Verify before complete
Require fresh, task-relevant evidence before claiming work is complete, fixed, passing, deployable, or ready to merge. Use at completion and release checkpoints.From its SKILL.md
npx -y skills add kevinb361/agent-skills --skill verify-before-completeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.0 KB, 165 tokens by cl100k_base, as published. Nobody here has run it
Verify before completion
Evidence must precede the claim in the current turn.
- Identify the exact claim about to be made.
- Choose the narrowest command or inspection that directly proves it.
- Run it now against the current working tree or live state, as appropriate.
- Read the result and exit status.
- Report the evidence, including failures and known gaps.
Do not substitute an earlier run, expected behavior, another agent's report, or code inspection for fresh verification. A partial check supports only a partial claim. If verification cannot run, say what remains unverified instead of declaring success.
For code changes, prefer the project's canonical gate. Also inspect the final diff for accidental files, secrets, and unrelated edits. For live systems, distinguish repository validation from deployment and runtime health.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.