What this skill is for
Use this skill to determine whether an ACP cycle has reviewable evidence for what happened.
When to use it
- Before declaring a demo, pilot, or benchmark run complete.
- When an export, replay, or lifecycle claim needs evidence.
- When a failure needs a preserved audit trail.
When not to use it
- Do not use it to optimize routing.
- Do not use it to infer missing metrics.
- Do not use it to mutate protocol history.
Inputs expected
- Cycle id or cycle JSON
- Desired export mode
- Claim boundary being evaluated
Preflight / prerequisites
- Confirm whether the review is source, generated evidence, or local debris.
- Confirm exports are generated through Relay, not hand-authored.
- Keep audit review separate from field-efficacy claims.
Workflow
- Fetch cycle, audit events, telemetry events, metrics, digests, routing decisions, and exports.
- Generate missing canonical exports if explicitly requested.
- Check for lifecycle anomalies, telemetry gaps, and missing output evidence.
- Produce a compact review summary with gaps and next actions.
Decision rules / judgment criteria
- Claims require artifacts, not memory.
- Missing telemetry is a gap, not a value to infer.
- Generated evidence must be classified before commit or freeze.
- Replay is an inspection path, not a semantic source of truth.
Escalation rules
Escalate when audit events contradict cycle state, export modes are missing, telemetry is absent for claim-bearing flows, or generated evidence is too broad to freeze safely.
Available scripts
scripts/build-audit-summary.mjs: inspect audit, telemetry, export, and lifecycle evidence from cycle JSON or a local demo cycle.
Outputs
- Audit timeline
- Telemetry summary
- Export readiness report
- Claim-safe evidence notes
Failure handling
Preserve failure outputs. Do not clean, rewrite, or regenerate evidence until the failure has been classified.
Trust / safety notes
Audit skills protect claim boundaries. They should make uncertainty more visible, not make the project look cleaner than it is.
Composition notes
Use inside pilot-cycle-review, foresight-submission-prep, and release evidence workflows.
Examples to inspect next
Read examples/casebook.md for audit success, missing export, ambiguous telemetry, and overclaiming examples.
Evaluation hooks
Run scripts/build-audit-summary.mjs and npm run skills:audit.
1---2name: operator-audit3description: Use this skill to inspect ACP audit events, telemetry, exports, replay evidence, and claim-safe operator traces.4---56# What this skill is for78Use this skill to determine whether an ACP cycle has reviewable evidence for what happened.910# When to use it1112- Before declaring a demo, pilot, or benchmark run complete.13- When an export, replay, or lifecycle claim needs evidence.14- When a failure needs a preserved audit trail.1516# When not to use it1718- Do not use it to optimize routing.19- Do not use it to infer missing metrics.20- Do not use it to mutate protocol history.2122# Inputs expected2324- Cycle id or cycle JSON25- Desired export mode26- Claim boundary being evaluated2728# Preflight / prerequisites29301. Confirm whether the review is source, generated evidence, or local debris.312. Confirm exports are generated through Relay, not hand-authored.323. Keep audit review separate from field-efficacy claims.3334# Workflow35361. Fetch cycle, audit events, telemetry events, metrics, digests, routing decisions, and exports.372. Generate missing canonical exports if explicitly requested.383. Check for lifecycle anomalies, telemetry gaps, and missing output evidence.394. Produce a compact review summary with gaps and next actions.4041# Decision rules / judgment criteria4243- Claims require artifacts, not memory.44- Missing telemetry is a gap, not a value to infer.45- Generated evidence must be classified before commit or freeze.46- Replay is an inspection path, not a semantic source of truth.4748# Escalation rules4950Escalate when audit events contradict cycle state, export modes are missing, telemetry is absent for claim-bearing flows, or generated evidence is too broad to freeze safely.5152# Available scripts5354- `scripts/build-audit-summary.mjs`: inspect audit, telemetry, export, and lifecycle evidence from cycle JSON or a local demo cycle.5556# Outputs5758- Audit timeline59- Telemetry summary60- Export readiness report61- Claim-safe evidence notes6263# Failure handling6465Preserve failure outputs. Do not clean, rewrite, or regenerate evidence until the failure has been classified.6667# Trust / safety notes6869Audit skills protect claim boundaries. They should make uncertainty more visible, not make the project look cleaner than it is.7071# Composition notes7273Use inside `pilot-cycle-review`, `foresight-submission-prep`, and release evidence workflows.7475# Examples to inspect next7677Read `examples/casebook.md` for audit success, missing export, ambiguous telemetry, and overclaiming examples.7879# Evaluation hooks8081Run `scripts/build-audit-summary.mjs` and `npm run skills:audit`.