Access USPTO patent data via PatentsView REST API and Google Patents Public Data (BigQuery). Search by inventor, assignee, CPC, or keywords; download metadata and claims; analyze portfolios; track tech trends. For IP landscape analysis, competitor monitoring, prior art search, and tech forecasting in life sciences and biotech.
SkillScore86Maintained
Automatic
◆Legal & Contracts pack
Last verified 8/23/2026
What it changes
Passed 19 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill86%
Checks it passed that the model alone missed
Uses assignee_country field with operator _eq set to US
Uses field name cpc_subgroup_id in the query payload filter
Uses operator _contains for assignee_organization in the filter payload
2 fixed17 passed either way3 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+189%
Agent turns
0%
Response time
-47%
Model gemini-3.6-flashMeasured 8/23/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
I'd like a Python snippet that queries USPTO patent data to find all US-assigned gene therapy patents under CPC classification A61K48 granted between 2020 and 2024. Please return a pandas DataFrame showing the patent number, title, grant date, and assignee organization name for each record.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses field name cpc_subgroup_id in the query payload filter
Missed
Passed
Uses assignee_country field with operator _eq set to US
Missed
Passed
Requests fields patent_number, patent_title, patent_date, and assignee_organization in field array f
Passed
Passed
case-01 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md442 linessingle file
uspto-database
Overview
The USPTO provides two primary programmatic access points for patent data: the PatentsView API (REST, free, no key required for basic use) for structured queries by inventor, assignee, CPC classification, and keywords; and Google Patents Public Data (BigQuery public dataset) for large-scale analytics across the full patent corpus. Both expose data under the CC0 Public Domain Dedication. This skill covers Python-based access patterns for both, plus basic patent portfolio analytics.
When to Use
Prior art search: Finding existing patents relevant to a technology before filing or to assess freedom-to-operate.
Competitor IP landscape analysis: Querying all patents from a specific assignee (company or institution) to map their technology portfolio.
CPC classification search: Finding patents in a specific technology area using Cooperative Patent Classification codes (e.g., C12N for nucleotides/genetic engineering).
Inventor network analysis: Identifying prolific inventors in a field and their institutional affiliations.
Technology trend tracking: Counting patent filings by year and technology category to identify emerging areas.
Life sciences IP analysis: Searching biotech-specific classifications (A61K for pharmaceuticals, C12N for genetics, G16B for bioinformatics).
For full-text patent PDF downloads, use the USPTO Bulk Data Storage System (BDSS) or Google Patents direct links.
Rate limits: PatentsView API allows 45 requests/minute without an API key; request a free key for 45 req/min with higher daily limits.
Prerequisites
Python packages: requests, pandas, matplotlib
Optional: google-cloud-bigquery for Google Patents Public Data queries
Data requirements: No account needed for PatentsView basic queries; Google Cloud account required for BigQuery
Rate limits: PatentsView — 45 requests/minute (unauthenticated), higher with free API key