Claude Code SkillScientific2 installs

Uspto Database

"Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches."

Install with the Claude Code Templates CLI
$ npx claude-code-templates@latest --skill="scientific/uspto-database" --yes

Requires Claude Code. The command adds this skill to your project's .claudedirectory — nothing runs on ToolZip's servers.

What's inside this skill

Component source (preview)

USPTO Database

Overview

USPTO provides specialized APIs for patent and trademark data. Search patents by keywords/inventors/assignees, retrieve examination history via PEDS, track assignments, analyze citations and office actions, access TSDR for trademarks, for IP analysis and prior art searches.

When to Use This Skill

This skill should be used when:

  • Patent Search: Finding patents by keywords, inventors, assignees, classifications, or dates
  • Patent Details: Retrieving full patent data including claims, abstracts, citations
  • Trademark Search: Looking up trademarks by serial or registration number
  • Trademark Status: Checking trademark status, ownership, and prosecution history
  • Examination History: Accessing patent prosecution data from PEDS (Patent Examination Data System)
  • Office Actions: Retrieving office action text, citations, and rejections
  • Assignments: Tracking patent/trademark ownership transfers
  • Citations: Analyzing patent citations (forward and backward)
  • Litigation: Accessing patent litigation records
  • Portfolio Analysis: Analyzing patent/trademark portfolios for companies or inventors

USPTO API Ecosystem

The USPTO provides multiple specialized APIs for different data needs:

Core APIs

  • PatentSearch API - Modern ElasticSearch-based patent search (replaced legacy PatentsView in May 2025)
- Search patents by keywords, inventors, assignees, classifications, dates

- Access to patent data through June 30, 2025

- 45 requests/minute rate limit

- Base URL: https://search.patentsview.org/api/v1/

  • PEDS (Patent Examination Data System) - Patent examination history
- Application status and transaction history from 1981-present

- Office action dates and examination events

- Use uspto-opendata-python Python library

- Replaced: PAIR Bulk Data (PBD) - decommissioned

  • TSDR (Trademark Status & Document Retrieval) - Trademark data
- Trademark status, ownership, prosecution history

- Search by serial or registration number

- Base URL: https://tsdrapi.uspto.gov/ts/cd/

Additional APIs

  • Patent Assignment Search - Ownership records and transfers
  • Trademark Assignment Search - Trademark ownership changes
  • Enriched Citation API - Patent citation analysis
  • Office Action Text Retrieval - Full text of office actions
  • Office Action Citations - Citations from office actions
  • Office Action Rejection - Rejection reasons and types
  • PTAB API - Patent Trial and Appeal Board proceedings
  • Patent Litigation Cases - Federal district court litigation data
  • Cancer Moonshot Data Set - Cancer-related patents

Quick Start

API Key Registration

All USPTO APIs require an API key. Register at:

https://account.uspto.gov/api-manager/

Set the API key as an environment variable:

export USPTO_API_KEY="your_api_key_here"

Helper Scripts

This skill includes Python scripts for common operations:

  • scripts/patent_search.py - PatentSearch API client for searching patents
  • scripts/peds_client.py - PEDS client for examination history
  • scripts/trademark_client.py - TSDR client for trademark data

Task 1: Searching Patents

Using the PatentSearch API

The PatentSearch API uses a JSON query language with various operators for flexible searching.

Basic Patent Search Examples

Search by keywords in abstract:
from scripts.patent_search import PatentSearchClient

client = PatentSearchClient()

# Search for machine learning patents
results = client.search_patents({
    "patent_abstract": {"_text_all": ["machine", "learning"]}
})

for patent in results['patents']:
    print(f"{patent['patent_number']}: {patent['patent_title']}")
Search by inventor:
results = client.search_by_inventor("John Smith")
Search by assignee/company:
results = client.search_by_assignee("Google")
Search by date range:
results = client.search_by_date_range("2024-01-01", "2024-12-31")
Search by CPC classification:
results = client.search_by_classification("H04N")  # Video/image tech

