$ loading_
Run and validate tests for AI agent skills and output quality.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "agent-skills-eval" yet — see the docs or source repo.
Run agent-skills-eval on my AI skill with all test cases, and summarize pass rate, failure reasons, and improvement suggestions.
A test summary with pass rate, failed case details, and actionable improvement suggestions.
I updated the skill prompt and output format. Use agent-skills-eval to rerun regression tests and compare performance before and after.
A before-and-after comparison showing improved metrics, regressions, and any newly introduced failures.
Use agent-skills-eval to run the same test suite multiple times, identify unstable cases, and analyze possible causes.
A list of highly variable test cases with possible sources of randomness or prompt-related issues.
Generate reusable AI agent skills and draft configs from website documentation.
Scan Agent Skills for security risks and manage them visually.
Access and sync thousands of agent skills across multiple AI coding tools.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Design, integrate, and optimize AI agent skills for production applications.
Generate test scenarios and measure how well agents follow skills and rules.