Skip to content
Back to skills

Principle Prove It Works

ASecurity

Prove it works. Apply when before declaring a task done, or when judging a claim that something works.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsgit

Works with

  • cursor

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add erickb336/sage-stack --skill principle-prove-it-works --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Principle Prove It Works?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Principle Prove It Works
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/erickb336-principle-prove-it-works/badge)](https://www.skillsdirectory.com/skills/erickb336-principle-prove-it-works)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: principle-prove-it-works
description: "Prove it works. Apply when before declaring a task done, or when judging a claim that something works."
license: MIT
metadata:
  source: "pstack principle-prove-it-works, MIT, Copyright (c) 2026 Lauren Tan, github.com/cursor/plugins, adapted; checked against pstack 0.15.36 at commit 0bb6f37"
---

<!-- Generated by scripts/build.mjs from the sources; edit the source, then run npm run build. -->

# Prove it works

Verify the result by checking the real thing directly. Do not infer it from a proxy, a self-report or "it compiles".

**Why.** Unverified work has unknown correctness. Indirect checks (a file's timestamp, fresh-looking output, an agent's own report, a cached screenshot) feel cheaper than direct observation, and acting on a wrong inference costs far more.

**Check the real thing.**
- Run the feature and inspect the diff.
- Read the actual value, not a cached or derived copy of it.
- Check that a process is alive directly, not through state derived from it.
- When a check fails, suspect the way you observed before you suspect the system.

**Script the check when you can.** The strongest proof is a command that re-runs the same comparison, not a one-time look. Write it, run it, and keep its output visible to the user, where a reviewer can re-run it. Commit it only when a large change, such as a port or a migration, needs a trail that someone can audit later.

**Stop** claiming when the evidence stops. Say what you ran and what you saw, and what you did not verify.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.