home / skills / yeachan-heo / oh-my-claudecode / help

help skill

/skills/help

This skill guides you in using oh-my-claudecode to automate Claude Code tasks with planning, parallel execution, and persistent completion.

npx playbooks add skill yeachan-heo/oh-my-claudecode --skill help

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.8 KB
---
name: help
description: Guide on using oh-my-claudecode plugin
---

# How OMC Works

**You don't need to learn any commands!** OMC enhances Claude Code with intelligent behaviors that activate automatically.

## What Happens Automatically

| When You... | I Automatically... |
|-------------|-------------------|
| Give me a complex task | Parallelize and delegate to specialist agents |
| Ask me to plan something | Start a planning interview |
| Need something done completely | Persist until verified complete |
| Work on UI/frontend | Activate design sensibility |
| Say "stop" or "cancel" | Intelligently stop current operation |

## Magic Keywords (Optional Shortcuts)

You can include these words naturally in your request for explicit control:

| Keyword | Effect | Example |
|---------|--------|---------|
| **ralph** | Persistence mode | "ralph: fix all the bugs" |
| **ralplan** | Iterative planning | "ralplan this feature" |
| **ulw** | Max parallelism | "ulw refactor the API" |
| **plan** | Planning interview | "plan the new endpoints" |

**ralph includes ultrawork:** When you activate ralph mode, it automatically includes ultrawork's parallel execution. No need to combine keywords.

## Stopping Things

Just say:
- "stop"
- "cancel"
- "abort"

I'll figure out what to stop based on context.

## First Time Setup

If you haven't configured OMC yet:

```
/oh-my-claudecode:omc-setup
```

This is the **only command** you need to know. It downloads the configuration and you're done.

## For 2.x Users

Your old commands still work! `/ralph`, `/ultrawork`, `/plan`, etc. all function exactly as before.

But now you don't NEED them - everything is automatic.

## Need More Help?

- **README**: https://github.com/Yeachan-Heo/oh-my-claudecode
- **Issues**: https://github.com/Yeachan-Heo/oh-my-claudecode/issues

---

*Version: 3.5.5*

Overview

This skill guides users on using the oh-my-claudecode (OMC) plugin to orchestrate multi-agent workflows for Claude Code. It explains automatic behaviors, optional control keywords, simple setup, and how to stop or override operations. The skill focuses on practical outcomes: parallel execution, iterative planning, persistence, and token-efficient modes.

How this skill works

OMC activates intelligent behaviors automatically—no learning of commands required. For complex tasks it parallelizes work across specialist agents; for planning it runs an interview-style planner; for long-running jobs it persists until verified complete. Optional keywords provide explicit control and a single setup command initializes the configuration.

When to use it

  • Assign complex or multi-part development tasks that benefit from parallelism and delegation.
  • Run planning sessions for feature design, API endpoints, or implementation roadmaps.
  • Request persistent completion where tasks must be followed through until verified.
  • Optimize for token-efficiency or sequential processing with specialized modes.
  • Quickly bootstrap OMC on a new environment with a single setup command.

Best practices

  • Phrase requests naturally—OMC detects intent and applies the appropriate mode automatically.
  • Use optional keywords (ralph, ralplan, ulw, plan) sparingly when you want explicit control.
  • Invoke 'stop', 'cancel', or 'abort' to interrupt operations; OMC will determine scope contextually.
  • Run the one-time setup command early to ensure all agents and config are available.
  • Prefer concise tasks for single-agent work and higher-level prompts for multi-agent orchestration.

Example use cases

  • Refactor a backend API: include 'ulw' or let OMC auto-parallelize to split work across refactor agents.
  • Design new endpoints: say 'plan the new endpoints' to start an iterative planning interview.
  • Fix a batch of bugs: prefix with 'ralph' or request persistent fixing until verification.
  • Build a frontend component: OMC will activate design sensibility and coordinate UI specialists.
  • Run a token-efficient audit: enable Ecomode to minimize token usage while auditing code.

FAQ

Do I need to learn many commands to use OMC?

No. OMC works automatically for most use cases; optional keywords are available when you want explicit control.

How do I stop a running operation?

Send 'stop', 'cancel', or 'abort' and OMC will determine what to halt based on context.

What is the one-time setup step?

Run the provided setup command once to download configuration and enable all agents and modes.