Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.parallel.ai/llms.txt

Use this file to discover all available pages before exploring further.

For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending .md to its URL or sending Accept: text/markdown.
Agent Skills let you add Parallel’s capabilities to AI coding agents like Cursor, Cline, GitHub Copilot, Windsurf, and 30+ other tools via the Agent Skills CLI. Skills are lightweight, declarative integrations that give your agent access to live web data without writing any code.
View the complete repository for this integration here

​
Available Skills

SkillDescription
parallel-web-searchFast web search for current events, fact-checking, and lookups
parallel-web-extractExtract clean content from URLs, including JavaScript-heavy sites and PDFs
parallel-deep-researchExhaustive, multi-source research reports with configurable depth
parallel-data-enrichmentBulk enrichment of companies, people, or products with web-sourced data

​
Prerequisites

1

Install the Parallel CLI

Install the Parallel CLI via pipx:
pipx install "parallel-web-tools[cli]" && pipx ensurepath
See the CLI docs for uv, Homebrew, npm, and other installation methods.
2

Authenticate

parallel-cli login
# or
export PARALLEL_API_KEY="your_api_key"
See the CLI docs for other authentication methods.

​
Installation

Install all skills globally so they’re available in every project: 
npx skills add parallel-web/parallel-agent-skills --all --global
Or install a specific skill: 
npx skills add parallel-web/parallel-agent-skills --skill parallel-web-search
To see all available skills before installing: 
npx skills add parallel-web/parallel-agent-skills --list

​
Usage

Once installed, skills are automatically available to your agent. No additional configuration is needed — your agent will use them when appropriate based on your prompts.
  • Web search is used by default for any research, lookup, or question needing current information
  • Extract is used when your agent needs to fetch content from a specific URL
  • Deep research is triggered when you explicitly request exhaustive or comprehensive research
  • Data enrichment is used for bulk enrichment of lists of companies, people, or products

​
Supported Agents

Agent Skills work with any tool that supports the Vercel Skills CLI, including: For Claude Code, you can also use the Claude Code Plugin Marketplace integration.

​
Learn More

For detailed skill documentation, configuration options, and local development instructions, see the parallel-agent-skills repository on GitHub.