Principle Prove It Works

Claude Code port: skills this file names (for example how, why, unslop, arena, or a ... principle skill) are sibling skills in this plugin. They are user-invoked, so the Skill tool can't load them. To use one, read ${CLAUDE_SKILL_DIR}/../<name>/SKILL.md (principle skills: ${CLAUDE_SKILL_DIR}/../principle-<name>/SKILL.md) and follow it. Subagents use the Agent tool; valid model values are fable, opus, sonnet, haiku.

Prove 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.

Pattern: After completing any task, ask: "how do I prove this actually works?"

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

Code and features:

1. Build it (necessary but not sufficient)
2. Run it and exercise the actual feature path
3. Check the full chain: does data flow from input to output?
4. For integrations, test the full communication path end-to-end

Delegation: trust artifacts, not self-reports. When verifying delegated work, inspect the actual output artifact (git diff, file contents, runtime behavior), not the delegate's summary.

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).