parallel-cli

Automates web search, extraction, and deep research via Parallel CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/AlexKoncept/omnia-hub --skill parallel-cli-alexkoncept
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/AlexKoncept/omnia-hub/tree/main/HERMES/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/AlexKoncept/omnia-hub --skill parallel-cli-alexkoncept

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Hermes agents often require scalable, vendor-backed web search, extraction, and deep research workflows that can run non-interactively and return structured results. This skill provides the Parallel CLI to orchestrate search, extract, research, enrichment, FindAll, and monitor tasks within Hermes workflows.

Core Features & Use Cases

  • JSON-first output for machine consumption across automation pipelines.
  • Async long-running jobs with status/poll and context chaining via previous-interaction-id.
  • Unified workflow: search, extract, deep research, enrichment, FindAll, and monitoring in a single CLI, enabling end-to-end research pipelines.

Quick Start

Run a quick web search with the Parallel CLI and return results in JSON.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I automate async web search and return structured JSON results?

To automate web research workflows, you need non-interactive execution with structured JSON outputs. This skill uses the Parallel CLI to orchestrate Hermes search, extraction, and monitoring tasks, returning machine-readable JSON via the --json flag for seamless pipeline integration.

What is context chaining and how does it work for deep research workflows?

Context chaining links sequential research interactions using a previous interaction ID. This skill supports context-aware follow-ups via the --previous-interaction-id flag, enabling continuous deep research, extraction, and enrichment by passing prior query context to subsequent async polling requests.

Can I run long-running extraction and monitoring jobs non-interactively?

Long-running extraction and monitoring jobs can run non-interactively using status and polling mechanisms. The Parallel CLI orchestrates these async tasks within Hermes workflows, allowing agents to submit jobs and poll for structured JSON results without blocking interactive sessions.

Does the Parallel CLI require JSON output for agent-centric research tasks?

JSON output is required for agent-centric research tasks using the Parallel CLI. The --json flag enforces structured machine-readable results, ensuring that search, FindAll, and enrichment data can be consumed automatically by downstream Hermes automation pipelines.

What's the best way to perform web data enrichment and FindAll tasks asynchronously?

The best way to perform asynchronous web enrichment and FindAll tasks is using a unified CLI that supports async execution and JSON outputs. This skill coordinates Hermes workflows via the Parallel CLI, handling search, extraction, enrichment, and FindAll operations in a single non-interactive pipeline.

Why does my async research pipeline need status and poll mechanisms?

Async research pipelines need status and poll mechanisms to handle long-running web search and extraction jobs without timing out. The Parallel CLI implements status polling to check background job progress, ensuring structured JSON results are retrieved successfully once deep research or monitoring tasks complete.