Skip to content
TrustedSkillsbeta
Back to all skills

Write Judge Prompt

Checked
hamelsmu·vlatest·ai-ml·MIT

Critically evaluates and refines prompts for large language models to maximize output quality and relevance.

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 hamelsmu/evals-skills --skill write-judge-prompt -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

hamelsmu

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 hamelsmu/evals-skills at 22418da2bf.

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

Commit
22418da2bf
Manifest
skills/write-judge-prompt/SKILL.md
Scanned
1 file, 137 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

The write-judge-prompt skill generates structured evaluation instructions to assess AI agent outputs against specific criteria. It transforms raw task requirements into precise rubrics that guide an evaluator model in scoring responses accurately and consistently.

When to use it

  • Automated grading: Create objective scoring rules for automated tests or benchmark suites.
  • Quality assurance: Define checklists to verify if an agent's output meets safety, format, or accuracy standards.
  • Model alignment: Craft specific constraints to ensure generated text adheres to complex domain rules (e.g., legal formatting).
  • Iterative improvement: Generate feedback prompts to analyze why a previous agent response succeeded or failed.

Key capabilities

  • Converts natural language task descriptions into formal evaluation rubrics.
  • Supports multi-criteria scoring with weighted importance for different aspects of the output.
  • Generates clear pass/fail conditions for binary decision-making in evaluation pipelines.

Example prompts

  • "Create a judge prompt to evaluate if a Python script correctly parses CSV files while handling missing values."
  • "Write an evaluation rubric for an AI agent that summarizes medical articles, focusing on accuracy and tone neutrality."
  • "Generate a scoring guide to assess whether a coding assistant's explanation is clear for a beginner audience."

Tips & gotchas

Ensure your input task description includes explicit success criteria; vague goals will result in weak judge prompts. This skill works best when paired with a separate generation prompt, creating a closed-loop evaluation system where the agent creates content and the judge validates it.