Ask (Local Advisor CLI)

SkillAI & models

The ask skill is a skill that lets an AI agent get a second opinion by asking a locally installed Claude or Gemini command-line tool. It sends a question or task to the chosen local advisor CLI and saves the exchange as a markdown artifact. The artifact records the original task, the backend and prompt used, the raw output, a summary, and action items.

Available today. Use it from your connected AI after setup.

Install a local Claude or Gemini command-line tool on the machine.

Then ask your AI: use the Ask (Local Advisor CLI) skill

What your AI can do with it

  • Run a question through a locally installed Claude CLI
  • Run a question through a locally installed Gemini CLI
  • Choose the backend the user requests or the best-installed option
  • Save a markdown artifact with the task, prompt, raw output, summary, and action items
  • Write artifacts to .omx/artifacts/ask-<backend>-<slug>-<timestamp>.md
  • Keep execution local instead of switching to a remote provider

Getting started

  1. Install a local Claude or Gemini command-line tool on the machine.
  2. Make sure the installed CLI is available to run from the command line.
  3. Invoke the skill with a backend and a question, such as ask claude <question> or ask gemini <question>.
  4. If no backend is specified, let the skill pick the installed backend that best matches the request.
  5. Read the saved markdown artifact in .omx/artifacts/ for the summary and action items.

What this skill tells your AI

The instructions your AI receives, as published by yeachan-heo/oh-my-codex in skills/ask/SKILL.md and read by ahel’s review.

Use a locally installed external advisor CLI for focused questions, reviews, brainstorming, or second opinions. This skill replaces the separate ask-claude and ask-gemini skills.

Usage

$ask claude <question or task>
$ask gemini <question or task>
omx ask claude "<question or task>"
omx ask gemini "<question or task>"

Backend selection

  • Use claude when the user asks for Claude, Anthropic, or the previous $ask-claude behavior.
  • Use gemini when the user asks for Gemini or the previous $ask-gemini behavior.
  • If no backend is specified, choose the installed backend that best matches the user request; if neither is clearly available, explain that a local CLI is required.

Local CLI commands

Claude:

omx ask claude "{{ARGUMENTS}}"
claude -p "{{ARGUMENTS}}"

Gemini:

omx ask gemini "{{ARGUMENTS}}"
gemini -p "{{ARGUMENTS}}"

If needed, adapt to the user's installed CLI variant while keeping local execution as the default path. Do not silently switch to an MCP or remote provider when the local binary is missing.

Artifact requirement

After local execution, save a markdown artifact to:

.omx/artifacts/ask-<backend>-<slug>-<timestamp>.md

Minimum artifact sections:

  1. Original user task
  2. Backend and final prompt sent to the CLI
  3. Raw CLI output
  4. Concise summary
  5. Action items / next steps

Task: {{ARGUMENTS}}

Signals

GitHub stars
33k
Forks
3k
Last commit
Oct 2026

Questions

What does the ask skill do?
It runs a question through a locally installed Claude or Gemini CLI and saves the exchange as a markdown artifact with the original task, raw output, a summary, and action items.
Which backends can it use?
It can use a locally installed Claude CLI or Gemini CLI. The user can request one, or the skill picks the installed backend that best matches the request.
Where is the artifact saved?
The markdown artifact is saved to .omx/artifacts/ask-<backend>-<slug>-<timestamp>.md.
Advanced
Item type
skill
Key
ask-2
Source
github.com/yeachan-heo/oh-my-codex