Skip to content
TrustedSkillsbeta
Back to all skills

Skill_Evaluator

Checked
vuralserhat86·vlatest·ai-ml

Skill_Evaluator assesses generated content for quality and accuracy, ensuring outputs meet desired standards and providing valuable feedback.

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 vuralserhat86/antigravity-agentic-skills --skill skill_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

vuralserhat86

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 vuralserhat86/antigravity-agentic-skills at f033922af6.

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

Commit
f033922af6
Manifest
skills/skill_evaluator/SKILL.md
Scanned
7 files, 1,663 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_evaluator skill assesses the quality and relevance of AI agent outputs. It can analyze text for factual accuracy, logical consistency, and adherence to specific guidelines or criteria. The skill provides a structured evaluation with scores and justifications, helping users understand why an output received a particular rating.

When to use it

  • Evaluating draft content: Assess the quality of blog posts, articles, or marketing copy generated by an AI agent before publishing.
  • Debugging agent behavior: Identify weaknesses in an agent's reasoning process by evaluating its responses to complex prompts.
  • Improving prompt engineering: Determine how changes to a prompt impact the quality and accuracy of the AI’s output.
  • Automated feedback loops: Integrate evaluation into automated workflows for continuous improvement of AI agent performance.

Key capabilities

  • Factual Accuracy Assessment
  • Logical Consistency Analysis
  • Adherence to Guidelines Evaluation
  • Structured Scoring with Justifications

Example prompts

  • "Evaluate the following text for factual accuracy and logical consistency: [text]"
  • "Score this response based on these criteria: [criteria]. Response: [response]"
  • "Assess whether this email adheres to our brand's tone of voice: [email content]"

Tips & gotchas

The quality of the evaluation depends heavily on providing clear and specific guidelines or criteria for assessment. Ensure that the input text is well-defined and free of ambiguity to obtain accurate results.