mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 15:29:36 +00:00
1.1 KiB
1.1 KiB
generate-evidence
Build an Evidence Pack for the current task: link intent → claims → verification artifacts.
Minimum contents
- Sources — commits, files touched, PR link if any.
- Assumptions — explicit list; mark unverified assumptions.
- Freshness — timestamps or commit SHAs for docs and code reviewed.
- Verification — commands run and results (e.g.
pytest,verify-launch, lint); paste exit summary or log pointers. - Contradictions — any claim vs observed behavior; mark
contradicteduntil resolved (see docs/governance/trust-fabric.md). - Rollback / compensation — one paragraph for Class B or R1+ changes.
Tie-in
- Decision memos must reference this pack: docs/governance/approval-policy.md.
- Structured reporting: section 20-point list in docs/governance/discovery-and-output-checklist.md.
Output as structured markdown or JSON-shaped bullets so machines and humans can scan it.