- Home
- Skills
- Prompt & Skill Engineering
- Skill Evals: Prove Your Skills Trigger
More screenshots
Works with the AI Agents you already use
Skill Evals: Prove Your Skills Trigger
Runs trigger tests and golden tasks on real Claude Code, Codex and Gemini CLI sessions and gives your skills a publishable scorecard.
$15
About this skill
Proves skills work on real agent hosts and produces a publishable scorecard and badge. It drafts trigger tests (should-trigger and near-miss should-not prompts) and golden tasks with fixtures and automated checks, runs them headless several times per prompt in clean temp folders on Claude Code, Codex or Gemini CLI (or as a manual checklist anywhere else), and measures recall, specificity, wrong-skill loads and golden-task pass rate.
Use when you want to test, benchmark or evaluate a skill, check it triggers reliably, compare hosts, prove a skill works before selling it, or generate eval scores for a listing.
Works in Claude Code, Codex, Gemini CLI, Cursor and Copilot. Live-tested on Claude Code, Codex and Gemini CLI (eval grade A), and used to test every skill in the Abiodun Anifowose catalogue. Part of SkillProof by Abiodun Anifowose.
Requires Python 3. Headless runs require local CLI installation and authenticated sessions. Real runs consume API credits or plan limits. Manual mode required for non-CLI hosts.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 25 days ago
Requires