principle-prove-it-works
- Use it when:
- A task is finished and the agent is about to say it's done.
- It does:
- Verifies against the real artifact: runs the feature, reads the actual value, inspects the diff, checks process liveness directly.
- Prefers:
- A script that reruns the same comparison, kept as output a reviewer can rerun.
- Runs:
- Only when you call it.
Skill 12 of 14 in the pstack bundle, after principle-fix-root-causes and before principle-guard-the-context-window.
TL;DR
One of pstack's principle skills, in Cursor's plugin repo. Indirect checks, such as file times, output freshness, an agent's own report or a cached screenshot, feel cheaper than looking, and it rules them out because acting on a wrong inference costs far more than checking the source. When a check fails, it suspects the way it observed before it suspects the system. The strongest proof is a deterministic script, run and kept as an artifact so a reviewer can rerun it instead of trusting the agent's word. The artifact stays visible to you, and is committed only for large or complex work that needs an auditable trail, like a big port or migration, with pstack's show-me-your-work skill.
Summarizes the skill at 8ecfb19.
npx skills add https://github.com/cursor/plugins --skill principle-prove-it-works skills.sh pageSource on GitHubAll skills from cursor/plugins
- Total Downloads
- 5,600 on skills.sh, Nov 9, 2026
- Repo stars
- 15,776 cursor/plugins
- First seen
- May 24, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 384 |
| Sep 28 | 441 |
| Oct 5 | 530 |
| Oct 12 | 426 |
| Oct 19 | 437 |
| Oct 26 | 476 |
| Nov 2 | 373 |
| Nov 9 | 324 |
| Category |
Test-first work, implementation from specs, git hygiene and scope control. Find root causes, review code and test what you built. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
Knowledge and rules the agent applies while it works: best practices, design principles, API references. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From cursor/plugins at 8ecfb19. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: 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: trueProve 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).