mikeyobrien

26 mods across 2 repositories, 3.2k stars between them.

code-assist

02

mikeyobrien/ralph-orchestrator

Agent Claude Code

Use this agent when implementing code tasks from task files, working through structured implementation plans, or executing code changes that follow the spec-to-implementation workflow. This agent follows the code-assist SOP for systematic, high-quality code delivery.\n\nExamples:\n\n \nContext: User wants to implement…

3.1k 3d ago A 280 tokens original MIT

ralph-e2e-verifier

03

mikeyobrien/ralph-orchestrator

Agent Claude Code

Use this agent when you need to run the Ralph orchestrator end-to-end test suite, analyze diagnostic outputs, and generate comprehensive reports of findings. This includes validating backend connectivity, orchestration loop behavior, event parsing, hat collections, memory systems, and error handling. Invoke this agent…

3.1k 3d ago A 358 tokens original MIT

ralph-loop-runner

04

mikeyobrien/ralph-orchestrator

Agent Claude Code

Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes successfully, and capturing both results and any runtime issues. Examples:\n\n \nContext: User wants to test if a…

3.1k 3d ago A 286 tokens original MIT

code-assist

05

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

3.1k 3d ago A 53 tokens original MIT

code-task-generator

06

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.

3.1k 3d ago A 40 tokens original MIT

evaluate-presets

07

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.

3.1k 3d ago A 28 tokens original MIT

find-code-tasks

08

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

3.1k 3d ago B 34 tokens original MIT

pdd

09

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.

3.1k 3d ago A 34 tokens original MIT

playwriter

10

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.

3.1k 3d ago A 25 tokens original MIT

pr-demo

11

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

3.1k 3d ago A 35 tokens original MIT

release-bump

13

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish.

3.1k 3d ago A 27 tokens original MIT

review-pr

14

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

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.

3.1k 3d ago A 32 tokens original MIT

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.

3.1k 3d ago A 41 tokens original MIT

tmux-terminal

16

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.

3.1k 3d ago A 23 tokens original MIT

tui-debug-in-pane

17

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.

3.1k 3d ago A 44 tokens original MIT

tui-validate

18

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.

3.1k 3d ago A 44 tokens original MIT

mikeyobrien/ralph-orchestrator

Instructions file

Instructions for mikeyobrien/ralph-orchestrator, a project described as: An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration.

3.1k 3d ago A 3 tokens copy · 100% MIT

ralph-docs

22

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, hats, memories, tasks, backends, presets), debug an unfamiliar failure mode, or propose a code…

3.1k 3d ago A 117 tokens original MIT

ralph-hats

23

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a .ralph/hats/.yml workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph run.

3.1k 3d ago A 59 tokens original MIT

ralph-loop

24

mikeyobrien/ralph-orchestrator

Skill Claude CodeCodex

Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate ralph run or ralph loops, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.

3.1k 3d ago A 54 tokens original MIT