返回插件超市
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.
Star
39
近 7 天增长
贡献者
4
语言
Python
更新于
2026-08-05
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.