Advanced Patent Search

Combine multiple criteria with logical operators:

results = client.advanced_search(
    keywords=["artificial", "intelligence"],
    assignee="Microsoft",
    start_date="2023-01-01",
    end_date="2024-12-31",
    cpc_codes=["G06N", "G06F"]  # AI and computing classifications
)

Direct API Usage

For complex queries, use the API directly:

import requests

url = "https://search.patentsview.org/api/v1/patent"
headers = {
    "X-Api-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

query = {
    "q": {
        "_and": [
            {"patent_date": {"_gte": "2024-01-01"}},
            {"assignee_organization": {"_text_any": ["Google", "Alphabet"]}},
            {"cpc_subclass_id": ["G06N", "H04N"]}
        ]
    },
    "f": ["patent_number", "patent_title", "patent_date", "inventor_name"],
    "s": [{"patent_date": "desc"}],
    "o": {"per_page": 100, "page": 1}
}

response = requests.post(url, headers=headers, json=query)
results = response.json()

Query Operators

  • Equality: {"field": "value"} or {"field": {"_eq": "value"}}
  • Comparison: _gt, _gte, _lt, _lte, _neq
  • Text search: _text_all, _text_any, _text_phrase
  • String matching: _begins, _contains
  • Logical: _and, _or, _not

Best Practice: Use _text_* operators for text fields (more performant than _contains or _begins)

Available Patent Endpoints

  • /patent - Granted patents
  • /publication - Pregrant publications
  • /inventor - Inventor information
  • /assignee - Assignee information
  • /cpc_subclass, /cpc_at_issue - CPC classifications
  • /uspc - US Patent Classification
  • /ipc - International Patent Classification
  • /claims, /brief_summary_text, /detail_description_text - Text data (beta)

Reference Documentation

See references/patentsearch_api.md for complete PatentSearch API documentation including:

  • All available endpoints
  • Complete field reference
  • Query syntax and examples
  • Response formats
  • Rate limits and best practices

Task 2: Retrieving Patent Examination Data

Using PEDS (Patent Examination Data System)

PEDS provides comprehensive prosecution history including transaction events, status changes, and examination timeline.

Installation

uv pip install uspto-opendata-python

Basic PEDS Usage

Get application data:
from scripts.peds_client import PEDSHelper

helper = PEDSHelper()

# By application number
app_data = helper.get_application("16123456")
print(f"Title: {app_data['title']}")
print(f"Status: {app_data['app_status']}")

# By patent number
patent_data = helper.get_patent("11234567")
Get transaction history:
transactions = helper.get_transaction_history("16123456")

for trans in transactions:
    print(f"{trans['date']}: {trans['code']} - {trans['description']}")
Get office actions:
office_actions = helper.get_office_actions("16123456")

for oa in office_actions:
    if oa['code'] == 'CTNF':
        print(f"Non-final rejection: {oa['date']}")
    elif oa['code'] == 'CTFR':
        print(f"Final rejection: {oa['date']}")
    elif oa['code'] == 'NOA':
        print(f"Notice of allowance: {oa['date']}")
Get status summary:
summary = helper.get_status_summary("16123456")

print(f"Current status: {summary['current_status']}")
print(f"Filing date: {summary['filing_date']}")
print(f"Pendency: {summary['pendency_days']} days")

if summary['is_patented']:
    print(f"Patent number: {summary['patent_number']}")
    print(f"Issue date: {summary['issue_date']}")

Prosecution Analysis

Analyze prosecution patterns:

analysis = helper.analyze_prosecution("16123456")

print(f"Total office actions: {analysis['total_office_actions']}")
print(f"Non-final rejections: {analysis['non_final_rejections']}")
print(f"Final rejections: {analysis['final_rejections']}")
print(f"Allowed: {analysis['allowance']}")
print(f"Responses filed: {analysis['responses']}")

Common Transaction Codes

  • CTNF - Non-final rejection mailed
  • CTFR - Final rejection mailed
  • NOA - Notice of allowance mailed
  • WRIT - Response filed
  • ISS.FEE - Issue fee payment
  • ABND - Application abandoned
  • AOPF - Office action mailed

Reference Documentation

See references/peds_api.md for complete PEDS documentation including:

  • All available data fields
  • Transaction code reference
  • Python library usage
  • Portfolio analysis examples

Task 3: Searching and Monitoring Trademarks

Using TSDR (Trademark Status & Document Retrieval)

Access trademark status, ownership, and prosecution history.

