parallel-cli

Runs web search, deep research, enrichment, and monitoring through the Parallel CLI.

16|Updated Sep 22, 2026
One-click install
npx skills add https://github.com/igniteenow/robo --skill parallel-cli-igniteenow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/igniteenow/robo/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/igniteenow/robo --skill parallel-cli-igniteenow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It gives agents terminal-native access to Parallel's web search, extraction, deep research, enrichment, entity discovery, and monitoring APIs when built-in search tools are not sufficient. ## Core Features & Use Cases - Structured Web Search & Extraction: Run searches with domain filters, recency filters, and JSON output, or extract clean markdown from URLs with objectives. - Async Deep Research: Launch multi-step research jobs with processor tiers, poll for completion, and chain follow-up questions via previous interaction IDs. - Enrichment, FindAll & Monitoring: Enrich CSV/JSON tables with web-researched columns, discover entity datasets at web scale, and track pages for changes over time. - Use Case: Ask the agent to compare leading AI coding agents by pricing and enterprise controls; it launches an async research job, polls for the result, and summarizes the report with citations. ## Quick Start Ask the agent to research a topic using Parallel, for example: run a deep research job comparing AI coding agents and summarize the findings with cited sources.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I run deep research from the command line with parallel-cli?▼

Run parallel-cli research run with your question, a processor tier like core or ultra, and --json for structured output. For long jobs, add --no-wait to launch asynchronously, then use research status or research poll with the returned run ID.

How to enrich a CSV file with web data using Parallel?▼

Use parallel-cli enrich run with --source-type csv, your source and target files, source column definitions as a JSON array, and an intent describing the columns to find. Poll the task group ID for completion and validate the output file afterward.

When should I use parallel-cli instead of built-in web search?▼

Prefer parallel-cli when the user explicitly requests Parallel or needs vendor-specific capabilities like enrichment, FindAll entity discovery, async deep research, or monitoring. For quick one-off lookups, native web_search and web_extract tools are sufficient.

Does parallel-cli work in headless or CI environments?▼

Yes, parallel-cli supports headless authentication via parallel-cli login --device or by setting the PARALLEL_API_KEY environment variable. Verify the current auth state at any time with parallel-cli auth.

Why does parallel-cli return an auth error?▼

Auth errors (exit code 3) occur when no valid credentials are configured. Check parallel-cli auth, confirm PARALLEL_API_KEY is set, or run parallel-cli login; interactive login may require a PTY or browser session.

Is parallel-cli free to use?▼

Parallel is a paid service with a free tier, not a fully free local tool. Usage beyond the free tier requires a paid account, and most commands require authentication with a Parallel API key.