graphrag-evaluation
100 / 100 · Low risk
Fine to try.
Use when evaluating GraphRAG system quality across knowledge graph completeness, retrieval relevance, answer correctness, and reasoning verification. Invoke when user mentions evaluate GraphRAG, quality metrics, benchmark, hallucination reduction, answer correctness, multi-step reasoning evaluation, test my GraphRAG, or measure RAG performance. Provides evaluation frameworks, metric selection, and testing protocols.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'graphrag-evaluation' ] || [ -L ~/.agents/skills/'graphrag-evaluation' ]; then echo 'A skill folder named graphrag-evaluation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/onfire7777/universal-ai-skills-library' "$d" && git -C "$d" checkout --quiet '2a76bf42ce5c860adf8d0f3fcf3f6804109ac65b' -- 'skills/graphrag-evaluation' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/graphrag-evaluation' ~/.agents/skills/'graphrag-evaluation' && 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/'graphrag-evaluation' ~/.claude/skills/'graphrag-evaluation' (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
[](https://zalavijaysinh.github.io/skilltrust/repos/onfire7777/universal-ai-skills-library/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 2a76bf4 | 100 |