Skip to content
TrustedSkillsbeta
Back to all skills

Eval Relevance

Checked
whitespectre·vlatest·ai-ml

Eval Relevance assesses how well a given query matches a document’s content, boosting search accuracy and information retrieval effectiveness.

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 whitespectre/ai-assistant-evals --skill eval-relevance -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

whitespectre

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 whitespectre/ai-assistant-evals at 8d48470982.

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

Commit
8d48470982
Manifest
skills/eval-relevance/SKILL.md
Scanned
2 files, 62 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

What it does

The eval-relevance skill assesses the relevance of AI agent responses to given prompts. It provides a numerical score representing how well the response addresses the prompt's intent and requirements, allowing for quantitative evaluation of agent performance. This skill is designed to be integrated into automated testing and feedback loops for AI agents.

When to use it

  • Automated Testing: Evaluate an AI agent’s responses across a suite of test prompts to identify areas needing improvement.
  • A/B Testing: Compare the relevance scores of different AI agent versions or configurations.
  • Prompt Engineering Evaluation: Determine how changes to prompt wording impact response quality and relevance.
  • Feedback Loop Optimization: Use relevance scores to automatically adjust training data or fine-tuning parameters for an AI agent.

Key capabilities

  • Relevance Scoring: Assigns a numerical score (likely on a scale) indicating the degree of relevance.
  • Automated Evaluation: Designed for integration into automated workflows and testing pipelines.
  • Quantitative Assessment: Provides objective, measurable data about response quality.

Example prompts

  • "Evaluate the following agent response to this prompt: [prompt text] Response: [agent response]"
  • "Score the relevance of this AI assistant's reply: Prompt: [prompt text], Reply: [agent response]"
  • "Assess the relevance of the following conversation turn: User: [user message], Agent: [agent response]"

Tips & gotchas

The accuracy of the eval-relevance skill depends on the clarity and specificity of the prompts provided to both the agent being evaluated and to the evaluation skill itself. Ensure prompts are well-defined to obtain meaningful relevance scores.