parallel-cli

Run asynchronous web research and entity discovery via the parallel-cli command-line interface.

Updated May 4, 2026
One-click install
npx skills add https://github.com/InverterNetwork/hermes-agent --skill parallel-cli-inverternetwork
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/InverterNetwork/hermes-agent/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/InverterNetwork/hermes-agent --skill parallel-cli-inverternetwork

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of performing complex, multi-step web research and entity discovery that exceeds the capabilities of simple one-shot search queries.

Core Features & Use Cases

  • Deep Research: Executes asynchronous, multi-step research tasks with support for different processing tiers.
  • Data Enrichment: Infers and adds structured data columns to existing datasets based on web research.
  • Entity Discovery: Performs web-scale FindAll operations to build datasets of specific entities like startups or market trends.
  • Use Case: Use this to research a list of competitors, extract their pricing models, and enrich a CSV file with their headquarters and employee counts.

Quick Start

Use the parallel-cli skill to perform a deep research task on the current state of AI coding agents and return the results in JSON format.

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 and data extraction for a list of entities?

You can automate web research by executing asynchronous, multi-step research tasks via a command-line interface to discover entities, extract structured data, and enrich datasets without manual browsing.

What is agent-native data enrichment and how does it work with existing datasets?

Agent-native data enrichment infers and adds structured data columns to your existing datasets based on web research, automatically querying the web to fill in missing attributes like employee counts or headquarters locations.

Can I run asynchronous deep research jobs from the command line?

Yes, you can run asynchronous deep research jobs directly from the command line, submitting complex queries and polling for processing results across different processing tiers.

Do I need an API key to perform web-scale entity discovery?

Yes, you need a valid API key and the parallel-cli binary installed to interface with the Parallel web services platform and execute web-scale FindAll operations for entity discovery.

What is the best way to build a dataset of competitors from web search results?

The best way to build a competitor dataset is using entity discovery operations to perform web-scale searches, extract their pricing models, and structure the results into formats like JSON or CSV.

What are the limitations of using CLI for multi-step research tasks?

Using a CLI for multi-step research tasks requires managing asynchronous job polling and ensuring your environment has the necessary binary and API key, making it less suited for simple one-shot search queries.