Skills for Real Engineers. Straight from my .agents directory.
principle-prove-it-works
Agent skill frombacknotprop/pstack
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.'
How to install principle-prove-it-works
npx skills add backnotprop/pstack# or add only this skill to Claude Code: copy the folder
skills/principle-prove-it-works/
# into
~/.claude/skills/principle-prove-it-works/ (all projects)
.claude/skills/principle-prove-it-works/ (one project)
1# Prove It Works23Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."45**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.67Check the real thing, not a proxy:8- Check process liveness directly, not indirectly through derived state9- Read the actual value, not a cached or derived representation10- When verification fails, suspect the observation method before suspecting the system1112## Script the check when you can1314The 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.1516Keep 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).
Excerpt shown under the repository's MIT license.
More skills in pstack
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
