← All skills

agent-eval

95 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By EthanYoQ/Skill-hub (GitHub) · coding · 11 stars · scanned at commit 1e73907

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'agent-eval' ] || [ -L ~/.agents/skills/'agent-eval' ]; then echo 'A skill folder named agent-eval already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/EthanYoQ/Skill-hub' "$d" && git -C "$d" checkout --quiet '1e7390741dffd3d5041fca4ebc056071ee3ba137' -- 'archives/user-installed-skills/agent-eval/61ca5bbbd5c736b7/agent-eval' && mkdir -p ~/.agents/skills && cp -R "$d"/'archives/user-installed-skills/agent-eval/61ca5bbbd5c736b7/agent-eval' ~/.agents/skills/'agent-eval' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'agent-eval' ~/.claude/skills/'agent-eval' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for EthanYoQ/Skill-hub shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/EthanYoQ/Skill-hub.svg)](https://zalavijaysinh.github.io/skilltrust/repos/EthanYoQ/Skill-hub/)

Score history