code-assist
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical…
Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL
Claude Code
$ npx -y skills add mikeyobrien/ralph-orchestrator --skill review-pr --agent claude-code
Codex
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a codex -y
Cursor
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a cursor -y
Gemini CLI
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a gemini-cli -y
GitHub Copilot
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a github-copilot -y
OpenCode
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a opencode -y
Windsurf
$ npx skills add mikeyobrien/ralph-orchestrator --skill review-pr -a windsurf -y
name: review-pr description: Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL metadata: internal: true
Run the `ralph.reviewer.yml` orchestration loop against a pull request. The loop checks out the PR in an isolated worktree, runs tests, reviews the diff, and produces a structured report.
/review-pr <PR number or URL>
Accepts: `207`, `#207`, or `https://github.com/.../pull/207`
Extract the PR number from the argument. Strip `#` prefix or extract from URL path.
ralph run -H ralph.reviewer.yml -p "Review PR #<N>"
**Bash tool settings:**
You are notified when the background job exits; wait for that before reading the report.
Read and print `.ralph/REVIEW-REPORT.md` to the conversation.
If the report file doesn't exist (loop failed before the synthesizer hat), check for and display whatever intermediate files exist: 1. `.ralph/review-scope.md` — what was scoped 2. `.ralph/review-verification.md` — test results 3. `.ralph/review-findings.md` — review findings
Check that the review worktree was removed:
ls -d .worktrees/review-<N> 2>/dev/null
Also note the presence of intermediate files (`.ralph/review-scope.md`, etc.) — they're useful for debugging but the user may want to clean them up later.
| Situation | Action | |-----------|--------| | Ralph exits non-zero | Display error output. Suggest re-running with `RALPH_DIAGNOSTICS=1` | | Report file missing | Display intermediate files that do exist (scope, verification, findings) | | PR argument missing | Ask the user for the PR number | | PR argument unparseable | Ask the user to provide a bare number, `#N`, or full GitHub URL |
A hat-based orchestration framework that keeps AI agents in a loop until the task is done. "Me fail English? That's unpossible!" - Ralph Wiggum
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical…
Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly…
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX…
Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or…
Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative…
Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration