Oh My Claudecode

Skill Verified Active

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Purpose

To streamline the process of using local AI models for tasks like code review, prompt engineering, and drafting by providing a consistent interface and automatically saving the output.

Features

Advisor routing for Claude, Codex, and Gemini CLIs
Artifact capture of LLM responses
Abstraction of raw CLI commands
Consistent invocation via `omc ask`

Use Cases

Getting code reviews from a local security advisor
Generating implementation plans for issues
Suggesting UX improvements for a given flow
Drafting content using local AI models

Non-Goals

Manually constructing provider CLI commands
Executing arbitrary commands on the local machine
Managing cloud-based LLM providers

Workflow

User invokes `/oh-my-claudecode:ask <provider> <question>`.
The skill routes the request to the `omc ask` command with the specified provider and question.
The `omc ask` command invokes the appropriate local CLI (`claude`, `codex`, or `gemini`).
The LLM processes the prompt.
The result is captured and saved as a markdown artifact in `.omc/artifacts/ask/`.
The artifact path is returned to the user.

Prerequisites

Local Claude, Codex, or Gemini CLI installed and authenticated
tmux installed (for some advanced OMC features, though not strictly required for this specific skill's core function)

Installation

First, add the marketplace

/plugin marketplace add Yeachan-Heo/oh-my-claudecode

/plugin install oh-my-claudecode@omc

Quality Score

Verified

100 /100

Analyzed about 13 hours ago

Trust Signals

Last commitabout 23 hours ago

GitHub owner Yeachan-Heo

Stars33.7k

Downloads 38.8k

LicenseMIT

Websiteoh-my-claudecode.dev

Status

View Source

Similar Extensions

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Skill

Yeachan-Heo

Github

100

Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.

Skill

steipete

Telegram Crabbox E2e Proof

100

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

Skill

steipete

ClawSweeper Skill

100

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.

Skill

steipete

Agent Browser

100

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Skill

shanraisshan

Chat Format

100

Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

Skill

ruvnet