principle-prove-it-works
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 do I install this agent skill?
npx skills add https://github.com/christofferbergj/agent-skills --skill principle-prove-it-worksIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill instructs the agent to verify its work by running code and scripts against artifacts, which creates an inherent surface for indirect prompt injection from the content being verified. It also encourages the dynamic creation and execution of verification scripts.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Prove It Works
Verify every output by checking the real thing directly: run the feature, read the actual value, inspect the diff. Proxies (file mtimes, self-reports, cached output, "it compiles") do not count. When a check fails, suspect the observation method before the system.
A Claude session without a Computer Use tool hands a check that needs one to Codex through /swarm's Computer Use route. For planning or review phases, the real artifact is the spec, graph, or reviewed diff; this principle does not start implementation.
Script the check when you can. A deterministic script that reruns the comparison beats a one-time look. Keep its output where the human can see it, and commit it only when the trail must be auditable later.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/christofferbergj/agent-skills/principle-prove-it-works">View principle-prove-it-works on skillZs</a>