yaojingang
347 lines
20 KiB
JSON
347 lines
20 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-15",
|
|
"skill_dir": ".",
|
|
"summary": {
|
|
"audit_decision": "continue-iteration",
|
|
"world_class_ready": false,
|
|
"audit_world_class_ready": false,
|
|
"ready_to_claim_world_class": false,
|
|
"ledger_completion_required": true,
|
|
"evidence_requirement_count": 4,
|
|
"task_count": 4,
|
|
"human_task_count": 1,
|
|
"external_task_count": 3,
|
|
"review_task_count": 0,
|
|
"decision": "collect-external-evidence"
|
|
},
|
|
"tasks": [
|
|
{
|
|
"key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"current": "model-executed 0; token-observed 0",
|
|
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
|
|
"runbook": [
|
|
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_execution_runs.json summary.model_executed_count > 0",
|
|
"reports/output_execution_runs.json summary.timing_observed_count > 0",
|
|
"reports/output_execution_runs.json summary.token_observed_count > 0",
|
|
"reports/skill_os2_audit.json item provider-holdout status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/skill_os2_audit.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/provider-holdout.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not commit provider credentials or environment dumps.",
|
|
"The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
|
|
],
|
|
"audit_next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
|
|
},
|
|
{
|
|
"key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"status": "human_required",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"current": "0/5 decisions; pending 5",
|
|
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
|
|
"runbook": [
|
|
"python3 scripts/yao.py output-review-kit --write-template",
|
|
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
|
|
"python3 scripts/adjudicate_output_review.py --write-template",
|
|
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
|
|
"python3 scripts/yao.py output-review",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_review_adjudication.json summary.pending_count == 0",
|
|
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
|
|
"reports/output_review_adjudication.json summary.invalid_decision_count == 0",
|
|
"reports/skill_os2_audit.json item human-adjudication status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_decisions.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/human-adjudication.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Reviewer decisions should not include raw user data or private customer detail.",
|
|
"Keep the answer key separate until after decisions are recorded."
|
|
],
|
|
"audit_next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
|
|
},
|
|
{
|
|
"key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"current": "native-enforced targets 0; installer-enforced targets 4",
|
|
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
|
|
"runbook": [
|
|
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
|
|
"Update the generated target adapter only when the guard is actually enforced by that target.",
|
|
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
|
|
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
|
|
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
|
|
"reports/runtime_permission_probes.json summary.failure_count == 0",
|
|
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
|
|
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"dist/targets/*/adapter.json",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/install_simulation.json",
|
|
"reports/install_simulation.md",
|
|
"security/permission_policy.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not mark native_enforcement true for metadata-only fallbacks.",
|
|
"Keep residual risks visible for targets that still rely on operator enforcement."
|
|
],
|
|
"audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
|
|
},
|
|
{
|
|
"key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"current": "external source events 0; adoption samples 0",
|
|
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
|
"runbook": [
|
|
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
|
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
|
"python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
|
|
"python3 scripts/yao.py skill-atlas --workspace-root .",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
|
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
|
"reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"scripts/telemetry_native_host.py",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Telemetry must remain metadata-only and local-first.",
|
|
"Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
|
|
],
|
|
"audit_next_action": "Install a real client against the native host and import production metadata-only events."
|
|
}
|
|
],
|
|
"evidence_requirements": [
|
|
{
|
|
"key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"current": "model-executed 0; token-observed 0",
|
|
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
|
|
"runbook": [
|
|
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_execution_runs.json summary.model_executed_count > 0",
|
|
"reports/output_execution_runs.json summary.timing_observed_count > 0",
|
|
"reports/output_execution_runs.json summary.token_observed_count > 0",
|
|
"reports/skill_os2_audit.json item provider-holdout status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/skill_os2_audit.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/provider-holdout.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not commit provider credentials or environment dumps.",
|
|
"The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
|
|
],
|
|
"audit_next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
|
|
},
|
|
{
|
|
"key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"status": "human_required",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"current": "0/5 decisions; pending 5",
|
|
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
|
|
"runbook": [
|
|
"python3 scripts/yao.py output-review-kit --write-template",
|
|
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
|
|
"python3 scripts/adjudicate_output_review.py --write-template",
|
|
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
|
|
"python3 scripts/yao.py output-review",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_review_adjudication.json summary.pending_count == 0",
|
|
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
|
|
"reports/output_review_adjudication.json summary.invalid_decision_count == 0",
|
|
"reports/skill_os2_audit.json item human-adjudication status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_decisions.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/human-adjudication.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Reviewer decisions should not include raw user data or private customer detail.",
|
|
"Keep the answer key separate until after decisions are recorded."
|
|
],
|
|
"audit_next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
|
|
},
|
|
{
|
|
"key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"current": "native-enforced targets 0; installer-enforced targets 4",
|
|
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
|
|
"runbook": [
|
|
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
|
|
"Update the generated target adapter only when the guard is actually enforced by that target.",
|
|
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
|
|
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
|
|
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
|
|
"reports/runtime_permission_probes.json summary.failure_count == 0",
|
|
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
|
|
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"dist/targets/*/adapter.json",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/install_simulation.json",
|
|
"reports/install_simulation.md",
|
|
"security/permission_policy.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not mark native_enforcement true for metadata-only fallbacks.",
|
|
"Keep residual risks visible for targets that still rely on operator enforcement."
|
|
],
|
|
"audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
|
|
},
|
|
{
|
|
"key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"current": "external source events 0; adoption samples 0",
|
|
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
|
"runbook": [
|
|
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
|
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
|
"python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
|
|
"python3 scripts/yao.py skill-atlas --workspace-root .",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
|
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
|
"reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"scripts/telemetry_native_host.py",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Telemetry must remain metadata-only and local-first.",
|
|
"Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
|
|
],
|
|
"audit_next_action": "Install a real client against the native host and import production metadata-only events."
|
|
}
|
|
],
|
|
"source_audit": {
|
|
"json": "reports/skill_os2_audit.json",
|
|
"markdown": "reports/skill_os2_audit.md",
|
|
"open_gap_count": 4
|
|
},
|
|
"artifacts": {
|
|
"json": "reports/world_class_evidence_plan.json",
|
|
"markdown": "reports/world_class_evidence_plan.md",
|
|
"ledger": "reports/world_class_evidence_ledger.md",
|
|
"intake": "reports/world_class_evidence_intake.md"
|
|
}
|
|
}
|