AcademySkillsDevelopment

agent-skills-eval

Teams that write agent skills and want to test them against real tasks before sharing them.

  • Recommendedour rating
  • 799gitHub stars
  • MITlicence
  • 3 days agolast update
git clone https://github.com/darkrishabh/agent-skills-eval.git
README.md

Loading the file...

What it does

A test runner for Agent Skills. You write a SKILL.md, add evals, and run them to see whether the skill actually improves how the model handles the task. It is available as an npm package with a CLI and an SDK.

Use cases

  1. 01Test a SKILL.md against sample tasks
  2. 02Compare model results with and without a skill
  3. 03Run skill checks in a CI pipeline

Questions about
agent-skills-eval.

What is agent-skills-eval used for?

Teams that write agent skills and want to test them against real tasks before sharing them. A test runner for Agent Skills. You write a SKILL.md, add evals, and run them to see whether the skill actually improves how the model handles the task. It is available as an npm package with a CLI and an SDK.

How do I install agent-skills-eval?

Run this in your terminal: git clone https://github.com/darkrishabh/agent-skills-eval.git

Is agent-skills-eval open source?

Yes. The code is on GitHub (darkrishabh/agent-skills-eval) under the MIT licence.

Is agent-skills-eval safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.