Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Parallel Web Intelligence Toolkit

Routes requests to Parallel CLI for web search, URL extraction, deep research, data enrichment, entity discovery, and scheduled monitoring.

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

What it does

A single routing skill that picks the right parallel-cli capability for the request:

  • Web Search — everyday lookups and bounded research questions
  • Web Extract — pull content from a known URL, including PDFs and JS-rendered pages
  • Data Enrichment — add web-sourced fields to a supplied list of companies, people, or products
  • Deep Research — exhaustive multi-source reports, reserved for explicitly comprehensive asks
  • FindAll — discover the entity set itself from natural-language criteria
  • Monitor — recurring change tracking with persistent external state

For technical or scientific queries it prioritizes peer-reviewed papers, preprints (arXiv, bioRxiv, medRxiv), and institutional sources (NIH, WHO, NASA, NIST) over blogs and news, citing author, year, and DOI. Safety guidance is unusually strong: web results are treated as untrusted data, user text is passed as quoted args or stdin, JSON flags are serialized rather than concatenated, task IDs must match CLI prefixes (trun_, tgrp_, findall_, mon_), the API key is never printed, and polling is capped at three rounds.

Who it's for

  • Analysts and researchers who need current, citable web evidence
  • Scientists and grad students who want literature-first sourcing with DOIs
  • Sales/data teams enriching lead or company lists at scale
  • Teams that must watch competitor pages or regulatory docs on a schedule

Examples

  1. "Summarize solid-state battery advances since 2024, favor peer-reviewed work" → Web Search with academic-source priority and DOI links.
  2. "Fill in latest funding round, HQ, and headcount for the 200 startups in this CSV" → one Data Enrichment batch instead of a search loop.
  3. "Tell me weekly when this competitor's pricing page changes" → a Monitor task; a one-off check falls back to Web Extract.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. 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 Claude 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.

  1. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/parallel-web ~/.claude/skills/
  3. Confirm the references/ files (web-search.md, deep-research.md, monitor.md, etc.) came along — the skill depends on them.
  4. Install the CLI with uv: uv tool install "parallel-web-tools[cli]==0.7.1" (install uv first if needed).
  5. Verify with parallel-cli --version; if not found, add ~/.local/bin to your PATH.
  6. Get an API key at https://platform.parallel.ai, then run parallel-cli login (use parallel-cli login --device on headless/CI/SSH), or export PARALLEL_API_KEY.
  7. Check credentials with parallel-cli auth.
  8. Restart Claude Code and try: "use the parallel-web skill to find the latest research on ...".
View source on GitHub ↗License: MIT