← All skills

rag-eval

95 / 100 · Low risk

Fine to try.

By glebis/claude-skills (GitHub) · other · 413 stars · scanned at commit 4d37d3b

Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".

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/'rag-eval' ] || [ -L ~/.agents/skills/'rag-eval' ]; then echo 'A skill folder named rag-eval already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/glebis/claude-skills' "$d" && git -C "$d" checkout --quiet '4d37d3b0af1f98cb4ac820d9abbce95e38e909fb' -- 'rag-eval' && mkdir -p ~/.agents/skills && cp -R "$d"/'rag-eval' ~/.agents/skills/'rag-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/'rag-eval' ~/.claude/skills/'rag-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 glebis/claude-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/glebis/claude-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/glebis/claude-skills/)

Score history