Verify

by Yeachan-Heo454bae017356ed1d056182cd929b6eb6cf6143adNo licenseListed Oct 9, 2026Updated Oct 9, 2026

Verify that a change really works before you claim completion

AI-generated overview

Guides an agent to verify that a code change actually works before claiming completion.

What it does: This skill provides a verification workflow for confirming that a feature, fix, or refactor works. It directs the agent to identify the behavior to prove, prefer existing tests, then typecheck or build, run narrow direct commands, and fall back to manual validation. It produces a concise report of what was verified, which commands or tests ran, what passed, and what failed or remains unverified.
When to use it: Use it when the user wants confidence that a change really works before it is declared complete. It fits situations where vague claims of success need to be replaced with concrete evidence.
Requirements: No scripts or special tooling are required beyond the agent; it relies on the project's existing tests, typecheck or build commands, and any direct verification commands available.

Use this skill when the user wants confidence that a feature, fix, or refactor actually works.

Turn vague “it should work” claims into concrete evidence.

Identify the exact behavior that must be proven.
Prefer existing tests first.
If coverage is missing, run the narrowest direct verification commands available.
If direct automation is not enough, describe the manual validation steps and gather concrete observable evidence.
Report only what was actually verified.

Do not say a change is complete without evidence.
If a check fails, include the failure clearly.
If no realistic verification path exists, say that explicitly instead of bluffing.
Prefer concise evidence summaries over noisy logs.

Source and attribution

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.