parallel-cli

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

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/zangjeicy/Hermes --skill parallel-cli-zangjeicy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/zangjeicy/Hermes/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/zangjeicy/Hermes --skill parallel-cli-zangjeicy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of performing complex, multi-step web research and entity discovery that requires more than a simple one-shot search, providing a structured, terminal-native interface for deep research and data enrichment.

Core Features & Use Cases

  • Deep Research: Execute multi-step, asynchronous research jobs with configurable processor tiers for varying levels of depth.
  • Structured Enrichment: Ingest CSV or JSON data to automatically enrich records with web-discovered information like revenue, leadership, or entity details.
  • Entity Discovery: Use the FindAll workflow to perform web-scale discovery of startups, companies, or specific entities based on complex criteria.

Quick Start

Use the parallel-cli skill to perform a deep research report on the current state of AI coding agents and output 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 multi-step web research and data enrichment from the command line?

Automated web research and data enrichment is executed through a structured command-line interface that supports asynchronous job management and structured JSON output. It enables complex, multi-step information gathering without manual browser interaction.

Can I enrich existing CSV or JSON records with web-discovered company data?

Existing CSV or JSON records can be enriched by ingesting data files to automatically append web-discovered information like revenue, leadership, or entity details. This structured enrichment process adds depth to your original dataset.

What's the best way to discover specific companies or entities based on complex criteria?

Entity discovery is handled by the FindAll workflow, which performs web-scale discovery of startups, companies, or specific entities based on complex criteria. It automates the search process to find matching organizations across the web.

Do I need an API key to run asynchronous research jobs?

An API key is required to interface with the Parallel web-native research stack and execute asynchronous research jobs. You also need the parallel-cli binary installed to run the commands and manage processor tiers.

How does asynchronous job management work for deep research tasks?

Asynchronous job management allows deep research tasks to execute in configurable processor tiers for varying levels of depth. It supports context-aware follow-up queries, enabling complex information gathering without blocking terminal execution.

Can I output deep research results in structured JSON format?

Structured JSON output is natively supported for deep research reports and data enrichment tasks. This format ensures the results are machine-readable and ready for downstream processing or integration into other data pipelines.