parallel-cli

Orchestrate vendor-backed web search, extraction, and research tasks from the terminal.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/adm-humanerd/drewgent --skill parallel-cli-adm-humanerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/adm-humanerd/drewgent/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/adm-humanerd/drewgent --skill parallel-cli-adm-humanerd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Parallel CLI provides a vendor-specific workflow for terminal-based web search, extraction, deep research, enrichment, and monitoring, enabling structured outputs and async task orchestration without leaving the command line.

Core Features & Use Cases

  • JSON-first outputs: Use --json to get machine-readable results for automation.
  • Non-interactive flows: Designed for scripts and background tasks with --no-wait, status, and poll.
  • Async long-running jobs: Launch tasks and poll for completion, enabling multi-step research pipelines.
  • Contextual enrichment and discovery: Supports FindAll-like entity discovery, enrichment planning, and monitor workflows.
  • Use cases include fast lookups, data enrichment pipelines, and monitoring tasks for ongoing web sources.

Quick Start

Run parallel-cli search 'AI coding agents' --json to perform a fast, structured lookup.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I run web search tasks from the terminal non-interactively?

Web search tasks can run non-interactively from the terminal using a CLI tool that supports background execution. You use flags like --no-wait to launch jobs and then poll for completion, enabling structured automation without manual intervention.

How do I get JSON output from a command line web search tool?

Command line web search tools can return JSON output by using the --json flag. This provides machine-readable structured results suitable for data enrichment pipelines, automation scripts, and downstream programmatic processing.

Can I orchestrate async long-running research jobs in a CLI workflow?

Async long-running research jobs can be orchestrated in a CLI workflow using status and poll commands. You launch a task without waiting, check its status periodically, and retrieve structured results upon completion for multi-step pipelines.

What is the best way to monitor web sources for changes via a terminal script?

Monitoring web sources via terminal scripts is best handled by a non-interactive CLI tool that supports async workflows. It can periodically execute search and extraction tasks, returning structured JSON data for ongoing tracking.

Does parallel-cli support contextual entity discovery and data enrichment?

Parallel-cli supports contextual entity discovery and data enrichment through FindAll-like workflows. It enables users to plan enrichment steps and execute them as async background tasks with structured JSON outputs.

How do I resume or follow up on a previous async research task?

You can resume or follow up on a previous async research task by using the --previous-interaction-id flag. This allows you to reference past job contexts for continuous multi-step research and enrichment without restarting.