The interface is localized. Original skills retain their author's language; some long-form pages are provided in English.
Explore skills
Development · SKILL.md

agent-evaluation

agent-evaluation

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill documentation

GitHub
Loading documentation from the source…
Saved skills