craigspaterson/agent-skills
Reusable skill definitions that teach AI agents consistent output formats, writing guidelines, and worked examples — works with Claude Code, GitHub Copilot, Cursor, and more.
Reusable skill definitions that teach AI agents consistent output formats, writing guidelines, and worked examples — works with Claude Code, GitHub Copilot, Cursor, and more.
npx add-skill craigspaterson/agent-skillsReusable skill definitions that teach AI agents consistent output formats, writing guidelines, and worked examples — works with Claude Code, GitHub Copilot, Cursor, and more.
🚀 Access and manage Jira issues effortlessly with this simple MCP server, enabling AI assistants to enhance your project workflows.
This is a no “vibe coding” zone, my personal AI engineering playground where I learn by building real systems. It focuses on mastering LLMs, RAG, agents, and multi-agent architectures through practical implementation, with an emphasis on clean backend design, modularity, and scalability.
An AI-native software engineering methodology — phased LLM agents for architecture, domain design, and planning before dev starts.
MCP server for AI agent deployment health — gateway, CPU/RAM, recent errors, skill registry, upgrades, disk usage. Cross-platform Linux-proc backend; OpenClaw operators get native ~/.openclaw/ parsing.
AI room designer for the Wayfair × Subconscious Hackathon. Upload a room photo and budget, a Subconscious TIM agent reads the space, picks furniture from a shared catalog, and renders the finished room with OpenAI gpt-image-1. Built with Next.js 16, Vercel AI SDK, and Supabase.
Open-source Claude Code skill for quantitative clinical trial design: sample size, Bayesian Go/No-Go, frequentist sensitivity, power curves, PPOS. R-based, generates CSV + PDF.