mcpbeat

RAG Evaluation Metrics

pramoddutta/rag evaluation metrics

Measure RAG pipeline quality with context precision/recall, faithfulness, answer relevancy, and groundedness using Ragas and DeepEval, with golden datasets and pass/fail thresholds.

3k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
195
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/PramodDutta/qaskills --skill RAG Evaluation Metrics

How to use it

Copy the folder

Take pramoddutta/rag evaluation metrics from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.