaces",
"status": "pass",
"expected": {
"overclaim_guard_active": true,
"violation_count": 0,
"ledger_ready_to_claim_world_class": false,
"ledger_pending_count": 4,
"metadata_covers_json": true,
"package_surface_minimum": true,
"claim_surface_covers_package": true,
"required_surfaces": {
"README.md": true,
"SKILL.md": true,
"manifest.json": true,
"agents/interface.yaml": true,
"evidence/world_class/README.md": true,
"security/permission_policy.json": true,
"reports/world_class_evidence_ledger.json": true,
"dist/manifest.json": true,
"dist/targets/openai/adapter.json": true
},
"prohibited_surfaces": []
},
"actual": {
"overclaim_guard_active": true,
"violation_count": 0,
"ledger_ready_to_claim_world_class": false,
"ledger_pending_count": 4,
"metadata_covers_json": true,
"package_surface_minimum": true,
"claim_surface_covers_package": true,
"required_surfaces": {
"README.md": true,
"SKILL.md": true,
"manifest.json": true,
"agents/interface.yaml": true,
"evidence/world_class/README.md": true,
"security/permission_policy.json": true,
"reports/world_class_evidence_ledger.json": true,
"dist/manifest.json": true,
"dist/targets/openai/adapter.json": true
},
"prohibited_surfaces": []
},
"paths": [
"reports/world_class_claim_guard.json",
"manifest.json",
"agents/interface.yaml",
"dist/manifest.json",
"dist/targets/openai/adapter.json",
"evidence/world_class/README.md",
"security/permission_policy.json",
"reports/world_class_evidence_ledger.json"
],
"detail": "The overclaim guard must scan package manifests, adapter metadata, security policy, and ledger surfaces before public readiness can be trusted."
},
{
"key": "world-class-evidence-workflow-coverage",
"label": "World-class evidence workflows cover every pending ledger entry",
"status": "pass",
"expected": {
"keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"intake_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"submission_review_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_runbook_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_coordination_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_coordination_counts_as_completion": false,
"operator_release_gate_ready": false,
"operator_release_gate_counts_as_completion": false,
"review_studio_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"intake_ready_to_claim_world_class": false,
"submission_review_ready_to_claim_world_class": false,
"submission_review_counts_as_completion": false,
"operator_runbook_ready_to_claim_world_class": false,
"operator_runbook_counts_as_completion": false,
"next_actions_present": {
"human-adjudication": true,
"native-client-telemetry": true,
"native-permission-enforcement": true,
"provider-holdout": true
},
"commands": {
"human-adjudication": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"native-client-telemetry": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"native-permission-enforcement": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"provider-holdout": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
}
}
},
"actual": {
"keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"pending_count": 4,
"human_pending_count": 1,
"external_pending_count": 3,
"source_check_count": 19,
"source_pass_count": 11,
"source_blocked_count": 8,
"plan_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"intake_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"submission_review_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_runbook_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_coordination_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"operator_coordination_counts_as_completion": false,
"operator_release_gate_ready": false,
"operator_release_gate_counts_as_completion": false,
"review_studio_keys": [
"human-adjudication",
"native-client-telemetry",
"native-permission-enforcement",
"provider-holdout"
],
"intake_ready_to_claim_world_class": false,
"submission_review_ready_to_claim_world_class": false,
"submission_review_counts_as_completion": false,
"operator_runbook_ready_to_claim_world_class": false,
"operator_runbook_counts_as_completion": false,
"next_actions_present": {
"human-adjudication": true,
"native-client-telemetry": true,
"native-permission-enforcement": true,
"provider-holdout": true
},
"commands": {
"human-adjudication": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"native-client-telemetry": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"native-permission-enforcement": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
},
"provider-holdout": {
"intake": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"operator_runbook": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
},
"review_studio": {
"prepare_submission": true,
"validate_intake": true,
"submission_review": true,
"refresh_ledger": true,
"guard_claim": true
}
}
}
},
"paths": [
"reports/world_class_evidence_ledger.json",
"reports/world_class_evidence_plan.json",
"reports/world_class_evidence_intake.json",
"reports/world_class_submission_review.json",
"reports/world_class_operator_runbook.json",
"reports/review-studio.json"
],
"detail": "Every pending world-class evidence key must have matching plan, intake, submission review, operator runbook, and Review Studio actions without counting planned work as completion."
},
{
"key": "skill-os-2-review-current-evidence",
"label": "Skill OS 2.0 review summary mirrors current evidence",
"status": "pass",
"expected": [
"score `91`",
"`16` gates",
"`3` warnings",
"`67` declared internal modules",
"`86 / 86` CLI help smoke checks passing across `153` scripts",
"`689` zip entries",
"archive with `689` entries",
"`12` installer permission checks enforced",
"`0` permission failures",
"`25` required artifacts",
"`23` reproduction commands",
"initial load `998/1000`",
"target count is `82`"
],
"actual": "all present",
"paths": [
"reports/skill-os-2-review.md",
"reports/review-studio.json",
"reports/package_verification.json",
"reports/install_simulation.json",
"reports/security_trust_report.json",
"reports/context_budget.json",
"reports/benchmark_reproducibility.json",
"scripts/ci_test.py"
],
"detail": "Manual 2.0 review summaries must not drift from generated gate, package, trust, context, benchmark, or CI evidence."
}
],
"artifacts": {
"json": "reports/evidence_consistency.json",
"markdown": "reports/evidence_consistency.md"
}
}
Reference in New Issue View Git Blame Copy Permalink