ask

Route prompts to Claude, Codex, or Gemini via the local omc ask wrapper and persist results as artifacts.

1|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/OliverOuyang/shuhe-work-skills --skill ask-oliverouyang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/OliverOuyang/shuhe-work-skills/tree/main/skills/ask
Command: npx skills add https://github.com/OliverOuyang/shuhe-work-skills --skill ask-oliverouyang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Route prompts to Claude, Codex, or Gemini via the local omc ask wrapper and persist the result as an artifact.

Core Features & Use Cases

  • Route prompts through the local omc ask wrapper to ensure safe, consistent interactions with AI providers.
  • Automatically persist responses as artifacts for auditing and traceability.
  • Use cases include code reviews, implementation planning, and decision logging.

Quick Start

Invoke the omc ask wrapper to route your prompt through the local Claude, Codex, or Gemini CLI and persist the result 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 Claude, Codex, or Gemini and save the result as an artifact?

To route prompts and capture artifacts, invoke the local omc ask wrapper, which directs your prompt to the configured CLI and automatically persists the response as an artifact for auditing.

What is the best way to maintain an auditable trail for AI-assisted code reviews?

Maintaining an auditable trail for code reviews requires routing prompts through the omc ask wrapper, which automatically persists AI responses as artifacts for traceability and decision logging.

Do I need a locally authenticated CLI to route prompts through the omc wrapper?

Yes, routing prompts through the omc wrapper requires a locally authenticated CLI for Claude, Codex, or Gemini to enforce safe interactions and prevent manual raw provider invocations.

Can I use this approach to log implementation planning decisions made by AI providers?

Yes, you can log implementation planning decisions by routing planning prompts through the omc ask wrapper, which captures the AI provider's response and persists it as an artifact.

Why does this method prevent manual raw provider invocations during interactive prompts?

Preventing manual raw provider invocations enforces correct usage and ensures that all interactive prompts are routed safely through the local omc ask wrapper to capture artifacts.

Are there limitations when routing prompts to multiple AI providers via a local wrapper?

Limitations include requiring a locally authenticated CLI for each provider and restricting interactions to the omc ask wrapper, preventing direct manual raw provider invocations for safety.