parallel-cli

Automate web search, extraction, and deep research with structured JSON outputs.

4|Updated May 18, 2026

Search Tags:#monitoring #web research #data enrichment #json output #deep research #entity discovery #web extraction

Ready to run

npx skills add https://github.com/ZardLi1115/zedclaw --skill parallel-cli-zardli1115

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/ZardLi1115/zedclaw/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill parallel-cli-zardli1115

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

parallel-cli helps you turn ambiguous web research questions into structured, citation-ready results without brittle copy-paste workflows, especially when you need multi-step extraction, enrichment, or ongoing monitoring.

Core Features & Use Cases

Agent-ready web research: Launch deep research tasks and then poll for status and results when work takes longer than a single response cycle.
Structured search and extraction: Perform web search and content extraction that returns machine-readable data (preferably JSON) for reliable downstream synthesis.
Enrichment and entity discovery: Enrich tabular inputs and discover datasets via FindAll for later filtering and reuse in code or planning.

Quick Start

Ask your agent to run a non-interactive Parallel deep research job for your question and return JSON output with sources as 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 deep web research and get structured JSON output?▼

Deep web research is automated using non-interactive jobs that return machine-readable JSON outputs with strict citation handling. This approach supports multi-step extraction, enrichment, and recurring monitoring for agent workflows.

Can I enrich tabular data and discover entities from web searches?▼

Yes, you can enrich tabular inputs and discover datasets via entity discovery. This process returns structured results for reliable downstream synthesis, filtering, and reuse in code or planning contexts.

What is the best way to monitor recurring changes on web sources?▼

The best way to monitor recurring changes is by using async job control with no-wait execution and status polling. This pattern detects ongoing changes rather than performing single one-shot lookups, returning structured data with citations.

Does parallel-cli work with long-running agent workflows?▼

Yes, it is designed for long-running agent workflows. You launch a deep research task and then poll for status and results when the work takes longer than a single response cycle, ensuring reliable execution.

How do I handle citations when extracting web content to JSON?▼

Citations are handled strictly based on returned CLI URLs within the JSON output. The structured search and extraction process ensures all machine-readable data includes source URLs for reliable downstream synthesis and verification.

When should I not use async web research jobs?▼

You should avoid async web research jobs for simple one-shot lookups. This approach requires JSON-first, non-interactive execution patterns and is built for multi-step extraction, enrichment, and ongoing monitoring rather than quick single answers.