claude-skills and skill-forge

The first is a curated collection of pre-built skills for Claude developers to use directly, while the second is a framework for creating and publishing custom skills—making them complements in a workflow where skill-forge generates new additions to repositories like claude-skills.

claude-skills
61
Established
skill-forge
44
Emerging
Maintenance 20/25
Adoption 10/25
Maturity 13/25
Community 18/25
Maintenance 13/25
Adoption 5/25
Maturity 9/25
Community 17/25
Stars: 6,484
Forks: 414
Downloads:
Commits (30d): 13
Language: Python
License: MIT
Stars: 12
Forks: 9
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About claude-skills

Jeffallan/claude-skills

66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

Implements context-aware skill activation that dynamically loads framework-specific references based on detected tech stacks, with 9 multi-skill workflows orchestrating complex development tasks from feature design through testing. Integrates with Atlassian MCP servers (Jira/Confluence) for epic-to-retrospective project lifecycle management, while the "Common Ground" feature surfaces and validates Claude's hidden assumptions about your codebase architecture.

About skill-forge

AgriciDaniel/skill-forge

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

Implements a multi-tier skill architecture (Tiers 1–4) with specialized sub-skills for planning, building, reviewing, and benchmarking, complemented by dedicated agent roles for design, validation, and execution. Includes cross-platform conversion to OpenAI Codex, Google Gemini, and Cursor, plus integrated evaluation pipelines with variance analysis and multi-agent grading. Built on the open Agent Skills standard with stdlib-only Python implementation for scaffolding, quality auditing (0-100 health scores), and performance benchmarking.

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