ask

Route prompts to local Claude, Codex, or Gemini CLIs and persist outputs as OMC ask artifacts.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Leap0920/Clean-Portfolio --skill ask-leap0920
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/Leap0920/Clean-Portfolio/tree/main/%25USERPROFILE%25/.openclaude/plugins/cache/omc/oh-my-claudecode/4.14.0/skills/ask
Command: npx skills add https://github.com/Leap0920/Clean-Portfolio --skill ask-leap0920

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the friction of switching between local Claude, Codex, and Gemini CLIs by giving you a single, consistent routing command that also preserves the result as an artifact.

Core Features & Use Cases

  • Provider-agnostic routing: Use the same entry point to target claude, codex, or gemini.
  • Canonical OMC advisor workflow: Ensures correct provider flag selection and version compatibility by using omc ask rather than assembling raw CLI commands.
  • Artifact persistence: Automatically saves the response into a timestamped ask artifact for later review, comparison, or reuse.
  • Use Case: Draft and iterate on implementation plans or reviews (e.g., security-focused code review of a patch) while retaining the full outputs in an artifact log.

Quick Start

Run /oh-my-claudecode:ask codex "review this patch from a security perspective" to route the request to the local Codex CLI and save the response 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 Claude, Codex, or Gemini models and save the responses?

You can route prompts to local models and save responses by using the omc ask command, which selects the correct provider CLI and automatically persists the output as a timestamped artifact.

What is the canonical way to run a security-focused code review using local LLM CLIs?

Running a security-focused code review through local LLM CLIs requires using omc ask with provider selection, ensuring correct flag compatibility while storing the generated review as an OMC ask artifact.

Can I manually construct provider CLI commands to save outputs as artifacts?

No, manually constructing raw provider CLI commands is forbidden. You must use the omc ask entry point to ensure canonical workflow execution and proper artifact persistence into the .omc/artifacts/ask/ directory.

Does omc ask support routing implementation plans to local Codex and saving the output?

Yes, omc ask supports routing implementation planning prompts to local Codex. It executes the request through the correct CLI and saves the full output as a timestamped artifact for later iteration.

Why should I use a single routing command instead of switching between local model CLIs directly?

Using a single routing command removes the friction of switching between local Claude, Codex, and Gemini CLIs, providing consistent provider invocation and automatically retaining results as artifacts for comparison.