- Home
- Skills
- K Dense Ai
- Claude Scientific Skills
- Uspto Database
uspto-database_skill
- Python
7.4k
GitHub Stars
1
Bundled Files
3 weeks ago
Catalog Refreshed
2 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstart where the catalogue uses aiagentskills.
npx veilstart add skill k-dense-ai/claude-scientific-skills --skill uspto-database- SKILL.md19.1 KB
Overview
This skill provides ready-to-use Python clients and helpers to access USPTO APIs for patent and trademark research. It supports PatentSearch (modern ElasticSearch API), PEDS prosecution history, TSDR trademark status retrieval, assignments, citations, office actions, PTAB and litigation data. Use it to automate prior art discovery, portfolio monitoring, prosecution analysis, and ownership tracking.
How this skill works
The package wraps USPTO endpoints and common workflows in small Python modules (patent_search, peds_client, trademark_client) and example scripts. It issues authenticated requests using your USPTO/PatentsView API keys, parses JSON/XML responses, and exposes helper methods for searches, transaction histories, office action retrieval, assignment lookups, and citation analysis. Rate limits and field-specific query operators are handled by the clients so you can build queries or call higher-level helpers.
When to use it
- Perform broad or advanced patent searches by keywords, CPC/IPC codes, assignees, inventors, or date ranges
- Retrieve full patent prosecution history and office action timelines from PEDS
- Lookup trademark status, registration/prosecution documents and monitor trademark health via TSDR
- Track ownership changes and assignments for due diligence or M&A
- Analyze forward/backward citations, examiner vs applicant citations, and litigation/PTAB activity
Best practices
- Register and store USPTO and PatentsView API keys as environment variables to avoid embedding secrets
- Prefer _text_* operators for free-text searches for performance and accuracy
- Page results and respect the documented rate limits; use batching for large portfolio queries
- Combine PEDS transaction timelines with office action text for prosecution analysis
- Validate and normalize assignee/inventor names when aggregating portfolio or assignment data
Example use cases
- Run a targeted prior art sweep for an invention using CPC codes plus abstract keyword filters
- Automate weekly monitoring of a trademark portfolio for status changes or abandonment risks
- Fetch full prosecution timeline for a patent application to estimate pendency and prosecution effort
- Aggregate assignments for a company to build an ownership history for due diligence
- Generate citation graphs (forward/backward) to find influential patents and potential clearance risks
FAQ
Yes. USPTO and PatentsView require API keys. Set them as environment variables (USPTO_API_KEY, PATENTSVIEW_API_KEY) before running the scripts.
Can I retrieve office action full text and transaction history?
Yes. Use the PEDS helper to get transaction events and codes, then call the office action text retrieval endpoints to download full office action documents for detailed analysis.