📄 skillActivePromisingmedium

awesome-agent-skills

by libukai

Agent Skills 终极指南:快速入门、资源推荐、精选技能与实用工具 |The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Toolkit

Supported Platforms

🤖 Claude Code

Stars

4.7k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

85/200

License

Unknown

Forks

333

Last Updated

Jun 11, 2026

Discovered

Apr 17, 2026

Validation

Passed

github.com/libukai/awesome-agent-skills

Quality Breakdown

85/ 200

Content Signals

Gotchas/Edge Cases+40
Progressive Disclosure+30
Trigger Description+20
Verification/Safety+20
Code Examples+15
Composability+15

Repo Health

Recent Activity+15
Scripts/Automation+10
Real Usage (Issues)+10
Single Responsibility+10
Config/Persistence+10
Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Contains .claude/ directory with settings.json - persistent Claude environment configuration
  • Contains .claude-plugin/ with marketplace.json - plugin marketplace configuration that could modify Claude behavior
  • Contains CLAUDE.md file - likely instructions for Claude agent behavior
  • Repository contains Python scripts (generate_report.py, run_eval.py, run_loop.py, package_skill.py) that execute code
  • Multiple agent definitions found (analyzer.md, comparator.md, grader.md) suggesting multi-agent orchestration capability
  • Plugin infrastructure (.claude-plugin/plugin.json files) for extending AI capabilities