45ck Agent Run Evidence Reviewer
Use this skill before accepting that an agent run worked, that a workflow improved, or that a learning should be made durable.
Evidence Checks
- The run has a task or issue id.
- The agent role and tool boundaries are clear.
- Changed files, commands, tests, and validators are named.
- Failures and retries are visible, not edited out.
- Claims are tied to concrete evidence.
- Generated artifacts point back to source.
- Sensitive traces are excluded or redacted.
- Follow-up work is filed instead of hidden in prose.
Verdicts
accept: evidence supports the resultneeds-gate: result may be correct but validation is missingneeds-redaction: evidence is useful but unsafe to store or shareneeds-follow-up: result is partial and requires tracked workreject: evidence contradicts the result or is too weak