parallel-cli

Automates web research workflows via Parallel CLI for Hermes agents in JSON-focused modes.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/zulumonkeymetallic/bob --skill parallel-cli-zulumonkeymetallic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/zulumonkeymetallic/bob/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/zulumonkeymetallic/bob --skill parallel-cli-zulumonkeymetallic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hermes agents need a vendor-specific CLI to orchestrate complex web research pipelines, enabling efficient lookups, extraction, enrichment, and monitoring across sources.

Core Features & Use Cases

  • Parallel CLI integration for Hermes agents to perform web search, extract, research, enrichment, FindAll, and monitor tasks in JSON-focused, non-interactive modes.
  • Supports async job handling, context chaining, and status polling to manage long-running research workflows.
  • Use Case: An agent runs a multi-step research task, polls for results, and summarizes findings with citations from sources.

Quick Start

Start a non-interactive web research task with the Parallel CLI for Hermes agent workflows.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I automate web research workflows with JSON output?

To automate web research workflows with JSON output, you can use a CLI tool that orchestrates search, extraction, enrichment, and monitoring in asynchronous, non-interactive modes. This approach requires explicit JSON output and supports context chaining to manage results.

What is asynchronous deep research and how does status polling work?

Asynchronous deep research runs long-running web extraction tasks in the background without blocking execution. Status polling periodically queries the job handler to check completion, enabling agents to retrieve enriched findings and citations once processing finishes.

How do I run non-interactive web search and extraction for agents?

Running non-interactive web search and extraction involves executing a vendor CLI in JSON-focused mode without user interaction. This allows agents to programmatically pass queries, chain context across steps, and collect structured results.

Does the Parallel CLI support context chaining and authentication?

Yes, the Parallel CLI supports context chaining and authentication. It integrates vendor-specific processors and authentication mechanisms to orchestrate complex web research pipelines across multiple sources securely.

What is the best way to monitor web sources and perform FindAll tasks asynchronously?

The best way to monitor web sources and perform FindAll tasks is by using an asynchronous CLI workflow that handles job polling and JSON-focused extraction. This allows continuous tracking and structured data collection across various sources.