general-patent-search

Search Google Patents for patent metadata by keyword, assignee, or chemical name.

144|21|Updated Jan 8, 2026
One-click install
npx skills add https://github.com/learningmatter-mit/AtomisticSkills --skill general-patent-search
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: general-patent-search
Source: https://github.com/learningmatter-mit/AtomisticSkills/tree/main/.agents/skills/general-patent-search
Command: npx skills add https://github.com/learningmatter-mit/AtomisticSkills --skill general-patent-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, beautifulsoup4, and includes scripts (resource) and references (resource) components.

What problem does it solve?

It helps researchers and teams quickly assess novelty and freedom-to-operate by retrieving relevant patent information for a material, chemical, or technology using open, free data sources.

Core Features & Use Cases

  • Keyword and assignee search: Finds patent titles, assignees, priority dates, and snippets using Google Patents scraping.
  • Material/chemical-focused queries: Supports searching by chemical names and related technology terms with text-based matching.
  • IP landscape discovery: Useful for early-stage research planning, competitive analysis, and IP screening for new materials or formulations.

Quick Start

Run the skill’s query script with your search string to return the top matching patent records: python .agents/skills/general-patent-search/scripts/query_google_patents.py "tetrafluoropropene OR HFO-1234yf" --limit 5.

Frequently Asked Questions about general-patent-search

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

FAQPage Schema
How do I search Google Patents for a chemical name or keyword?

You can search Google Patents by running the query script with your target chemical name or keyword string. This web-scraping approach retrieves publication metadata including titles, assignees, priority dates, and snippets to map your IP landscape.

Can I use a Python script for freedom-to-operate patent research?

Yes, you can perform freedom-to-operate patent research using a Python web-scraping script to query Google Patents. It retrieves relevant publication metadata to help assess novelty and map the intellectual-property landscape for new materials.

What patent metadata does a Google Patents keyword query return?

A Google Patents keyword query returns publication metadata including the patent title, assignee, priority date, and text snippet. This information supports early-stage research planning, competitive analysis, and IP screening across chemistry and materials.

Do I need a Conda environment to run a patent search script?

Yes, you need the base-agent Conda environment to run this patent search script. The Python web-scraping query endpoint relies on this specific environment setup to function correctly and retrieve patent publication data.

How do I limit the number of patent search results for an IP landscape?

You can limit patent search results by passing a configurable limit parameter to the query script. Running the command with a specified limit restricts the returned patent records to a manageable number for IP landscape discovery.

What is the best way to map an intellectual-property landscape for new materials?

The best way to map an intellectual-property landscape for new materials is using a Python web-scraping script to query Google Patents. This approach quickly retrieves relevant patent titles and assignees for early-stage research planning and IP screening.