25-ai-agent-evidence-pack-spec
Installation
SKILL.md
AI Agent Evidence Pack Spec Skill
Use When
- Use when defining AI-agent compliance evidence items, sources, collection, sampling, integrity, chain of custody, retention, redaction, presentation, and auditor access. Use evidence-pack-builder to assemble a specific pack and control packs to define obligations.
Do Not Use When
- Do not use as the incident evidence pack spec — this is the steady-state compliance evidence pack; the incident pack is a superset for SEV3+ events. Cross-link to
06-deployment-operations/17-ai-incident-evidence-pack-spec. - Do not use this skill to fabricate missing project facts, legal conclusions, test results, approvals, or certification claims.
Required Inputs
| Artefact | Source or provider | Required? | Missing-input behaviour |
|---|---|---|---|
| Target sources: AI_Agent_SOC2_Control_Pack.md, AI_Agent_ISO27001_Control_Pack.md (where applicable), AI_Agent_HIPAA_Control_Pack.md (where applicable), AI_Agent_Compliance_Policy_Pack.md, AI_Agent_Architecture_Spec.md, AI_Agent_Runbook.md, AI Incident Evidence Pack Spec, parent evidence-pack builder skill. | Project owner, approved workspace artefacts, or accountable control owner | Yes | Stop dependent claims; list the missing item, owner, and consequence. For review checks, record not assessed. |
| Scope, audience, baseline/version, and accountable decision owner | Requester or project context | Yes | Ask for or record the gap; do not infer authority or scope. |