The rpi skill runs a full development loop for AI agents. It starts with discovery to understand what needs to be built. Then it moves to crank to implement the work. Finally it runs validation to check everything works. This cycle repeats until the goal is met.
Developers and AI agents use this skill to automate their work. It follows agile practices like test-driven development and continuous delivery. The skill tracks progress with DORA metrics and keeps the team focused on what matters.
You can trigger it with simple commands like run rpi or research-plan-implement one turn. It makes sure no step is skipped and that each phase adds real value. The result is a reliable, repeatable way to build and improve skills.
Add Rpi skill to your workflow
Global
mkdir -p ~/.claude/skills/rpiProject
mkdir -p .claude/skills/rpiSource Repository
More Skill Development Claude Code Skills
Lark Skill Makerlarksuite/cli
Create reusable skills to automate Feishu tasks with lark-cli commands
Setup Matt Pocock Skillsmattpocock/skills
Set up your repo for engineering skills with just a few guided steps
Write A Skillmattpocock/skills
Build new agent skills with clear structure and bundled resources
Writing Skillsobra/superpowers
Test your agent skills like code to make them truly effective
Teachmattpocock/skills
Teach yourself any skill with guided lessons and mission-driven practice
Animejsheygen-com/hyperframes
Safely add Anime.js animations to your HyperFrames compositions with seek control
Contribute Catalogheygen-com/hyperframes
Turn your idea into a new HyperFrames registry block or component
Teach Impeccablepbakaus/impeccable
Old command renamed to /impeccable teach. Use that one instead