RAG Evaluator
Systematic evaluation of RAG systems across retrieval and generation.
Community trust tier
This skill is community-contributed. Review before installing in sensitive environments.
What is evaluate-rag?
Provides a systematic approach to evaluating Retrieval-Augmented Generation systems by conducting separate analyses of retrieval and generation components. Guides practitioners through error analysis, building evaluation datasets, and measuring Recall@k metrics.
Best for
evaluate-rag is ideal for developers, teams, and agents who need to systematic evaluation of rag systems across retrieval and generation.. Whether you're automating workflows, improving code quality, or extending functionality, this claude skill integrates directly into Claude Code.
Why use evaluate-rag?
- Integrates seamlessly with Claude Code
- From hamelsmu
- Battle-tested by 277 developers
- Open ecosystem standard — works across agents
Installation and usage
Getting started with evaluate-rag is straightforward. Follow the steps below to install this claude skill into your Claude Code environment and start using it immediately.
How to install
claude in your terminal — if it opens, you're ready./ inside Claude Code to see your installed skills and invoke them by name.