Skip to content
TrustedSkillsbeta
Back to all skills

Skill Judge

Checked
softaworks·vlatest·agents·MIT

Skill Judge analyzes text for bias, sentiment, or factual accuracy, offering valuable insights and promoting responsible communication.

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 softaworks/agent-toolkit --skill skill-judge -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

softaworks

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 softaworks/agent-toolkit at 3027f20f31.

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

Commit
3027f20f31
Manifest
skills/skill-judge/SKILL.md
Scanned
2 files, 919 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 skill-judge tool evaluates and assesses AI agent skills to determine their effectiveness, reliability, and suitability for specific tasks. It provides structured feedback based on predefined criteria such as accuracy, efficiency, and adherence to guidelines.

When to use it

  • Before deploying an AI agent in a production environment to ensure its capabilities meet required standards.
  • To compare the performance of multiple skills or agents against each other.
  • During development to identify areas for improvement in an AI agent's functionality.
  • When auditing existing skills to verify they align with organizational policies and quality benchmarks.

Key capabilities

  • Evaluates skill accuracy based on predefined metrics.
  • Assesses efficiency in task completion.
  • Provides detailed feedback reports for each evaluation.
  • Supports comparison between multiple agents or skills.

Example prompts

  • "Evaluate the skill-translate tool for accuracy and reliability."
  • "Compare the performance of skill-summarize and skill-extract on a given dataset."
  • "Generate a report assessing how well the skill-judge tool itself performs."

Tips & gotchas

  • Ensure that the evaluation criteria are clearly defined before running an assessment to get meaningful results.
  • The tool may require access to benchmark datasets or test cases for accurate evaluations.