
Ask Advisor Router
Send a prompt to a local Claude, Codex, Gemini, Grok, Cursor or Muse CLI and save the answer as a file.
- Repository
- Yeachan-Heo/oh-my-claudecode
- Stars
- 40,512
- Licence
- MIT
- Files
- 1 file
What it does
This skill lets the agent forward a question or task to another AI command-line tool installed on your machine (such as Codex, Gemini, Grok, Cursor or Muse) through a wrapper command called omc ask. The answer is saved as a markdown file in a .omc/artifacts/ask folder so you can review it later. The skill tells the agent to use this wrapper rather than calling those tools directly.
Great for
- Developers who already have several AI coding CLIs installed and want a second opinion from another model
- Teams that want a saved record of advisor-style reviews, such as a security review of a patch
- Users of the oh-my-claudecode toolkit who want consistent routing to multiple providers
Skip it if
- People without the listed CLIs installed and logged in, since the skill cannot work without them
- Sensitive code or private data sent to third-party providers, because prompts leave your machine through those services
- Users who want a self-contained skill with no external dependencies
Try asking
- “/oh-my-claudecode:ask codex "review this patch from a security perspective"”
- “/oh-my-claudecode:ask gemini "suggest UX improvements for this flow"”
- “/oh-my-claudecode:ask claude "draft an implementation plan for issue #123"”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
ask.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip ask.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip ask.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Verify each provider CLI works with its --version command before asking through the skill
- Review the saved artifact in .omc/artifacts/ask before acting on its advice
- Do not send secrets or proprietary code to providers you have not approved for that data
What's inside
- SKILL.md
Redistributed unmodified from Yeachan-Heo/oh-my-claudecode under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.