RAG Evaluation

Use when designing, running, reviewing, or diagnosing evaluations for retrieval-augmented generation systems, including corpora, chunking, retrieval, reranking, context assembly, grounded answers, citations, refusals, latency, cost, and regressions.

9 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sandbaseai/workbuddy-skill --skill rag-evaluation
Manual install
git clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/rag-evaluation ~/.claude/skills/rag-evaluation

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# RAG Evaluation

Use this skill to measure and improve retrieval-augmented generation systems independently of a particular vector store, framework, model vendor, or judge library. Inspect the corpus, access controls, ingestion and retrieval code, prompts, models, configuration, product task, existing traces, privacy constraints, latency target and cost model before selecting metrics.

Separate retrieval, context construction and answer generation. An end-to-end score alone cannot explain which stage failed, and a grounded answer can still be wrong when its sources are wrong.

## Define the evaluation contract

Record:

- target users, tasks, languages, domains and risk tiers;
- corpus snapshot, permissions, freshness and authoritative-source policy;
- retriever, filters, embedding, index, fusion, reranker and top-k configuration;
- generator, prompt, context budget, refusal and citation behavior;
- quality, latency, cost, privacy and safety objectives;
- baseline, candidate, decision thresholds, confidence requirements and owner.

Pin every reproducibility input: source document identifiers and revisions, parser and chunker versions, chunk text hashes, embedding model and dimensions, index build, query rewrite, retrieval parameters, reranker, prompt, generator, decoding, judge, code commit and run time. Do not compare runs whose hidden inputs differ without naming the confounder.

## Build a representative dataset
Read the full skill on GitHub

Details

Skill name
rag-evaluation
Path
skills/rag-evaluation/SKILL.md
License
MIT
Repo updated
8 September 2026

FAQ

What does the RAG Evaluation skill do?

Use when designing, running, reviewing, or diagnosing evaluations for retrieval-augmented generation systems, including corpora, chunking, retrieval, reranking, context assembly, grounded answers, citations, refusals, latency, cost, and regressions.

How do I install the RAG Evaluation skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill rag-evaluation. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is RAG Evaluation popular?

It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.

Related skills

Access Control Security Best Practices

9

sandbaseai/workbuddy-skill

Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.

Security

Accessibility Review

9

sandbaseai/workbuddy-skill

Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.

Frontend & Design

Acquire Codebase Knowledge

9

sandbaseai/workbuddy-skill

Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.

Software Development

RAG Implementation

9

sandbaseai/workbuddy-skill

Use when designing or reviewing Retrieval-Augmented Generation systems, knowledge search, document Q&A, grounding, citations, or retrieval evaluation.

AI, LLMs & Agents

Prompt Optimizer

9

sandbaseai/workbuddy-skill

Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan

AI, LLMs & Agents

Skill Sunset

9

sandbaseai/workbuddy-skill

Use when cleaning up, modernizing, retiring, or evaluating accumulated AGENTS.md, CLAUDE.md, or SKILL.md instructions; produce evidence-backed, reversible recommendations without automatically deleting domain or safety knowledge.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.