---
name: cursor-principle-prove-it-works
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.'"
disable-model-invocation: true
metadata:
  decimalai-skill-id: "eb9593d0-b7e0-4575-83ca-ad4ab0785cca"
  decimalai-version-id: "d8f50bd1-5228-4f8c-9a62-6af5f1caff80"
  decimalai-version: "2"
  decimalai-body-sha256: "e31d18752e004725446708d44e4e2f9061156f082cadd286e5f2de4390efa2fc"
  decimalai-name: "cursor/principle-prove-it-works"
  decimalai-format: "1"
  decimalai-invocation: "user"
  decimalai-category: "testing"
  decimalai-source: "https://app.decimal.ai/s/cursor-principle-prove-it-works@2/SKILL.md"
---
# 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.

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).