Eval Harness

Builds an eval harness for capabilities and regressions, with metrics, graders and repeatable tests.

How to use it

Install it with the open Skills CLI (needs Node.js), then restart your agent:

npx skills add affaan-m/ECC --skill eval-harness
  1. Download the ZIP from this page and unzip it.
  2. Put the eval-harness folder in .claude/skills/ inside your project (or ~/.claude/skills/ for all projects).
  3. Restart Claude Code and call it with /eval-harness.

بالعربي

يبني إطار تقييم للقدرات والتراجعات مع مقاييس ومحكمين واختبارات قابلة للتكرار؛ ليس ضمانا لصحة كل إجابة.