ask-claude

Query the local Claude CLI and save responses to markdown artifacts.

3|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Tienching/oh-my-codebuddy --skill ask-claude-tienching
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask-claude
Source: https://github.com/Tienching/oh-my-codebuddy/tree/main/.codex/skills/ask-claude
Command: npx skills add https://github.com/Tienching/oh-my-codebuddy --skill ask-claude-tienching

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ask Claude via a local CLI to obtain focused guidance and capture a reusable artifact for later reference.

Core Features & Use Cases

  • Local Claude CLI execution for focused questions, reviews, or second opinions without MCP routing.
  • Artifact generation and storage to .omb/artifacts/claude-<slug>-<timestamp>.md for traceability.
  • Simple routing and prompts designed for predictable, reproducible results.

Quick Start

Invoke the Claude CLI locally with your task to generate a reusable artifact.

Frequently Asked Questions about ask-claude

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

FAQPage Schema
How do I run Claude locally and save the AI responses as artifacts for reference?

Run Claude locally by executing the Claude CLI binary with your query to obtain focused guidance, which automatically captures and saves the output as a reusable artifact in a markdown file for later audit and reference.

Can I use the local Claude CLI for code reviews without routing through an MCP server?

Yes, you can query the local Claude CLI directly for code reviews or second opinions. It executes focused prompts locally without MCP routing, ensuring predictable, reproducible results saved as timestamped artifacts.

Do I need the Claude CLI binary installed to generate reusable AI artifacts?

Yes, the Claude CLI binary must be installed and accessible in your local development environment. This Skill invokes the binary directly to process prompts and store the generated artifacts for traceability.

Where are Claude AI artifacts stored when querying the local CLI?

Claude AI artifacts are saved locally to the .omb/artifacts/ directory. Each file is named using a claude-slug-timestamp convention, ensuring every generated response is traceable and organized for future reference.

What's the best way to get a second opinion on local development questions using Claude?

The best way is to use a local CLI execution designed for focused questions. This approach routes your prompt directly to Claude, avoiding complex integrations, and yields a reusable artifact documenting the AI's guidance for your records.

Does this local Claude integration work for automated prompt workflows?

Yes, the integration uses simple routing and prompts designed for predictable, reproducible results. This makes it suitable for automated local workflows where you need consistent AI guidance captured as markdown artifacts.