Agent skill · Workflow & Productivity

ralph-tui

Run ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/claude), session management, and troubleshooting. Use when asked to "run ralph-tui", "execute PRD tasks", or "start a ralph session".

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-tui-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: 9 KB
Bundled scripts: none
Path: skills/agent/ralph-tui-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-TUI Agent Execution Guide > A practical guide for AI agents running ralph-tui task loops ## Quick Start ```bash cd /path/to/project # Run ralph-tui (both agents work reliably) ralph-tui run --prd ./prd.json --agent opencode --headless --iterations 20 # or ralph-tui run --prd ./prd.json --agent claude --headless --iterations 20 # Monitor progress ralph-tui status --json | jq '{status, progress: .session.progress}' ``` ## Agent Selection **Both agents work reliably** when sessions are properly managed. | Agent | Speed | Notes | |-------|-------|-------| | `opencode` | ~5-10s/task | Lightweight, fast | | `claude` | ~20-30s/task | More verbose output, thorough | ```bash # OpenCode ralph-tui run --prd ./prd.json --agent opencode --headless # Claude ralph-tui run --prd ./prd.json --agent claude --headless ``` --- ## Prerequisites 1. **ralph-tui installed**: `which ralph-tui` 2. **Agent CLI installed**: `opencode` or `claude` 3. **PRD file**: JSON format with user stories --- ## Preparing a PRD ### Option 1: Create PRD Interactively ```bash ralph-tui create-prd # or with AI chat assistance: ralph-tui create-prd --chat ``` ### Option 2: Convert Markdown to JSON ```bash ralph-tui co

What's inside
Steps it walks through
  1. Quick Start
  2. Agent Selection
  3. Prerequisites
  4. Preparing a PRD
  5. Option 1: Create PRD Interactively
  6. Option 2: Convert Markdown to JSON
  7. Option 3: Manual JSON Structure
  8. Key PRD Fields
  9. The .ralph-tui/ Directory
  10. Running Ralph-TUI
  11. Standard Execution
  12. Check Status
  13. Resume Interrupted Session
  14. Session Management
Ships with 1 file
  • metadata.json
Commands it runs
cd /path/to/project
Run ralph-tui (both agents work reliably)
ralph-tui run --prd ./prd.json --agent opencode --headless --iterations 20
or
ralph-tui run --prd ./prd.json --agent claude --headless --iterations 20
Monitor progress
ralph-tui status --json | jq '{status, progress: .session.progress}'
OpenCode
ralph-tui run --prd ./prd.json --agent opencode --headless
Claude
More from claude-skill-registry
All skills →
About this skill
What does the ralph-tui skill do?

Run ralph-tui task loops for automated PRD execution. Covers headless mode, PRD preparation, agent selection (opencode/claude), session management, and troubleshooting. Use when asked to "run ralph-tui", "execute PRD tasks", or "start a ralph session".

How do I install it?

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