# Principle Prove It Works

> Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

- Skill: `v1truv1us-ai-eng-system/principle-prove-it-works` (Agent Skill)
- Install (CLI): `npx skillmds add v1truv1us-ai-eng-system/principle-prove-it-works`
- Raw SKILL.md: https://api.skillmd.com/api/skills/v1truv1us-ai-eng-system/principle-prove-it-works/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: v1truv1us (https://skillmd.com/u/v1truv1us-ai-eng-system)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/v1truv1us-ai-eng-system/principle-prove-it-works

---


# 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. Agents report what they intended, not always what happened.