Update to pstack

{
  "description": "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.'",
  "included_files": [],
  "name": "principle-prove-it-works",
  "skill_md_contents": "---\nname: principle-prove-it-works\ndescription: \"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.'\"\ndisable-model-invocation: true\n---\n\n# Prove It Works\n\nVerify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or \"it compiles.\"\n\n**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.\n\n**Pattern:** After completing any task, ask: \"how do I prove this actually works?\"\n\nCheck the real thing, not a proxy:\n- Check process liveness directly, not indirectly through derived state\n- Read the actual value, not a cached or derived representation\n- When verification fails, suspect the observation method before suspecting the system\n\nCode and features:\n1. Build it (necessary but not sufficient)\n2. Run it and exercise the actual feature path\n3. Check the full chain: does data flow from input to output?\n4. For integrations, test the full communication path end-to-end\n\nDelegation: trust artifacts, not self-reports.\nWhen 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.\n\n## Script the check when you can\n\nThe 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. A script comparing the old and new compiled output catches what a glance misses.\n\nKeep 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). Most work just needs it visible, not committed.\n"
}