Agent skill · Workflow & Productivity

ralph-loop

Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for task tracking, and support multiple execution modes. Use when running autonomous coding sessions, implementing self-correcting workflows, or building iterative development pipelines.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-loop-housegarofalo-claude-code-base-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 11 KB
Bundled scripts: none
Version: 1.0.0
Path: skills/agent/ralph-loop-housegarofalo-claude-code-base-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Ralph Loop: Iterative Development Methodology Configure and run self-correcting iterative development loops for autonomous AI coding. Ralph loops iterate until completion criteria are met, with proper state management and handoff support. ## Triggers Use this skill when: - Running autonomous coding sessions - Implementing self-correcting workflows - Building iterative development pipelines - Creating loops that validate and fix their own work - Setting up background coding tasks - Keywords: ralph, iterative, loop, autonomous, self-correcting, iteration, background, continuous ## Concept Overview ``` RALPH LOOP CYCLE ┌─────────────────────────────────────────────┐ │ │ │ ┌──────────┐ │ │ │ Start │ │ │ │ Iteration│ │ │ └────┬─────┘ │ │ │ │ │ v │ │ ┌──────────┐ ┌──────────┐ │ │ │ Work │────>│ Validate │ │ │ │ │ │ │ │ │ └──────────┘ └────┬─────┘ │ │ │ │ │ ┌───────────┴───────────┐ │ │ │ │ │ │ v v │ │ [FAIL] [PASS] │ │ │ │ │ │ │ v │ │ │ ┌──────────┐ │ │ │ │ Complete?│ │ │ │ └────┬─────┘ │ │ │ │ │ │ │ ┌────────┴────────┐│ │ │ │ ││ │ v v v│ │ [Fix Issue] [NO] [YES]│ │ │ │ ││ │ └─────────┘ EXIT │ │ │ │ └────────────────────┘ │ │ <promise>COMPLETE</promise> ``` --- ## Setup Wizard ### Phas

What's inside
Steps it walks through
  1. Triggers
  2. Concept Overview
  3. Setup Wizard
  4. Phase 1: Project Selection
  5. Phase 2: Task Selection
  6. Phase 3: Prompt Configuration
  7. Phase 4: Options Configuration
  8. Auto-Detection Logic
  9. Configuration Files
  10. Directory Structure
  11. config.json
  12. Execution Commands
  13. Quick Start Examples
  14. Archon Integration
Ships with 1 file
  • metadata.json
Commands it runs
Detect project type and commands
if [ -f "package.json" ]; then
elif [ -f "pyproject.toml" ] || [ -f "setup.py" ]; then
elif [ -f "*.csproj" ] || [ -f "*.sln" ]; then
elif [ -f "go.mod" ]; then
fi
Full wizard
Quick with defaults
Auto mode (highest priority TODO task)
Custom prompt without task
More from claude-skill-registry
All skills →
About this skill
What does the ralph-loop skill do?

Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for task tracking, and support multiple execution modes. Use when running autonomous coding sessions, implementing self-correcting workflows, or building iterative development pipelines.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ralph-loop-housegarofalo-claude-code-base-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going