playbook/codex/skills/verification-before-completion/SKILL.md

name	description
verification-before-completion	Evidence-based verification before claiming completion. Triggers: verify, verification, run tests, prove, 验证, 跑一下, 确认一下, 自证.

Verification Before Completion（先验证再宣称完成）

When to Use

• Any task where correctness matters (bug fixes, refactors, releases)
• When the environment is complex or assumptions are likely

Inputs（required）

• What “done” means (acceptance criteria)
• The smallest verification command(s) that prove it
• Constraints: cannot run tests? no access? limited environment?

Procedure（default）

1. Define Success Signals

   • Tests passing, build artifacts produced, commands return 0
   • Specific output text or file diffs

2. Run the Smallest Check

   • Start narrow (changed module tests) then broaden if needed

3. Record Evidence

   • Capture key output lines, exit codes, and relevant file paths

4. Handle Gaps

   • If verification can’t be run, say why and offer alternatives (manual checklist, static reasoning, targeted logs)

Output Contract（stable）

• What changed
• What was verified (exact commands)
• Evidence (exit codes / key outputs)
• What was not verified (and why)
• Next steps (if any)

Guardrails

• Don’t claim “fixed” without a verification signal
• Prefer repeatable commands over subjective inspection