Agent skill

ralph-wiggum

Executa loops autonomos de desenvolvimento via tecnica Ralph Wiggum. Usar quando: (1) Iniciar loop Ralph na sessao atual, (2) Usuario diz "/ralph-loop", (3) Explicar a tecnica Ralph Wiggum, (4) Configurar estrutura Ralph para um projeto, (5) Usuario menciona "autonomous loop", "I'm in danger" ou "ralph".

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-rafael-2109-frete-sistema --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/agent/ralph-wiggum-rafael-2109-frete-sistema/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 Wiggum Technique The Ralph Wiggum technique is an AI development methodology using autonomous loops to reduce development effort. Named after the Simpsons character ("I'm in danger!"). ## Available Commands ### /ralph-loop (or skill:ralph-wiggum:ralph-loop) Start Ralph loop in current Claude Code session. ### /help (or skill:ralph-wiggum:help) Explain Ralph Wiggum technique and available commands. ### /cancel-ralph (or skill:ralph-wiggum:cancel-ralph) Cancel active Ralph loop. ## Quick Start 1. **Create specs**: Add requirement specs to `.claude/ralph-loop/specs/` directory 2. **Run planning**: `./ralph-loop.sh plan 3` (3 iterations) 3. **Run building**: `./ralph-loop.sh 10` (10 iterations) ## Three Phases, Two Prompts, One Loop | Phase | Prompt | Purpose | |-------|--------|---------| | 1 | (human) | Define requirements, create specs | | 2 | PROMPT_plan.md | Gap analysis: specs vs code → IMPLEMENTATION_PLAN.md | | 3 | PROMPT_build.md | Implement, test, commit, push | ## Loop Mechanics ### Outer Loop (Bash) ```bash while :; do cat PROMPT.md | claude ; done ``` Each iteration: 1. Feeds prompt to Claude 2. Agent completes ONE task 3. Updates IMPLEMENTATION_PLAN.md 4. Commits

What's inside
Steps it walks through
  1. Available Commands
  2. /ralph-loop (or skill:ralph-wiggum:ralph-loop)
  3. /help (or skill:ralph-wiggum:help)
  4. /cancel-ralph (or skill:ralph-wiggum:cancel-ralph)
  5. Quick Start
  6. Three Phases, Two Prompts, One Loop
  7. Loop Mechanics
  8. Outer Loop (Bash)
  9. Inner Loop Control
  10. Key Principles
  11. Key Terminology
  12. When to Regenerate Plan
  13. File Structure
  14. Security Warning
Ships with 1 file
  • metadata.json
Commands it runs
while :; do cat PROMPT.md | claude ; done
docker-compose -f docker-compose.ralph.yml run ralph
More from claude-skill-registry
All skills →
About this skill
What does the ralph-wiggum skill do?

Executa loops autonomos de desenvolvimento via tecnica Ralph Wiggum. Usar quando: (1) Iniciar loop Ralph na sessao atual, (2) Usuario diz "/ralph-loop", (3) Explicar a tecnica Ralph Wiggum, (4) Configurar estrutura Ralph para um projeto, (5) Usuario menciona "autonomous loop", "I'm in danger" ou "ralph".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-rafael-2109-frete-sistema --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