Agent Skills Hub

skill-creator

A framework for building modular, reusable agent skills. Provides guidelines for structuring SKILL.md, bundled scripts, references, and assets to extend Claude's capabilities.

wechat-article-writer

Automated WeChat article writing workflow including web research, viral title generation, drafting, and professional layout optimization.

claude-review

Review Hyperlane documentation changes against project standards, ensuring compliance with architectural patterns and content guidelines.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.

ralph

Convert markdown PRDs into structured prd.json files for the Ralph autonomous AI agent system to enable repeatable, context-aware software development.

vultisig

MPC-based multi-chain wallet SDK and CLI for AI agents and developers. Perform secure, threshold-signed crypto operations (send, swap, sign) across 40+ blockchains without seed phrases.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

ai-marketing-claude

Generate professional multi-platform ad campaigns from a URL. Get ad copy, audience targeting, creative specs, and budget strategies ready for media buying.

tavily-web

Advanced web search, content extraction, and site crawling capabilities using the Tavily API, optimized for AI agent research and data gathering.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.

skills

A project-specific architectural template for Next.js 15, FastAPI, and Supabase applications, including structured AI integration patterns.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.