Skip to content
TrustedSkillsbeta
Back to all skills

Model Evaluator

Checked
jmsktm·vlatest·ai-ml

Evaluates large language models based on custom metrics and datasets provided by the user, reporting detailed performance analysis.

Repository

Install on your platform

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

Installs under a different name. Its SKILL.md names it Model Evaluator, not the name it is listed under, so the command below uses that name.
  1. 1

    Run this in your project

    terminal
    $ npx skills add jmsktm/claude-settings --skill "Model Evaluator" -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

jmsktm

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 jmsktm/claude-settings at c113b0d7e1.

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

Commit
c113b0d7e1
Manifest
skills/model-evaluator/SKILL.md
Scanned
1 file, 211 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 Model Evaluator skill provides a way to assess and compare different AI models. It allows users to evaluate model performance based on specific criteria, providing insights into which model best suits their needs. This is achieved through structured evaluation frameworks and comparative analysis of results.

When to use it

  • Choosing between LLMs: When deciding which large language model (LLM) to integrate into an application or workflow.
  • Benchmarking models: To establish a baseline performance for various AI models across different tasks.
  • Evaluating custom models: When assessing the effectiveness of fine-tuned or newly developed AI models.
  • Comparing prompt strategies: Determining which prompting techniques yield better results with a given model.

Key capabilities

  • Model evaluation based on defined criteria
  • Comparative analysis of different models
  • Structured evaluation frameworks
  • Performance benchmarking

Example prompts

  • "Evaluate the performance of GPT-4 and Claude 3 Opus on summarization tasks."
  • "Compare the accuracy of Llama 3 70B versus Mistral Large in answering factual questions."
  • "Run a benchmark test for Gemini 1.5 Pro using this evaluation dataset [dataset link]."

Tips & gotchas

The effectiveness of the Model Evaluator depends on having well-defined evaluation criteria and appropriate datasets to assess model performance. Ensure your prompts are clear and specific to obtain meaningful results.