Skip to content
TrustedSkillsbeta
Back to all skills

Evaluate Rag

Checked
hamelsmu·vlatest·ai-ml·MIT

Evaluates Retrieval-Augmented Generation (RAG) responses for accuracy and relevance, boosting RAG system quality & reliability.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add hamelsmu/evals-skills --skill evaluate-rag -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

hamelsmu

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned hamelsmu/evals-skills at 22418da2bf.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
22418da2bf
Manifest
skills/evaluate-rag/SKILL.md
Scanned
1 file, 166 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The evaluate-rag skill provides a framework to assess Retrieval-Augmented Generation (RAG) pipelines by comparing AI agent outputs against ground truth data. It automatically calculates metrics like accuracy and relevance to determine how well an agent retrieves and utilizes information from its knowledge base.

When to use it

  • Validating the performance of a RAG system before deploying it to production environments.
  • Debugging retrieval issues where the AI answers incorrectly despite having access to relevant documents.
  • Benchmarking different embedding models or chunking strategies to see which yields higher accuracy scores.
  • Continuously monitoring agent health over time to detect drift in data quality or retrieval logic.

Key capabilities

  • Executes automated evaluation tests on RAG pipelines using predefined ground truth datasets.
  • Generates quantitative metrics to score the precision and recall of retrieved context.
  • Facilitates iterative improvement by highlighting specific failures in information retrieval or synthesis.

Example prompts

  • "Run an evaluation test on my customer support bot's RAG pipeline using the provided Q&A dataset."
  • "Compare the accuracy of two different embedding models for my legal document search agent."
  • "Generate a report on why my AI agent is failing to retrieve recent policy updates from the knowledge base."

Tips & gotchas

Ensure you have a reliable ground truth dataset ready, as the skill relies on comparing outputs against known correct answers. This tool is specifically designed for RAG architectures; it will not evaluate standard LLMs without an external retrieval component.