Agent skill · AI & Agents

ralph-run

Run RALPH autonomous development loop with multi-agent pipeline

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-run --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 17 KB
Bundled scripts: none
Allowed tools: BashReadWriteEditGlobGrepTaskAskUserQuestionTodoWrite
Path: skills/agent/ralph-run/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-RUN - Multi-Agent Autonomous Development Execute the RALPH development cycle using a multi-agent pipeline: **Planner → Coder → QA Reviewer → QA Fixer** ## Commands | Command | Description | |---------|-------------| | `/ralph-run` | Start with default 10 iterations | | `/ralph-run 20` | Start with 20 iterations | | `/ralph-run --parallel` | Run independent subtasks in parallel | | `/ralph-run --simple` | Skip planner, direct implementation | | `/ralph-run --task "desc"` | Single-task mode (no PRD needed) | | `/ralph-run --no-worktree` | Run in current branch (skip worktree isolation) | ## Related Commands | Command | Description | |---------|-------------| | `/ralph-merge` | Merge completed worktree to main branch | | `/ralph-review` | Review worktree changes before merging | | `/ralph-discard` | Abandon worktree without merging | ## Triggers - `/ralph-run` - "run RALPH" - "start autonomous development" - "implement the PRD" ## Critical Rules 1. **USE AGENT PIPELINE** - Planner → Coder → QA Reviewer → QA Fixer 2. **ONE SUBTASK AT A TIME** - Complete fully before moving on 3. **QA MUST PASS** - No skipping QA validation 4. **ASK WHEN UNCERTAIN** - Use AskUserQuestion for amb

What's inside
Steps it walks through
  1. Commands
  2. Related Commands
  3. Triggers
  4. Critical Rules
  5. Multi-Agent Pipeline
  6. Phase 0: Prerequisites & Worktree Setup
  7. Worktree Isolation (unless --no-worktree)
  8. Phase 1: Planning (Planner Agent)
  9. Phase 2: Implementation (Coder Agent)
  10. Phase 3: QA Review (QA Reviewer Agent)
  11. Phase 4: QA Fix (QA Fixer Agent)
  12. Phase 5: Commit & Update
  13. Phase 6: Memory & Learning
  14. Phase 7: Context Compaction
Ships with 1 file
  • metadata.json
Commands it runs
Check for PRD
if [ -f prd.json ]; then
echo "✓ PRD: $PROJECT - $REMAINING stories remaining"
else
echo "❌ No prd.json - run /prd first"
exit 1
fi
Check for implementation plan
if [ -f implementation_plan.json ]; then
echo "✓ Implementation plan exists"
More from claude-skill-registry
All skills →
About this skill
What does the ralph-run skill do?

Run RALPH autonomous development loop with multi-agent pipeline

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ralph-run --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