awesome-agent-skills and learn

Given their descriptions, the projects appear to be **competitors**: project A is a curated list of skills and tools for AI coding agents, while project B offers a way to find and install agent skills, suggesting they both aim to provide access to agent capabilities but through different means.

awesome-agent-skills
52
Established
learn
40
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 13/25
Community 19/25
Maintenance 13/25
Adoption 4/25
Maturity 9/25
Community 14/25
Stars: 2,949
Forks: 254
Downloads:
Commits (30d): 0
Language:
License: MIT
Stars: 7
Forks: 3
Downloads:
Commits (30d): 0
Language:
License: MIT
No Package No Dependents
No Package No Dependents

About awesome-agent-skills

heilcheng/awesome-agent-skills

A curated list of skills, tools, tutorials, and capabilities for AI coding agents (Claude, Codex, Antigravity, Copilot, VS Code)

Organizes skills as lazy-loaded instruction files (`SKILL.md`) that AI agents browse, request, and execute on-demand—reducing memory overhead while supporting multiple agent platforms (Claude, Copilot, Codex, Gemini). Aggregates official skill collections from Anthropic, OpenAI, and HuggingFace alongside community-maintained repositories covering document processing, development tools, and domain-specific capabilities. Skills work across agents and delivery mechanisms including CLI installers, MCP, and package managers.

About learn

agentskill-sh/learn

Find & install agent skills. The /learn command for Claude Code, Codex, Cursor, Copilot, and more.

Performs local security scanning on skills before installation and tracks user ratings to surface quality—addressing vulnerabilities from malicious skill files. Integrates with Claude Code, Cursor, Copilot, and seven other AI agent platforms via a standardized skill metadata format, querying a 40,000+ skill directory API with context-aware recommendations based on project analysis.

Scores updated daily from GitHub, PyPI, and npm data. How scores work