parallel-cli

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

Updated May 18, 2026
One-click install
npx skills add https://github.com/ossoolli/Nexum-Core --skill parallel-cli-ossoolli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/ossoolli/Nexum-Core/tree/main/optional-skills/research/parallel-cli
Command: npx skills add https://github.com/ossoolli/Nexum-Core --skill parallel-cli-ossoolli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agents often need structured web research, URL extraction, entity discovery, and ongoing change monitoring beyond simple one-shot lookups. This Skill provides terminal-native access to Parallel's vendor stack with JSON output and non-interactive, async workflows. ## Core Features & Use Cases - Web Search & Extraction: Run structured searches with domain and date filters, and extract clean markdown content from URLs with optional objectives. - Deep Research & Enrichment: Launch async multi-step research jobs with processor tiers, poll for results, and enrich CSV/JSON datasets with web-inferred columns. - FindAll & Monitoring: Discover web-scale entity sets and create monitors for recurring change detection. - Use Case: Launch an async deep research job comparing AI coding agents with --no-wait, continue other work, then poll for the final cited report. ## Quick Start Use the parallel-cli skill to search for the latest Anthropic funding news and return JSON results with citations.

Frequently Asked Questions about parallel-cli

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

FAQPage Schema
How do I run a web search with parallel-cli?▼

Run parallel-cli search followed by your query and the --json flag for structured output. You can narrow results with --include-domains, --exclude-domains, --after-date, and --max-results flags.

How do I run async deep research jobs with parallel-cli?▼

Launch with parallel-cli research run plus --no-wait and --json to get a run ID immediately. Later check progress with research status or research poll using that ID, choosing processor tiers from lite to ultra.

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

Use parallel-cli when the user explicitly requests Parallel or needs vendor-specific features like enrichment, FindAll entity discovery, or monitoring. For quick one-off lookups, native web_search and web_extract tools are preferred.

How do I authenticate parallel-cli in headless or CI environments?▼

Set the PARALLEL_API_KEY environment variable, or run parallel-cli login --device for headless and SSH sessions. Verify the current auth state anytime with parallel-cli auth.

What do parallel-cli exit codes mean?▼

Exit code 0 means success, 2 indicates bad input, 3 an auth error, 4 an API error, and 5 a timeout. For auth errors, check parallel-cli auth and confirm your API key or login status.