Agent skill · Code Review & Quality

ralph

Create and run Ralph loops for structured AI-driven development. Triggered by "create a ralph loop for X" or "ralph plan for X". Uses interview to clarify requirements, expert review via Ralph wrappers, creates phased task plans, and executes in YOLO mode.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-carmandale-agent-config --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 18 KB
Bundled scripts: none
Path: skills/agent/ralph-carmandale-agent-config/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 Skill Create bulletproof development plans that execute reliably in YOLO mode. ## Trigger Phrases - "create a ralph loop for..." - "ralph plan for..." - "make a ralph loop and start with an interview" - "yolo this feature..." ## The Bulletproof Process ``` 1. RESEARCH - Understand the codebase ↓ 2. INTERVIEW - Gather requirements from user ↓ 3. DESIGN - Create architecture document ↓ 4. EXPERT REVIEW - ralph review design (wrapper) ↓ 5. ORACLE - (if complex) Deep architecture review ↓ 6. CREATE PLAN - Write atomic, complete tasks ↓ 7. PLAN REVIEW - ralph review plan (wrapper) ↓ 8. FINALIZE - User approval ↓ 9. EXECUTE - ralph yolo ↓ 10. POST-REVIEW - ralph review post (wrapper) ``` --- ## Phase 1: RESEARCH (Required) **Before creating ANY interview, understand the codebase.** Start with a canonical template: ```bash ralph scaffold research ``` ### What to Research 1. **Find existing patterns** - How does similar functionality work? 2. **Identify files to modify** - What will change? 3. **Understand the architecture** - Where does this fit? 4. **Note naming conventions** - Match existing style ### Research Commands ```bash # Find relevant files rg -l "keyword" --type sw

What's inside
Steps it walks through
  1. Trigger Phrases
  2. The Bulletproof Process
  3. Phase 1: RESEARCH (Required)
  4. What to Research
  5. Research Commands
  6. Research Output
  7. Phase 2: INTERVIEW (Required)
  8. Interview Question Categories
  9. Interview Template
  10. Phase 3: DESIGN (Required)
  11. Design Document Template
  12. Phase 4: EXPERT REVIEW (Required)
  13. Run Design Review
  14. Process Review Feedback (re-review loop)
Ships with 1 file
  • metadata.json
Commands it runs
ralph scaffold research
Find relevant files
rg -l "keyword" --type swift
find . -name "*.swift" -path "*/Views/*" | head -20
Understand existing patterns
rg -A5 "struct.*View.*:" --type swift | head -50
Check file structure
tree -L 3 path/to/relevant/code/
Read key files
cat path/to/existing/similar/feature.swift | head -100
More from claude-skill-registry
All skills →
About this skill
What does the ralph skill do?

Create and run Ralph loops for structured AI-driven development. Triggered by "create a ralph loop for X" or "ralph plan for X". Uses interview to clarify requirements, expert review via Ralph wrappers, creates phased task plans, and executes in YOLO mode.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ralph-carmandale-agent-config --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