parallel-cli

Run parallel web search and extraction workflows with JSON output.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/thisismynewfmail-ui/Monika-agent --skill parallel-cli-thisismynewfmail-ui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/thisismynewfmail-ui/Monika-agent/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/thisismynewfmail-ui/Monika-agent --skill parallel-cli-thisismynewfmail-ui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This vendor skill provides a dedicated, CLI-based workflow for performing parallel web search, extraction, deep research, enrichment, FindAll-style discovery, and monitoring using a vendor-specific stack, enabling JSON-first, non-interactive automation.

Core Features & Use Cases

  • JSON output via --json for structured results.
  • Non-interactive command execution and explicit flow control with --no-wait, status, and poll.
  • Context chaining with --previous-interaction-id for multi-turn tasks.
  • Unified workflow covering search, extract, research, enrich, findall-style discovery, and monitoring in agent pipelines.

Quick Start

Run a search with --json to start a JSON-formatted, non-interactive knowledge lookup.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I get JSON output from parallel web searches for automated enrichment pipelines?

Parallel web search for automated enrichment pipelines can return JSON output by using the --json flag, ensuring structured results for non-interactive agent workflows. This enforces a JSON-first output format suitable for automation.

Can I run non-interactive deep research queries without waiting for the process to finish?

Non-interactive deep research queries can run without waiting by using the --no-wait flag. You can then check the execution status and poll for results asynchronously within your agent pipelines.

What is context chaining and how does it work for multi-turn web research?

Context chaining for multi-turn web research links sequential tasks via the --previous-interaction-id flag. This passes context between commands, enabling continuous discovery and extraction workflows across multiple steps.

Does this CLI tool support FindAll-style discovery and monitoring for long-running workflows?

The CLI tool supports FindAll-style discovery and monitoring for long-running workflows through its unified command structure. It handles both one-shot lookups and continuous automated agent pipelines.

What's the best way to structure async web search tasks for data extraction?

The best way to structure async web search tasks for data extraction is combining --json for structured output with async control flags like status and poll. This enables non-interactive execution and explicit flow control.

Why does my automated agent pipeline need a non-interactive CLI for web research?

Automated agent pipelines need a non-interactive CLI for web research to enforce JSON-first output and enable async control. This prevents blocking execution during long-running enrichment and deep research workflows.