Claude for Legal

Anthropic's official legal domain Plugin ecosystem with 12 first-party plugins and 5 Managed Agent Cookbooks, a reference architecture for vertical AI agent design

andrej-karpathy-skills

Installable version of Karpathy's four principles, a 65-line CLAUDE.md that addresses LLM coding agents' silent assumptions, over-engineering, and orthogonal edits

hello-agents

The most structured open-source Chinese tutorial on AI Agent development. Covers MCP/A2A/ANP protocol comparison, a 200-line SimpleAgent framework, Agentic RL, and three full-stack projects. Learning resource, not a production tool. Apache 2.0 licensed.

16 Releases in One Day: The AI-Era Personal Tool Development Method

An indie developer shipped 16 versions in 7 hours using Claude AI. This isn't chaos — it's a methodology. Two patterns worth stealing: 3-layer decoupling and AI-compressed research cycles.

Academic Research Skills

Full-pipeline academic research framework for Claude Code covering deep research, paper writing, peer review, and workflow orchestration with human-in-the-loop design

Understand Anything

Converts any codebase or knowledge base into an interactive knowledge graph using tree-sitter static analysis plus LLM semantic reasoning, supporting 15+ AI platforms

magic-trace

Jane Street's Intel PT hardware tracing tool that records every function call at ~40ns resolution with 2-10% overhead. Linux + Intel x86 only.

gs-quant

Goldman Sachs' open-source institutional-grade quantitative finance Python SDK covering derivatives pricing, risk management, and backtesting.

Your AI Has Access to Everything — and Understands Nothing

browser-use

Python framework for AI agents to control web browsers. Uses Playwright + LLM for DOM-indexed ReAct-style automation with Claude/GPT/Gemini/Ollama support. Official MCP and Claude Code Skill integration. 95k+ stars. MIT licensed.