claim-with-proof

After this, the AI stops saying "done" before it actually is — it runs the verification command and cites the evidence inline before any "shipped" or "tests pass" claim.

For developers who've gotten "done!" from an AI and then discovered the tests weren't even run.

Before: "tests pass! shipped."

[Didn't actually run them. Production breaks 20 minutes later.]

After: verification first

"Ran the test suite. 47 pass, 0 fail. Coverage: 91% on the modified files. Diff: 124 lines across 3 files. Lint clean. The change is ready for review."

Use when

• before any "tests pass / fixed / shipped" statement
• before committing or opening a PR
• after a subagent reports it finished

Three ways to use this

1. Paste it (any AI, 30 seconds, no install)
   Open the .md file, copy contents, paste into Claude / ChatGPT / Cursor / Perplexity with: "Read this and apply it whenever the task it describes comes up in our conversation." Done.
2. Install it (Claude Code / Cursor users)
   Drop the unzipped folder into ~/.claude/skills/ (Claude Code), .cursor/skills/ (Cursor), or your IDE's equivalent. Auto-loads next session.
3. New to AI assistants? Get Claude free at claude.ai, then use Option 1.

€7