ask

Routes prompts to local AI providers and saves responses as timestamped artifacts.

5|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/RobinNorberg/oh-my-copilot --skill ask-robinnorberg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/RobinNorberg/oh-my-copilot/tree/main/skills/ask
Command: npx skills add https://github.com/RobinNorberg/oh-my-copilot --skill ask-robinnorberg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Route prompts to local AI providers (Copilot, Claude, Codex, Gemini) and persist the results as artifacts for reuse and auditing.

Core Features & Use Cases

  • Route prompts to the selected local AI providers via a safe wrapper.
  • Persist responses as standardized artifacts for traceability and later review.
  • Enforce provider-version compatibility and prevent raw CLI invocations.

Quick Start

Route a question to Copilot, Claude, Codex, or Gemini using omcp ask and have the response 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 prompts to local AI providers like Copilot or Claude?

You route prompts to local AI providers by using a safe CLI wrapper that enforces version compatibility and prevents raw invocations. This ensures your prompts reach Copilot, Claude, Codex, or Gemini securely for advisor-style responses.

What is the best way to save AI responses as artifacts for auditing?

Saving AI responses as artifacts for auditing involves persisting the output as standardized markdown files under a local directory. This captures timestamps and provider details to enable traceability and later review.

Can I use local CLI tools to get advisor-style responses from Gemini or Codex?

Yes, you can use local CLI tools to get advisor-style responses from Gemini or Codex. The wrapper validates provider versions to ensure your local environment safely invokes these specific models without outdated risks.

Do I need local CLI availability to route prompts to multiple AI providers?

Yes, local CLI availability is required to route prompts to multiple AI providers. The system enforces a wrapper that depends on local command line access to validate provider versions and execute the prompt safely.

Why does routing prompts to local AI fail when using raw CLI invocations?

Routing prompts to local AI fails with raw CLI invocations because the system enforces a safe wrapper to prevent unsafe or outdated executions. Bypassing this wrapper removes provider version validation and artifact capture.