Agent Routines is a versioned, GitHub-ready source repository for reusable AI Agent Skills, deterministic workflows, installation adapters, manuals, validation scripts, and Mermaid diagrams. The source repository is the maintenance source of truth. Codex and Claude Code user or project directories are installation targets only.
npx skills add lliangcol/agent-routinesAgent Routines is a versioned, GitHub-ready source repository for reusable AI Agent Skills, deterministic workflows, installation adapters, manuals, validation scripts, and Mermaid diagrams. The source repository is the maintenance source of truth. Codex and Claude Code user or project directories are installation targets only.
A collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.
Exercise: Build applications with GitHub Copilot agent mode
Claude Code plugin for designing modular systems from functional requirements and reviewing existing codebases for modularity problems with actionable improvement recommendations. Based on the Balanced Coupling model.
Curate resources for vibe coding to build software with AI agents and streamline development workflows.
Self-hosted runtime for AI coding agents. Real Linux containers, your hardware, your keys, your data.
Claude Code skill: generates Vite+React websites via a tiered design prompt library