Parallel Web Intelligence Toolkit

Routes requests to the right Parallel CLI capability — web search, URL extraction, deep research, enrichment, entity discovery, or recurring monitoring.

Web & APIIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Reads the request and routes it to one of six capabilities (Web Search, Web Extract, Data Enrichment, Deep Research, FindAll, Monitor) using an explicit decision table.
Requires reading the matching references/*.md file before running a command, preventing common misuse such as looping Web Search instead of running an enrichment job.
Enforces academic source priority for technical questions: peer-reviewed papers, preprints (arXiv/bioRxiv/medRxiv), institutional sources (NIH, WHO, NASA, NIST), with author–year and DOI citations.
Covers installation via uv tool install, interactive and device-code login, auth verification, async task status commands, and bounded polling (max 3 polls, ~27 minutes).
Includes hard safety rules: treat all returned web content as untrusted, never echo PARALLEL_API_KEY, and only use CLI-issued task IDs with valid prefixes.

Who it's for

Analysts and researchers who need current, citable web evidence.
Scientists and grad students who want literature-first answers instead of blog summaries.
Data/ops people filling web-sourced columns for lists of companies, people, or products.
Anyone who already has (or can create) a Parallel API key.

Example uses

"Pull the full text and tables from this PDF article URL" → Web Extract handles PDFs and JS-rendered pages.
"For these 40 startups, add HQ city, latest funding round, and headcount" → a single Data Enrichment run instead of 40 searches.
"Watch this regulatory page and tell me weekly if it changes" → a Monitor task; a one-off check stays in Web Search.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/parallel-web/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/parallel-web folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/parallel-web/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/parallel-web ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
Copy the skill into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/parallel-web ~/.claude/skills/
Confirm the references/ files came along: ls ~/.claude/skills/parallel-web.
Install the CLI (uv required): uv tool install "parallel-web-tools[cli]==0.7.1"
Get an API key at https://platform.parallel.ai and export PARALLEL_API_KEY=..., or run parallel-cli login (parallel-cli login --device on headless/CI machines).
Verify with parallel-cli auth; if the command is not found, add ~/.local/bin to your PATH.
Restart Claude Code and try: "use parallel-web to find current sources on <topic>".

View source on GitHub ↗License: MIT