patent-search
关于
This Claude skill enables patent searching across 76M+ patents via BigQuery for fast, zero-setup global searches, or through the PatentsView API for detailed US patent metadata. Developers can quickly test it using the provided Python script with pre-configured credentials. Choose BigQuery for worldwide coverage or PatentsView for rich US patent details like inventors and citations.
快速安装
Claude Code
推荐/plugin add https://github.com/RobThePCGuy/Claude-Patent-Creatorgit clone https://github.com/RobThePCGuy/Claude-Patent-Creator.git ~/.claude/skills/patent-search在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Patent Search Skill
Two powerful patent search methods:
- BigQuery Search (Recommended) - 76M+ worldwide patents, zero local storage
- PatentsView API - Detailed US patent metadata (inventors, assignees, classifications, citations)
FOR CLAUDE: All files and dependencies installed.
- Go directly to Quick Test section
- Script at:
.claude/skills/patent-search/bigquery_search.py - Run from skill directory
- Windows: Use cmd syntax (dir, set, &&)
Quick Test
# Windows
cd ".claude\skills\patent-search"
set GOOGLE_APPLICATION_CREDENTIALS=%APPDATA%\\gcloud\\application_default_credentials.json
python bigquery_search.py search "voice biometric" 5
# Linux/macOS
cd .claude/skills/patent-search
export GOOGLE_APPLICATION_CREDENTIALS="$HOME/.config/gcloud/application_default_credentials.json"
python bigquery_search.py search "voice biometric" 5
Expected: 5 patent results in ~4 seconds
Quick Start
BigQuery Search
# Keyword search (2-3 keywords for best results)
python bigquery_search.py search "voice biometric authentication" 20
# Get specific patent (hyphenated format: US-XXXXXXX-XX)
python bigquery_search.py get US-12424224-B2
# CPC classification search
python bigquery_search.py cpc G10L 15
PatentsView API
Choosing the Right Method
Use BigQuery When:
- Quick keyword search needed
- Worldwide patents (not just US)
- Fast results (3-4 seconds)
- Zero local storage
- CPC classification search
- Budget-conscious (free tier: 1TB/month)
Use PatentsView When:
- Need detailed US patent metadata
- Searching by inventor/assignee
- Citation analysis required
- Complex boolean queries
- Exact field matching
- Patent family analysis
Combined Workflow
- Start with BigQuery (broad keyword search)
- Identify relevant patents and CPC codes
- Switch to PatentsView (detailed metadata/citations)
- Export final results
Example:
# Step 1: BigQuery broad search
python bigquery_search.py search "voice biometric authentication" 20
# Step 2: Found CPC G10L17, search more
python bigquery_search.py cpc G10L17 50
# Step 3: Use PatentsView for inventor/assignee analysis
Instructions for Claude
When user requests patent searches:
- Understand Goal: Technology, time period, prior art vs competitive analysis, US vs worldwide
- Check Dependencies: Verify BigQuery/PatentsView setup
- Choose Method: Default BigQuery for broad, PatentsView for detailed
- Optimize Queries:
- BigQuery: 2-3 keywords, simplify if zero results, use CPC codes
- PatentsView: Verify API key, construct JSON queries, handle pagination
- Present Results: Parse JSON, highlight key info, provide Google Patents URLs
- Offer Next Steps: Suggest refinements, related classifications, citation analysis
Common Use Cases
Prior Art Search
- BigQuery keyword search
- Identify CPC codes
- BigQuery CPC search
- PatentsView citation analysis
- Document findings
Competitive Intelligence
- PatentsView search by assignee
- Filter by date range
- Group by CPC
- Identify key inventors
- Trend report
Technology Landscape
- BigQuery CPC search worldwide
- Analyze by country/date
- Identify patent families
- PatentsView US details
- Summary report
Freedom to Operate
- BigQuery keyword + CPC search
- Filter by jurisdiction/active status
- PatentsView claim analysis
- Review forward citations
- Risk assessment
Performance & Coverage
| Method | Patents | Coverage | Speed | Cost | Storage |
|---|---|---|---|---|---|
| BigQuery | 76M+ | Worldwide | 3-4s | Free* | 0GB |
| PatentsView | 9.2M | US only | 1-3s | Free | 0GB |
*Free tier: 1TB queries/month
Quick Reference
BigQuery Commands
python bigquery_search.py search "query" <limit>
python bigquery_search.py get <PATENT-NUMBER>
python bigquery_search.py cpc <CODE> <limit>
Common CPC Codes
| Code | Technology |
|---|---|
| G10L | Speech analysis/synthesis |
| G10L15 | Speech recognition |
| G10L17 | Speaker recognition/verification |
| G06F21 | Security arrangements |
| G06N | Computing models |
Troubleshooting
FOR CLAUDE: Only run diagnostics if Quick Test fails.
| Problem | Solution |
|---|---|
| BigQuery auth fails | gcloud auth application-default login |
| No module google.cloud | pip install google-cloud-bigquery db-dtypes |
| Zero results | Simplify query (2-3 keywords max) |
| Patent get fails | Use hyphenated format: US-XXXXX-XX |
| PatentsView 403 | Set API key environment variable |
| Rate limit (429) | Wait 60 seconds (PatentsView: 45 req/min) |
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
creating-opencode-plugins
元该Skill为开发者创建OpenCode插件提供指导,涵盖命令、文件、LSP等25+种事件类型。它详细说明了插件结构、事件API规范及JavaScript/TypeScript实现模式,帮助开发者构建事件驱动的模块。适用于需要拦截操作、扩展功能或自定义AI助手行为的插件开发场景。
evaluating-llms-harness
测试该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。
langchain
元LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。
