Skip to content
TrustedSkillsbeta
Back to all skills

Evaluation Framework

Checked
athola·vlatest·other·MIT

This Evaluation Framework assists in systematically assessing project progress, identifying risks, and ensuring alignment with goals for improved outcomes.

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 athola/claude-night-market --skill evaluation-framework -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

athola

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 athola/claude-night-market at 9045831255.

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

Commit
9045831255
Manifest
plugins/leyline/skills/evaluation-framework/SKILL.md
Scanned
7 files, 1,823 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

This skill provides a structured framework for evaluating AI agent outputs. It allows users to define criteria, assign weights to those criteria, and then score the output against these defined parameters. The resulting evaluation can be used for iterative improvement of agent performance or comparative analysis between different agents.

When to use it

  • Agent Training: Evaluate an agent's responses during training to identify areas needing improvement.
  • A/B Testing: Compare the outputs of two different AI agent configurations based on a consistent evaluation framework.
  • Quality Assurance: Regularly assess an agent’s performance against predefined quality standards.
  • Benchmarking: Objectively measure and track an agent's progress over time using standardized criteria.

Key capabilities

  • Criteria Definition: Ability to specify the parameters used for assessment.
  • Weighted Scoring: Assigning different levels of importance to each criterion.
  • Output Scoring: Applying the defined criteria and weights to score a given AI output.
  • Comparative Analysis: Facilitating comparisons between agent outputs based on evaluation results.

Example prompts

  • "Evaluate this response: [AI Agent Response] using these criteria: Relevance (50%), Accuracy (30%), Clarity (20%)."
  • "Score the following text against a framework where Creativity is weighted 40%, and Conciseness is 60%."
  • “Compare these two responses to the prompt ‘Summarize this article’ using my evaluation criteria.”

Tips & gotchas

The quality of the evaluation heavily depends on clearly defined and well-weighted criteria. Ambiguous or poorly designed criteria will lead to inconsistent and unreliable results.