agentic-loop
Autonomous coding loop that plans, builds, tests, and commits
All Skills in This Repository (14)
Pure Emerald Level IndicatorsSetup Review
Ralph configures itself.
prd-check
Validate PRD structure, test coverage, and quality via npx ralph prd-check.
Explain Code
Explain code functionality line by line with concept highlighting.
Vibe & Thrive Cheatsheet
Display agentic-loop commands for planning, execution, quality checks, and setup.
vibe-list
List agentic-loop slash commands, Ralph CLI, and Vibe CLI commands.
Loopgram Review
List and review Telegram brainstorm ideas, then convert them into PRDs.
my-dna
Configures AI persona by gathering user preferences and updating CLAUDE.md with a DNA section.
Styleguide Generator
Generates a /styleguide route with React components and CSS variables from user-defined preferences.
idea
Transform feature concepts into structured idea files for AI development workflows.
Code Review
Review code for security vulnerabilities, error handling, type safety, and quality.
prd
Generate executable PRDs as structured JSON files from idea files.
Tour
Configure agentic-loop project settings by checking dependencies and inspecting files.
Frequently Asked Questions
FAQPage SchemaHow to install agentic-loop?โผ
Run `npx skills add allierays/agentic-loop --all -g -y` in your terminal to install all skills globally. You need Node.js 18+, the Claude Code CLI, and jq installed first.
How does the autonomous coding loop work?โผ
You describe a feature, Claude generates a PRD of small testable stories, and Ralph executes each story by writing code, running lint and tests, and committing when everything passes. Failures are saved and retried automatically.
Does agentic-loop work with Claude Code?โผ
Yes. It is built specifically for Claude Code and orchestrates the Claude CLI for code generation, verification, and testing in a two-terminal workflow.
Can beginners use agentic-loop without coding experience?โผ
Yes. The /tour command walks you through setup interactively, and the loop handles coding, testing, and committing based on plain-English feature descriptions.
How does agentic-loop verify the code it writes?โผ
After each story it runs a verification pipeline covering linting, unit tests, PRD test steps, API smoke tests, and frontend browser checks before committing.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core