About principle-prove-it-works
A verification skill for developers and agents that requires checking task results directly rather than relying on indirect signals. It recommends repeatable scripts and visible evidence reviewers can rerun.
Key features
- 01Verify actual results directly
- 02Avoid proxy signals and cached data
- 03Script deterministic checks
- 04Keep verification evidence visible
Use cases
- 01Confirming a process is actually running
- 02Checking real values instead of derived representations
- 03Providing rerunnable evidence for a migration
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/principle-prove-it-worksin Claude Code to confirm it loaded.
Bundled filesLICENSE
Details
From the project READMEProve It Works
Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."
Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.
Check the real thing, not a proxy:
- Check process liveness directly, not indirectly through derived state
- Read the actual value, not a cached or derived representation
- When verification fails, suspect the observation method before suspecting the system
Script the check when you can
The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.
Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill).