patent-search

Query patent databases via PatentsView and BigQuery for prior art and competitive patents.

167|28|Updated Nov 15, 2025
One-click install
npx skills add https://github.com/RobThePCGuy/Claude-Patent-Creator --skill patent-search
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: patent-search
Source: https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/patent-search
Command: npx skills add https://github.com/RobThePCGuy/Claude-Patent-Creator --skill patent-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-cloud-bigquery, db-dtypes, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Efficiently searching patent databases for prior art, competitive intelligence, or technology landscapes requires access to vast datasets and specialized tools. This Skill offers two powerful methods for comprehensive patent searching, streamlining your research.

Core Features & Use Cases

  • BigQuery Global Search: Access 76M+ worldwide patents for quick keyword and CPC classification searches.
  • PatentsView US Metadata: Detailed US patent metadata including inventors, assignees, classifications, and citation analysis.
  • Advanced Query Construction: Build complex queries with Boolean operators, date ranges, and exact field matching.
  • Use Case: A user needs to find all US patents by a specific inventor related to a particular technology, including their citation network. This skill can leverage PatentsView for this detailed analysis, providing insights beyond simple keyword searches.

Quick Start

Search for patents related to 'voice biometric authentication' using BigQuery and show me the top 5 results.

Frequently Asked Questions about patent-search

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

FAQPage Schema
How do I search for prior art patents across global databases?

Patent prior art searches can be performed using BigQuery to access 76M+ worldwide patents with keyword and CPC classification filtering, or PatentsView for detailed US patent metadata including inventors, assignees, and citations. Both methods support complex boolean queries and date ranges to narrow results efficiently.

Can I search patents by inventor or assignee name?

Yes, both BigQuery and PatentsView support targeted searches by inventor and assignee. PatentsView provides detailed US patent metadata including inventor and assignee information, enabling you to locate all patents associated with specific individuals or organizations and explore their citation networks.

What's the best way to conduct a freedom-to-operate analysis?

Freedom-to-operate analyses use patent searches to identify competing patents and prior art. This Skill enables structured queries with CPC filtering, date ranges, and citation-network exploration across 76M+ patents, helping you assess patent landscapes and potential infringement risks systematically.

How do I build complex patent queries with boolean operators?

Complex boolean queries are constructed using Python helper scripts that support field-specific matching, exact phrases, and logical operators. The Skill integrates with BigQuery and PatentsView APIs to execute these queries while respecting rate limits (45 requests per minute) and handling pagination.

Does patent search work with CPC classification filtering?

Yes, CPC classification filtering is a core feature available through BigQuery for global patent searches. The Skill supports structured queries using CPC codes to refine results, enabling you to focus on specific technology categories and narrow patent landscapes by classification.

What limitations should I know before conducting large-scale patent searches?

Patent searches are rate-limited to 45 requests per minute through PatentsView and BigQuery APIs. BigQuery covers 76M+ worldwide patents while PatentsView provides richer US patent metadata; choose based on geographic scope and detail requirements. Results require pagination handling for large datasets.