Skip to content
TrustedSkillsbeta
Back to all skills

Llm Evaluation

Checked
wshobson·vlatest·ai-ml·MIT

Provides LLMs guidance and assistance for building AI and machine learning applications.

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 wshobson/agents --skill llm-evaluation -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

wshobson

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 wshobson/agents at 46891e7e60.

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

Commit
46891e7e60
Manifest
plugins/llm-application-dev/skills/llm-evaluation/SKILL.md
Scanned
2 files, 646 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 llm-evaluation skill enables users to assess the performance of large language models (LLMs) by defining evaluation criteria, scoring responses, and providing detailed feedback. It supports both automated and manual evaluation methods, making it useful for refining model outputs and ensuring alignment with desired outcomes.

When to use it

  • You need to evaluate the accuracy or quality of an LLM's response to a specific query.
  • You want to compare multiple models based on predefined metrics such as relevance, coherence, or factual correctness.
  • You are iterating on prompts and need structured feedback to improve model performance.

Key capabilities

  • Automated scoring based on user-defined criteria
  • Manual evaluation with customizable rubrics
  • Comparison of multiple model responses side by side
  • Detailed feedback generation for each response

Example prompts

  • "Evaluate this LLM's response against the following criteria: accuracy, clarity, and relevance."
  • "Compare the outputs from Model A and Model B using a rubric focused on factual correctness."
  • "Provide detailed feedback on how well this model answered the question about climate change."

Tips & gotchas

  • Define clear evaluation criteria in advance to ensure consistent results.
  • Manual evaluations may be time-consuming for large datasets, so consider automating where possible.