skills.rest
jcrabapple
jcrabappleCOMMUNITY
Explore all skills by this author →
GitHub

parallel-cli

Runs Parallel CLI workflows for web search, extraction, deep research, enrichment, and monitoring.

10|2|Updated May 6, 2026
Search Tags:#monitoring#cli#web search#data enrichment#deep research#entity discovery#parallel-cli
One-click install
npx skills add https://github.com/jcrabapple/hermes-skills --skill parallel-cli-jcrabapple
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parallel-cli
Source: https://github.com/jcrabapple/hermes-skills/tree/main/parallel-cli
Command: npx skills add https://github.com/jcrabapple/hermes-skills --skill parallel-cli-jcrabapple

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It gives agents a terminal-native way to use Parallel's vendor stack for web search, content extraction, deep research, data enrichment, entity discovery, and change monitoring with JSON output and non-interactive async jobs. ## Core Features & Use Cases - Search and Extraction: Run structured web searches with domain and date filters, and extract clean markdown from URLs with optional objectives. - Async Deep Research: Launch long-running research jobs with --no-wait, then poll status and chain follow-ups via --previous-interaction-id. - Enrichment, FindAll, and Monitoring: Enrich CSV/JSON tables with web-inferred columns, discover entity datasets at web scale, and track pages over time. - Use Case: Ask the agent to compare leading AI coding agents by pricing and enterprise controls; it launches an async research run, polls for completion, and summarizes the report with citations from returned sources only. ## Quick Start Ask the agent to use parallel-cli to research a topic with JSON output and cite only the returned 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 a deep research task with parallel-cli?▼

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

How to 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 state with parallel-cli auth before running commands.

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.

Can parallel-cli enrich CSV files with web data?▼

Yes, parallel-cli enrich run accepts a CSV source with column definitions and an intent describing the fields to infer, then writes an enriched output file. Validate the output file before reporting success.

Why does parallel-cli login fail in my terminal?▼

Login may require browser or PTY interaction, so run it with pty=true or switch to parallel-cli login --device for headless flows. Also confirm the CLI is on PATH and check exit code 3, which indicates an auth error.

Related Skills

Explore More Education & Research Skills→
l8yh1l8yh1

ai-sdr

Identify B2B leads by defining ICPs and generating CRM-ready spreadsheets.

Community
Advanced
taizen-aitaizen-ai
8

discovery-prep

Generate unified discovery preparation briefs from CRM, calendar, and research data.

Official
Advanced
weebcoder101weebcoder101
3

deep-research

Automate comprehensive web research with parallel searches and synthesized reports.

Community
Advanced
afel6afel6

duckduckgo-search

Search DuckDuckGo for web, news, image, and video results without an API key.

Community
Intermediate