parallel-cli

Run agent-native web research and extraction tasks via Parallel CLI.

Updated May 26, 2026
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill parallel-cli-ruiyangruiyi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill parallel-cli-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you get high-quality web research outputs—search results, extracted content, deep multi-step findings, and enriched structured data—without manually juggling separate browsing, scraping, and formatting steps.

Core Features & Use Cases

  • Agent-native web research: Run deep research workflows that synthesize findings across sources with structured outputs suitable for downstream reasoning.
  • Web extraction & enrichment: Extract clean content from URLs and enrich entities/rows with additional attributes from the web.
  • FindAll & monitoring workflows: Discover large sets of entities and track changes over time with monitor-style workflows.

Quick Start

Ask the agent to run parallel-cli to research your question in JSON format and return a structured report with citations to the Parallel CLI output URLs.

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 in a structured format?

You can automate web research and data extraction by running CLI commands that return JSON-first structured results, supporting both one-shot and asynchronous long-running tasks for reliable outputs without manual browsing.

What is the best way to enrich entities with additional attributes from the web?

The best way to enrich entities is using web extraction workflows that augment your rows with additional attributes from the web, returning JSON-first structured data outputs suitable for immediate downstream analysis.

Can I run async long-running web monitoring tasks and poll for results later?

Yes, async long-running web monitoring tasks are supported. You can use options like --no-wait and status/poll to track changes over time, discovering large sets of entities and retrieving results when ready.

Does web research support context chaining for follow-up iterations?

Yes, web research supports context chaining for follow-up iterations using the --previous-interaction-id option. This allows you to build upon previous queries while applying domain and date constraints for reliable structured results.

How do I discover large sets of entities and track changes over time?

You can discover large sets of entities and track changes over time using FindAll and monitoring workflows. These monitor-style workflows run via CLI to ensure reliable structured results with domain and date constraints.