parallel-cli

Execute web research and entity discovery jobs via the Parallel CLI.

Updated Jun 17, 2026
One-click install
npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill parallel-cli-cxnaive
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill parallel-cli-cxnaive

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 multi-step, asynchronous research jobs with support for different processor tiers.
  • Data Enrichment: Infers and adds structured data columns to existing datasets based on web research.
  • Entity Discovery: Performs web-scale FindAll operations to identify and extract lists of entities based on specific criteria.
  • Use Case: Use this skill to research a list of competitor companies from a CSV file, automatically enriching the data with their CEOs and annual revenue.

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 entity discovery for large datasets?

Automated web research and entity discovery is executed through asynchronous job management, allowing you to process complex queries and extract structured JSON data across multiple steps. This handles multi-step information gathering that exceeds simple one-shot search capabilities.

What is the best way to enrich a CSV file with company data like CEO and revenue?

CSV data enrichment is performed by inferring and adding structured columns based on web research, automatically appending details like a company's CEO or annual revenue. It processes existing datasets to extract and append relevant web-scale entity information.

Do I need a specific environment to run asynchronous web research jobs?

Running asynchronous web research jobs requires an authenticated Parallel account and the parallel-cli binary installed on the host system. These prerequisites enable context-aware follow-up queries and structured JSON output generation.

Can I discover lists of entities based on specific criteria across the web?

Web-scale entity discovery is supported through FindAll operations that identify and extract lists of entities matching specific criteria. This allows you to gather comprehensive datasets by querying across the web for matching items.

How does context-aware follow-up querying work for complex information gathering?

Context-aware follow-up queries build on previous asynchronous research job results, enabling multi-step information gathering without losing prior context. This allows for deep, structured JSON data discovery across different processor tiers.

What are the limitations of using CLI for automated data enrichment?

CLI-based automated data enrichment is limited to environments where the parallel-cli binary is installed and an authenticated Parallel account is active. Without these host system prerequisites, asynchronous job management and web research execution cannot operate.