ask

Route user requests asynchronously to Gemini, Codex, OpenCode, or Droid.

3.4k|329|Updated Oct 25, 2025
One-click install
npx skills add https://github.com/bfly123/claude_code_bridge --skill ask-bfly123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/bfly123/claude_code_bridge/tree/main/claude_skills/ask
Command: npx skills add https://github.com/bfly123/claude_code_bridge --skill ask-bfly123

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables non-blocking delegation of user requests to a chosen AI provider (Gemini, Codex, OpenCode, or Droid), allowing seamless multi-provider workflows without waiting for results.

Core Features & Use Cases

  • Async routing of user requests to a specified AI provider
  • Non-blocking operation that returns a task ID and log path for tracking
  • Suitable for workflows that require quick delegation and later result retrieval across providers

Quick Start

Dispatch a request to a chosen AI provider asynchronously by specifying the provider and the message.

Frequently Asked Questions about ask

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

FAQPage Schema
How do I route requests to Gemini asynchronously without blocking my workflow?

To dispatch a request asynchronously, specify the AI provider and your message. The skill enforces strict non-wait behavior after dispatch, immediately returning a task ID and log path for tracking the background operation later.

Can I use async delegation across multiple AI providers like Codex and OpenCode?

Yes, async delegation supports multi-provider workflows across Gemini, Codex, OpenCode, and Droid. It is designed for non-blocking operation, allowing seamless task dispatch across different models without waiting for results.

How do I track a background AI task after non-blocking delegation?

Track a background AI task using the task ID and log path reported immediately after dispatch. The skill enforces strict non-wait behavior, providing these identifiers so you can retrieve results later in your workflow.

What is asynchronous AI provider delegation and when do I need it?

Asynchronous AI provider delegation routes user requests to a chosen model without blocking execution. You need it for multi-provider workflows that require quick dispatch and later result retrieval, avoiding wait delays.

Are there limitations to non-blocking AI task dispatch?

The main limitation of non-blocking AI task dispatch is strict non-wait behavior; it does not return results immediately. You must track the task ID and log path to retrieve outcomes later, making it unsuitable for synchronous requests.