parallel-cli

Automate web search and deep-research workflows with JSON outputs via Parallel CLI.

3|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/ever-oli/io --skill parallel-cli-ever-oli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/ever-oli/io/tree/main/skills/research/parallel-cli
Command: npx skills add https://github.com/ever-oli/io --skill parallel-cli-ever-oli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

parallel-cli provides a vendor-backed, JSON-first CLI workflow for agent-native web search, extraction, deep research, enrichment, and monitoring, enabling structured results and automation in non-interactive contexts.

Core Features & Use Cases

  • JSON-first, non-interactive workflows for web search, extraction, and research using a vendor CLI
  • Support for enrichment, entity discovery (FindAll-like), and ongoing monitoring
  • Works alongside IO native tools when a Parallel-specific workflow is requested, with clear guidance on when to use each

Quick Start

Run parallel-cli with --json to start a non-interactive research task and inspect the structured results.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I get structured JSON output from automated web search workflows?

Structured JSON output from automated web search workflows is achieved by running parallel-cli with the --json flag. This provides deterministic results for non-interactive agent tasks without requiring manual parsing.

What is asynchronous web research and how does it work in non-interactive environments?

Asynchronous web research in non-interactive environments works by using the --no-wait option to start tasks like research run or enrich run. This allows automated workflows to continue executing while complex search operations process in the background.

How do I automate entity discovery and data enrichment for web monitoring?

Automate entity discovery and data enrichment using the parallel-cli findall run and enrich run commands. These tools execute asynchronous workflows to identify entities and append structured data for ongoing monitoring tasks.

Can I use parallel-cli for web extraction without user interaction?

Yes, parallel-cli is designed specifically for non-interactive web extraction. By using the extract command with the --json flag, it returns structured data outputs suitable for automated agent-based tasks and backend workflows.

Do I need to install parallel-web-tools to run deep research workflows?

Yes, you must install the parallel-web-tools package to run deep research workflows. The parallel-cli acts as the vendor interface, but the underlying tools are required to execute search, extract, and research commands.