القائمة
This skill should be used when setting up or running the Ralph autonomous coding loop that iterates through stories, runs tests, commits, and logs learnings.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Generate social media preview images (Open Graph) for Rails apps. Creates an OG image using the project's design system at /og-image, screenshots it at 1200x630, and configures meta tags in the layout head.
TDD and testing patterns for Rails applications using Minitest and fixtures. Use when writing tests, setting up test data, or debugging test failures.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Write Ruby and Rails code in DHH's 37signals style. Use when writing Rails code, creating models, controllers, or any Ruby file. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and "clarity over cleverness."
Turbo and Stimulus patterns for Rails applications. Use when implementing interactivity, real-time updates, or frontend behavior without JavaScript frameworks.
| name | ralphing |
| description | This skill should be used when setting up or running the Ralph autonomous coding loop that iterates through stories, runs tests, commits, and logs learnings. |
Ralph is an autonomous AI coding loop that ships features while you sleep. Each iteration runs in a fresh context window, while memory persists through git history and text files.
When the user wants to implement a multi-story feature autonomously, or mentions "ralph", "ralphing", or "autonomous loop".
The user provides a PRD file, or you help them create one. Ask:
bundle exec rake, npm test)# PRD
Branch: `<branch-name>`
## Stories
### US-001: <Story title>
- [ ] <Acceptance criterion>
- [ ] <Acceptance criterion>
### US-002: <Story title>
- [ ] <Acceptance criterion>
Guidelines for stories:
Note: Ralph is typically run in a git worktree. If already on the correct branch (or detached HEAD), the branch checkout is skipped.
~/.claude/skills/ralphing/assets/ralph.sh start <repo_path> <prd.md> [max_iterations] [test_cmd]
This returns a session directory (e.g., /tmp/ralph/ABC123-...) and runs the loop in the background.
Poll the session status periodically:
~/.claude/skills/ralphing/assets/ralph.sh status <ralph_dir>
This outputs:
status: running, complete, or failediteration: current/max iterationsprogress.txtKeep polling until status is complete or failed.
start copies PRD, generates prompt, checks out branch (if needed), and spawns background process<promise>COMPLETE</promise> or max iterations reachedstatus to observe progress without blockingassets/ralph.sh - the loop script (start/status commands)assets/prompt.md - prompt template (uses <RALPH_DIR> placeholder)