Skip to content
TrustedSkillsbeta
Back to all skills

Eval Harness

Checked
affaan-m·vlatest·ai-ml·MIT

Eval Harness allows you to systematically test and evaluate AI model outputs against a defined set of criteria for consistent performance & 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 affaan-m/ecc --skill eval-harness -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

affaan-m

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 affaan-m/everything-claude-code at d3b8a3e908.

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

Commit
d3b8a3e908
Manifest
skills/eval-harness/SKILL.md
Scanned
4 files, 695 lines
Copies in repo
3 — all of them scanned
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-harness skill provides a framework for evaluating and testing AI models, allowing users to define custom evaluation metrics, run benchmarks, and analyze model performance systematically. It supports structured testing scenarios and integrates with various model interfaces.

When to use it

  • You need to benchmark multiple AI models against the same set of tasks or datasets.
  • You want to measure how well a model performs on specific metrics like accuracy, speed, or response quality.
  • You are developing new AI agents and require a standardized way to validate their capabilities before deployment.

Key capabilities

  • Custom evaluation metric configuration
  • Integration with multiple model APIs
  • Benchmarking across different datasets
  • Performance analysis and reporting

Example prompts

  • "Run a benchmark test on the latest language model using the standard evaluation dataset."
  • "Evaluate this AI agent's performance on sentiment classification tasks."
  • "Compare the accuracy of two models using the eval-harness framework."

Tips & gotchas

  • Ensure that all required dependencies are installed before running evaluations.
  • The skill may require access to specific datasets or APIs, so verify compatibility with your environment.