SkillAgentSearch skills...

uspto-database

Access USPTO data (Patent Search, PEDS, TSDR, assignments) when you need to query patents/trademarks and retrieve prosecution or status information programmatically.

Install / Use

npx skills add aipoch/medical-research-skills --skill uspto-database

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

86/100

Supported Platforms

Universal

Our assessment of uspto-database

uspto-database scores 86/100 on our quality scale, 433rd of 604 Data & Analytics skills we index.

Its SKILL.md is 3.0 KB long, well organised into 10 sections with 1 code example: a solid amount of guidance for an agent.

With 1,916 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
17/20
Description
15/15
Adoption
14/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so uspto-database is actively maintained.
  • Our last check on 2026-11-03 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

uspto-database compared with similar skills

All 4 of these similar skills score higher than uspto-database; compare them before choosing.

SkillScoreStarsUpdatedFormat
uspto-database (this skill)by aipoch861.9k2mo agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md

Frequently asked questions

How do I install uspto-database?
Run npx skills add aipoch/medical-research-skills --skill uspto-database. The install tabs above show the steps for each supported agent.
Which AI agents does uspto-database work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is uspto-database safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is uspto-database still maintained?
The repository was last updated about 2 months ago, so uspto-database is actively maintained.

name: uspto-database description: Access USPTO data (Patent Search, PEDS, TSDR, assignments) when you need to query patents/trademarks and retrieve prosecution or status information programmatically. license: MIT author: AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • Find relevant US patents by keyword, inventor, assignee, CPC/IPC class, or date range for prior-art screening.
  • Retrieve patent application/prosecution history (PEDS) to understand office actions, events, and timeline status.
  • Check trademark status and documents via TSDR for clearance, monitoring, or portfolio review.
  • Validate patent lifecycle signals such as maintenance-fee-related status or expiration indicators as part of diligence.
  • Pull assignment/ownership-related information to support chain-of-title checks.

Key Features

  • Patent search client for querying USPTO/PatentsView-style endpoints and returning matching patent identifiers/records.
  • PEDS client for fetching examination history and event data for applications.
  • TSDR access for trademark status and document retrieval.
  • Script-oriented workflow designed for automation (batch queries, pipelines, and integration into internal tools).

Dependencies

  • Python >=3.9
  • requests >=2.31.0
  • uspto-opendata-python >=0.3.0

Example Usage

# Example: search patents by abstract text and print results
# Prerequisite: set required API keys in environment variables as expected by your scripts/clients.
# For example (names may vary by implementation):
#   export USPTO_API_KEY="..."
#   export PATENTSVIEW_API_KEY="..."

from scripts.patent_search import PatentSearchClient

def main():
    client = PatentSearchClient()

    # Query example: search for patents whose abstract contains "AI"
    query = {"_text_all": {"patent_abstract": "AI"}}

    results = client.search_patents(query)
    print(results)

if __name__ == "__main__":
    main()

Implementation Details

  • Workflow

    1. Search: Use scripts/patent_search.py to locate relevant patent numbers/records from a text or fielded query.
    2. History: Use scripts/peds_client.py to retrieve prosecution/examination history (events, dates, and status signals).
    3. Status checks: Use retrieved metadata to assess maintenance-fee/expiration-related status where available.
  • Query model

    • Patent search is driven by a JSON query object (e.g., full-text constraints such as "_text_all" over fields like patent_abstract).
    • Returned results are intended to be fed into downstream steps (e.g., PEDS lookups by application/patent identifiers).
  • Authentication

    • API keys for USPTO and/or PatentsView are required and should be provided via environment variables or configuration used by the clients.
  • Networking

    • HTTP requests are performed via requests; ensure timeouts/retries are configured in the underlying clients if running large batches.

Related Skills

View on GitHub
GitHub Stars1.9k
CategoryData
Updated2mo ago
Forks175

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions