The skill OS for Codex, Claude Code, and Gemini CLI. One pool, one router, one feedback loop — across all three hosts. Per-turn semantic top-K with dynamic context sizing, session-end self-evaluation, and evidence-blended re-ranking that gets better the more you use it.
Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/
Add a description, image, and links to the skill-eval topic page so that developers can more easily learn about it.
To associate your repository with the skill-eval topic, visit your repo's landing page and select "manage topics."