Basic Trademark Usage

Get trademark by serial number:
from scripts.trademark_client import TrademarkClient

client = TrademarkClient()

# By serial number
tm_data = client.get_trademark_by_serial("87654321")

# By registration number
tm_data = client.get_trademark_by_registration("5678901")
Get trademark status:
status = client.get_trademark_status("87654321")

print(f"Mark: {status['mark_text']}")
print(f"Status: {status['status']}")
print(f"Filing date: {status['filing_date']}")

if status['is_registered']:
    print(f"Registration #: {status['registration_number']}")
    print(f"Registration date: {status['registration_date']}")
Check trademark health:
health = client.check_trademark_health("87654321")

print(f"Mark: {health['mark']}")
print(f"Status: {health['status']}")

for alert in health['alerts']:
    print(alert)

if health['needs_attention']:
    print("⚠️  This mark needs attention!")

Trademark Portfolio Monitoring

Monitor multiple trademarks:

def monitor_portfolio(serial_numbers, api_key):
    """Monitor trademark portfolio health."""
    client = TrademarkClient(api_key)

    results = {
        'active': [],
        'pending': [],
        'problems': []
    }

    for sn in serial_numbers:
        health = client.check_trademark_health(sn)

        if 'REGISTERED' in health['status']:
            results['active'].append(health)
        elif 'PENDING' in health['status'] or 'PUBLISHED' in health['status']:
            results['pending'].append(health)
        elif health['needs_attention']:
            results['problems'].append(health)

    return results

Common Trademark Statuses

  • REGISTERED - Active registered mark
  • PENDING - Under examination
  • PUBLISHED FOR OPPOSITION - In opposition period
  • ABANDONED - Application abandoned
  • CANCELLED - Registration cancelled
  • SUSPENDED - Examination suspended
  • REGISTERED AND RENEWED - Registration renewed

Reference Documentation

See references/trademark_api.md for complete trademark API documentation including:

  • TSDR API reference
  • Trademark Assignment Search API
  • All status codes
  • Prosecution history access
  • Ownership tracking

Task 4: Tracking Assignments and Ownership

Patent and Trademark Assignments

Both patents and trademarks have Assignment Search APIs for tracking ownership changes.

Patent Assignment API

Base URL: https://assignment-api.uspto.gov/patent/v1.4/ Search by patent number:

```python

import requests

import xml.etree.ElementTree as ET

def get_patent_assignments(patent_number, api_key):

url = f"https://assignment-api.uspto.gov/patent/v1.4/assignment/patent/{patent_number}"

headers = {"X-Api-Key": api_key}

response = requests.get(url, headers=headers)

if response.status_code == 200:

return response.text # Returns XML

assignments_xml = get_patent_assignments("11234567", api_key)

root = ET.fromstring(assignments_xml)

for

Preview truncated. View the full source on GitHub →

Type
Skill
Category
Scientific
Installs
2
Source
GitHub ↗

Related Claude Code Skills

SkillScientific

Generate Image

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

99 installsView →
SkillScientific

Markitdown

"Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more."

72 installsView →
SkillScientific

Scientific Critical Thinking

"Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims."

66 installsView →
SkillScientific

Scientific Slides

"Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer."

52 installsView →
SkillScientific

Statistical Analysis

"Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research."

40 installsView →
SkillScientific

Market Research Reports

"Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix."

39 installsView →

Catalog data and component content are sourced from the open-source davila7/claude-code-templates project (MIT license). ToolZip curates the listing and writes original descriptions; every component links back to its original source. Claude Code is a product of Anthropic. ToolZip is an independent catalog and is not affiliated with or endorsed by Anthropic.