add-parallel

Configure Parallel AI IPC actions in NanoClaw for web search and research.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/chrisfrantz/nanoclaw --skill add-parallel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-parallel
Source: https://github.com/chrisfrantz/nanoclaw/tree/main/.codex/skills/add-parallel
Command: npx skills add https://github.com/chrisfrantz/nanoclaw --skill add-parallel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Legacy MCP-based integration notes for Parallel AI. The Codex version of NanoClaw uses IPC actions instead of MCP.

Core Features & Use Cases

  • Quick Search: Fast web lookups using Parallel Search API (free to use).
  • Deep Research: Comprehensive analysis using Parallel Task API (asks permission).
  • Non-blocking Design: Uses NanoClaw scheduler for result polling (no container blocking).

Quick Start

Install and configure the IPC-based Parallel integration in NanoClaw to begin using web search and structured task features.

Frequently Asked Questions about add-parallel

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

FAQPage Schema
How do I replace MCP-based workflows with IPC actions in NanoClaw?

You need a valid Parallel AI API key, a functional NanoClaw setup, and updated host and container components to successfully expose and execute the IPC actions required for this integration.

How does non-blocking scheduling work for deep research results?

Non-blocking scheduling works by using the NanoClaw scheduler for result polling, ensuring the container does not block while waiting for comprehensive analysis or deep research tasks to complete.

What is the difference between quick search and deep research in Parallel AI?

Quick search performs fast web lookups using the free Parallel Search API, while deep research conducts comprehensive analysis using the Parallel Task API, which asks for user permission before executing.

Can I use Parallel AI web search without blocking my container process?

Yes, you can use Parallel AI web search without blocking your container process by leveraging the NanoClaw scheduler to poll for results, ensuring the integration remains non-blocking.