Skill of Skills
The curated directory for AI coding skills — quality-scored across Claude Code, Cursor, Codex, Windsurf, Cline & more
Trust & Quality Guide
Every skill is quality-scored based on structural signals — not just GitHub stars.
Quality Tiers
High-viability skill with gotchas, examples, verification layers.
Good structure, some quality signals present.
Basic skill, limited quality signals.
Risk & Trust
Published by a platform vendor (Anthropic, Cursor, OpenAI, etc.).
Standard permissions. Safe for general use.
Extended permissions. Review before use.
Maintenance Status
Updated recently
< 90 days
Feature-complete with releases
> 90 days + releases
Infrequent updates, no releases
90-365 days
No recent updates
> 365 days
No commit data
N/A
Top Rated
View allgarrytan/gstack
by garrytan
No description available
skills
by vercel-labs
The open agent skills tool - npx skills
openai/codex
by openai
No description available
everything-claude-code
by affaan-m
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
jackwener/opencli
by jackwener
No description available
Wei-Shaw/sub2api
by Wei-Shaw
No description available
Recently Added
View allHKUDS/Vibe-Trading
by HKUDS
No description available
777genius/agent-teams-ai
by 777genius
No description available
santifer/career-ops
by santifer
No description available
hatchet-dev/hatchet
by hatchet-dev
No description available
LLMQuant/quant-mind
by LLMQuant
No description available
triggerdotdev/trigger.dev
by triggerdotdev
No description available
Skill Types
Library & API Reference
386 skills
🧪Product Verification
30 skills
📊Data Fetching & Analysis
51 skills
🔄Business Process & Team Automation
65 skills
🏗️Code Scaffolding & Templates
177 skills
🔍Code Quality & Review
85 skills
🚀CI/CD & Deployment
22 skills
📋Runbooks
10 skills
⚙️Infrastructure Operations
38 skills
📦Uncategorized
76 skills
How It Works
Multi-Platform Discovery
Skills are discovered across Claude Code, Cursor, Codex, Windsurf, and Cline by scanning for platform-specific markers like SKILL.md,.cursorrules,AGENTS.md, and more.
Quality Scoring
Each skill is scored on 12 structural quality signals: gotchas/edge cases, progressive disclosure, verification layers, code examples, and more. Quality is 60% of the ranking — not stars.
AI Categorization
Skills are classified into 9 use-case types derived from production lessons scaling to 500+ skills at Uber. Each type maps to a real workflow.