Claude Skill
mgechev/skillgrade
Skillgrade is a TypeScript evaluation framework for writing unit tests for AI agent skills. Supports Claude Code, Codex, and Gemini CLI to catch regressions and ensure skill reliability.
Overview
Stars464
Forks33
LanguageTypeScript
Last pushed2026-05-13
Last synced2026-05-15
Repository
Ownermgechev
Repositoryskillgrade
Full namemgechev/skillgrade
Repo ID1,167,891,649
GitHub URLhttps://github.com/mgechev/skillgrade
🚀 Install this Skill
openclaw install mgechev/skillgradeSummary
Skillgrade is a TypeScript-based evaluation framework that lets you write "unit tests" for your AI agent skills, supporting Claude Code, Codex, and Gemini CLI. It helps you validate skill behavior, catch regressions, and ensure reliability before deploying agent capabilities.
Chinese description
为你的智能体技能编写"单元测试"
Key features
- Write unit-test-like evaluations for agent skills
- Support for Claude Code, Codex, and Gemini CLI
- Catch regressions and validate skill behavior
- TypeScript-based, lightweight framework
- Designed for agent skill reliability
Use cases
- Validate custom Claude Code skills before deployment
- Run regression tests on agent skill updates
- Ensure consistent behavior across different CLI agents
- Integrate skill testing into CI/CD pipelines
- Benchmark skill performance across multiple agent platforms