parallel-cli

Coordinate web search, extraction, and research tasks via a unified CLI.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill parallel-cli-anandaanugrahhandyanto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/AnandaAnugrahHandyanto/savarez_agent/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill parallel-cli-anandaanugrahhandyanto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Optional vendor skill for Parallel CLI enables agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring with JSON output and non-interactive flows.

Core Features & Use Cases

  • Unified CLI workflow for web search, extraction, deep research, enrichment, FindAll, and monitoring.
  • JSON-first, non-interactive execution with async long-running jobs via --no-wait, status, and poll; context chaining with --previous-interaction-id.
  • Designed for agents requiring structured outputs and cross-task orchestration in research-heavy sessions.

Quick Start

Run a one-shot web search with parallel-cli search "AI coding agents" --json to get 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 run web search and extraction tasks with JSON output for agent workflows?

Run web search and extraction tasks with JSON output using a unified CLI workflow that supports non-interactive execution. Use commands like parallel-cli search "query" --json to get structured results directly for agent processing.

Can I execute long-running deep research jobs asynchronously without blocking my terminal?

Yes, you can execute long-running deep research jobs asynchronously using the --no-wait flag. Monitor progress later by polling the job status to retrieve results without keeping the terminal occupied.

How does context chaining work across multiple enrichment and search tasks in a CLI session?

Context chaining connects enrichment and search tasks using the --previous-interaction-id flag. This passes context between sequential CLI operations, maintaining session state for cross-task orchestration in research-heavy workflows.

What is the best way to monitor async research jobs and poll for completion status?

Monitor async research jobs by using the status and poll commands within the CLI workflow. These commands track the execution state of long-running tasks initiated with --no-wait, returning current status updates as structured JSON.

Does the parallel-cli workflow support non-interactive mode for automated web search and FindAll operations?

Yes, the parallel-cli workflow supports non-interactive mode for automated web search and FindAll operations. It provides JSON-first outputs designed specifically for agent-native automation without requiring interactive input.

When should I use the monitor task instead of the poll command for deep research workflows?

Use the monitor task for continuous observation of integrated research workflows, while the poll command checks the status of specific asynchronous jobs. Both return JSON outputs to track deep research progress without blocking execution.