ask

Route advisor prompts to Claude, Codex, or Gemini via the omc ask wrapper and save artifacts.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ask-clementath
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/ClementATH/oh-my-claudecode/tree/main/skills/ask
Command: npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ask-clementath

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Simplifies routing advisor prompts to Claude, Codex, or Gemini using the local omc ask wrapper and ensures the result is captured as an artifact, without manual raw CLI construction.

Core Features & Use Cases

  • Provider-agnostic routing: transparently routes prompts to the selected AI provider via the omc ask wrapper.
  • Artifact persistence: stores the resulting response as an artifact under the project’s .omc/artifacts/ask path.
  • Safety and consistency: enforces correct provider usage and prevents manual CLI flag assembly to reduce errors.

Quick Start

Ask a provider by running /oh-my-claudecode:ask <provider> <question> to receive a response and have it saved as an artifact.

Frequently Asked Questions about ask

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I route a single prompt to Claude, Codex, or Gemini without manually assembling CLI flags?

You can route advisor prompts to Claude, Codex, or Gemini using a local wrapper that transparently handles provider selection, avoiding manual CLI flag assembly and reducing command construction errors.

How are AI advisor responses saved as artifacts when routing prompts to different providers?

AI advisor responses are automatically captured and stored as artifacts under the project’s .omc/artifacts/ask path, ensuring prompt results are persisted locally for later review or planning.

Do I need a specific local CLI installed to route prompts to multiple AI providers?

Yes, routing prompts to AI providers requires the local omc ask wrapper to be installed and authenticated, which enforces correct provider usage and maintains safety consistency across interactions.

What is the best way to use AI providers for quick code reviews and brainstorming while keeping the output?

The best way to handle quick advisor responses for reviews, planning, or brainstorming is to route prompts through a unified wrapper, which captures the resulting output as a local artifact.

When should I avoid using a wrapper to route prompts to different AI providers?

You should avoid using a wrapper for prompt routing if your environment lacks the required local CLI installation or if your use case demands direct, manual control over raw provider CLI flags.