evidence-completion
Skill0 starsChanged 37 days agoMITView on GitHub
Check whether completion claims are supported by direct evidence.
In this repository8 other files it gives its agents.
- browser-qaSkill
- compact-checkpointSkill
- jev-judgeSkill
- rule-rubricSkill
- safety-preflightSkill
- seo-auditSkill
- steer-queueSkill
- targeted-file-relevanceSkill
The file
Files
Audit evidence completion for: $ARGUMENTS
- Restate the requested deliverables and side effects.
- Map every completion claim to inspected evidence: file content, command exit status, rendered output, persisted UI state, or external confirmation.
- Distinguish implementation, configuration, execution, persistence, and publication.
- Mark configured-but-untested items separately from verified behavior.
- Re-run only the smallest checks needed to close material gaps.
- Return
COMPLETE,PARTIAL, orBLOCKED, followed by evidence and remaining limitations.
A hook counter, file existence, toast, redirect, or generated screenshot call is not sufficient evidence by itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.