rag-accuracy-skill
Measure RAG answer quality through three core metrics: Faithfulness (accuracy to context), Relevance (retrieval quality), and Answer Quality (overall usefulness).'
npx skills add majiayu000/claude-skill-registry --skill rag-accuracy-skill --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: rag-accuracy version: 1.0 last_updated: 2025-12-04 description: RAG evaluation metrics - faithfulness, relevance, answer quality measurement license: MIT priority: critical triggers: - "accuracy", "evaluation", "faithfulness", "relevance", "metrics" - Evaluation tasks - Quality assessment dependencies: - langsmith-testing-SKILL.md compatibility: - ragas: ">=0.1.0" - langchain: ">=0.1.0" changelog: - version: 1.0 date: 2025-12-04 changes: - Initial release for RAG evaluation - RAGAS framework integration - Custom metric implementations --- # 📈 RAG Accuracy SKILL ## Purpose Measure RAG answer quality through three core metrics: **Faithfulness** (accuracy to context), **Relevance** (retrieval quality), and **Answer Quality** (overall usefulness). --- ## Auto-Trigger Conditions **Activate when:** - User mentions: "accuracy", "evaluation", "faithfulness", "relevance", "metrics" - Evaluation tasks - Quality assessment - A/B testing RAG variants --- ## Core Metrics (3 Metrics) ### 1. Faithfulness (0-1 scale) **Definition:** How accurate is the generated answer to the retrieved context? **Why Critical:** Detects hallucinations (LLM making up facts not in context) **Calculation:*
- Purpose
- Auto-Trigger Conditions
- Core Metrics (3 Metrics)
- 1. Faithfulness (0-1 scale)
- 2. Context Relevance (0-1 scale)
- 3. Answer Relevance (0-1 scale)
- RAGAS Framework Integration
- 1. Installation
- 2. Batch Evaluation
- Custom Metric Implementations
- 1. Faithfulness (Manual)
- 2. Relevance (Manual)
- LangSmith Integration
- 1. Add Metrics as Feedback
pip install ragas
What does the rag-accuracy-skill skill do?
Measure RAG answer quality through three core metrics: Faithfulness (accuracy to context), Relevance (retrieval quality), and Answer Quality (overall usefulness).'
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill rag-accuracy-skill --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.