youngfreeFJS

youngfreeFJS / skill-test-skill

Public

Tests and scores any Agent Skill against the official anthropics/skills specification. Use this skill when you need to check if a skill repository or SKILL.md file is compliant with the Agent Skills standard, audit skill quality, get a compliance score, or receive specific improvement suggestions.

12
0
100% credibility
Found Apr 02, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

This is a testing tool for AI agent skills that reads instructions, checks against official rules, scores across six quality areas, and provides detailed reports with improvement advice.

How It Works

1
🔍 Discover the Skill Checker

You hear about a helpful tool that tests your AI helper instructions to see if they follow the best rules.

2
📥 Add the Checker to Your Toolkit

You simply bring this checker into your collection of AI helpers so it's ready to use.

3
📁 Gather Your Skill Instructions

You prepare the folder or main instructions file for the AI skill you want to improve.

4
🔬 Launch the Check

You tell the checker to examine your skill, and it carefully reviews every part, scoring it in areas like structure, quality, and design.

5
📋 Receive Your Personalized Report

A clear report appears with your overall grade, like 'Excellent' or 'Good', plus friendly tips on what to fix first.

🎉 Celebrate Your Upgraded Skill

You follow the suggestions to polish your AI skill, making it production-ready and super effective.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is skill-test-skill?

This project is an Agent Skill that audits other Agent Skills against Anthropic's official specification, delivering a compliance score out of 100 across six dimensions like structure, frontmatter, and content quality. Point it at a skill directory or SKILL.md file via natural language queries in English or Chinese, and it spits out a Markdown report with line-by-line checks, grades (like Excellent or Poor), and prioritized fixes—think standardized tests scores for agent skills, similar to SAT or GRE practice tests scores. Built as a lightweight Markdown-based skill, it handles GitHub repos or local paths without needing extra setup.

Why is it gaining traction?

Unlike basic linters, it scores holistically—like unit tests github or dbt tests github but tailored for agent skills—flagging issues against the spec's progressive disclosure rules and trigger optimization, with actionable suggestions that save rework time. Developers dig the detailed rubrics and multi-language reports, plus easy triggers like "Score this skill at /path/to/repo," making it a quick github actions for tests alternative for skill validation. Low stars (12) aside, its focus on real-world Anthropic examples sets it apart from generic checks.

Who should use this?

Anthropic developers building production skills, open-source maintainers auditing PRs with SKILL.md files, or teams optimizing descriptions for better agent triggering. Ideal for those tired of manual spec reviews, especially if you're iterating on skills with scripts, references, or assets directories. Suits contributors to anthropics/skills repos needing english tests scores-style feedback before merging.

Verdict

Grab it if you're deep in Agent Skills development—solid docs and user-facing scoring make it useful despite 12 stars and 1.0% credibility score signaling early maturity; pair with github tests passing badge workflows for CI. Needs more adoption and edge-case tests to hit production-ready status, but it's a practical start for spec compliance.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.