Epo Patent Search logo

Epo Patent Search

Community
RobThePCGuy
epo-patent-search

Search European patents using EPO OPS API (full-text, legal status, families) and BigQuery (100M+ patents, EP filter) for prior art, competitive intelligence, and freedom-to-operate analysis

Overview

PublisherRobThePCGuy
RepositoryClaude-Patent-Creator
Skill nameepo-patent-search
Stars
203
Forks
33
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by RobThePCGuy on GitHub. Read the source before you install it.

Installation

Install the Epo Patent Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/epo-patent-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git /tmp/Claude-Patent-Creator
mkdir -p .claude/skills
cp -r /tmp/Claude-Patent-Creator/skills/epo-patent-search .claude/skills/epo-patent-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Epo Patent Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Epo Patent Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Epo Patent Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

EPO Patent Search Skill

Search European patents using the EPO Open Patent Services (OPS) API and Google BigQuery with EP country filtering.

When to Use

Invoke this skill when users ask to:

  • Search for European patents
  • Find EP prior art for a technology
  • Check legal status of EP patents
  • Explore patent families across jurisdictions
  • Conduct EP freedom-to-operate analysis
  • Research the EP patent landscape for a technology area
  • Get full-text EP claims or descriptions

What This Skill Does

Provides access to European patent data through two methods:

  1. EPO OPS API (European Patent Data):

    • Full-text EP patent retrieval (claims, description)
    • Legal status and procedural history
    • INPADOC patent family linking
    • Applicant and inventor search
    • EP publication types (A1, A2, A3, B1, B2)
    • Designated contracting states
  2. BigQuery (Worldwide Patents, EP Filter):

    • Fast keyword search across 100M+ patents with country="EP"
    • CPC classification search for EP patents
    • Filing trend analysis
    • Cross-jurisdiction comparison

Required Setup

BigQuery (Primary)

Prerequisites:

  1. Google Cloud Project (free to create)
  2. BigQuery API enabled
  3. Application Default Credentials configured

Setup:

bash
gcloud auth application-default login
export GOOGLE_CLOUD_PROJECT=your-project-id

EPO OPS API (Optional, for full-text/legal status)

Prerequisites:

  1. Register at https://developers.epo.org/
  2. Create an application to get Consumer Key and Secret
  3. Set environment variables

Setup:

bash
export EPO_OPS_CONSUMER_KEY=your-key
export EPO_OPS_CONSUMER_SECRET=your-secret

How to Use

When this skill is invoked:

  1. Determine search type:

    • Keyword search: use BigQuery with country="EP" for speed
    • Full-text retrieval: use EPO OPS for complete claims/description
    • Legal status: use EPO OPS for procedural data
    • Family search: use EPO OPS INPADOC family service
    • CPC search: use BigQuery for broad classification browsing
  2. Execute search:

    Full-text keyword search (EP patents), falling back to search_patents_bigquery with the same arguments if not configured:

    python
    results = search_patents_google(
        query="blockchain authentication",
        country="EP",
        limit=20,
        start_year=2020
    )

    BigQuery CPC search (EP patents):

    python
    results = search_patents_by_cpc_bigquery(
        cpc_code="H04L9/32",
        country="EP",
        limit=30
    )

    EPO OPS full-text retrieval:

    python
    results = search_epo_patents(
        query="EP3456789",
        search_type="full_text"
    )

    EPO OPS family search:

    python
    results = search_epo_patents(
        query="EP3456789",
        search_type="family"
    )
  3. Present results:

    • Rank by relevance
    • Show key metadata (title, applicant, dates, IPC/CPC)
    • Highlight legal status (in force, expired, opposed)
    • Provide links to Espacenet for full documents
    • Note patent family members in other jurisdictions

Search Result Format

python
{
    "publication_number": "EP3456789A1",
    "title": "Authentication system using distributed ledger",
    "abstract": "A system for authenticating...",
    "applicant": "Example GmbH",
    "inventors": ["Hans Mueller", "Maria Schmidt"],
    "filing_date": "2019-03-15",
    "publication_date": "2020-01-22",
    "grant_date": null,
    "ipc_codes": ["H04L9/32", "G06F21/31"],
    "cpc_codes": ["H04L9/32", "G06F21/31"],
    "designated_states": ["DE", "FR", "GB", "NL", "IT"],
    "priority_claims": ["US16/234567 (2018-12-28)"],
    "family_id": "67890123",
    "legal_status": "Examination in progress",
    "publication_type": "A1"
}

EP Publication Types

CodeTypeDescription
A1Application + searchPublished EP application with search report
A2Application onlyPublished without search report
A3Search reportSearch report published separately
B1Granted patentPatent specification as granted
B2Amended patentAmended specification after opposition
B3Limited patentPatent after limitation proceedings

Cross-Jurisdiction Linking

Use family_id to find related patents across jurisdictions:

EP3456789A1 (European application)
├── US10123456B2 (US counterpart)
├── CN112345678A (Chinese counterpart)
├── JP2020-123456A (Japanese counterpart)
└── WO2019/123456A1 (PCT application)

This is essential for:

  • Prior art analysis (one patent may be available in multiple languages)
  • Freedom-to-operate (check where patent is in force)
  • Competitive intelligence (track filing strategy)

Presentation Format

Present search results as:

EP PATENT SEARCH RESULTS
=========================

Query: "blockchain authentication"
Source: BigQuery (EP filter) + EPO OPS
Found: 89 EP patents
Date Range: 2020-2025

[1] EP3456789B1 - Authentication system using distributed ledger
    Applicant: Example GmbH (DE)
    Filed: 2019-03-15 | Granted: 2022-08-10
    IPC: H04L9/32, G06F21/31
    Status: Patent in force (validated in DE, FR, GB)
    Family: US10123456B2, CN112345678B, WO2019/123456A1
    Espacenet: https://worldwide.espacenet.com/patent/search?q=EP3456789

[2] EP3567890A1 - Blockchain-based identity verification method
    Applicant: Tech Corp (US)
    Filed: 2020-01-10 | Published: 2021-06-16
    IPC: H04L9/00, G06Q20/38
    Status: Examination in progress
    Family: US20210203456A1, WO2020/234567A1

---

Top CPC Codes in Results:
- H04L9/32 (15 patents): Authentication/verification
- G06F21/31 (12 patents): User authentication
- H04L9/00 (8 patents): Cryptographic mechanisms

Common Use Cases

EP Prior Art Search

  1. BigQuery keyword search (country="EP")
  2. Identify relevant CPC codes
  3. BigQuery CPC search (country="EP")
  4. EPO OPS full-text for top results
  5. Document findings with citations

Patent Family Analysis

  1. Find EP patent via BigQuery or EPO OPS
  2. Get family_id
  3. Search for family members worldwide
  4. Map filing strategy across jurisdictions
  5. Check legal status in each country

EP Freedom-to-Operate

  1. Search EP patents in relevant technology
  2. Filter for granted patents (B1/B2)
  3. Check legal status (in force vs expired)
  4. Identify validated countries
  5. Assess infringement risk

EP Opposition Research

  1. Find granted EP patents (B1)
  2. Check if within 9-month opposition window
  3. Search for prior art predating priority date
  4. Analyze claims scope
  5. Assess opposition grounds (Art. 100 EPC)

Performance & Coverage

MethodPatentsCoverageSpeedCost
BigQuery (EP)~5M EPEP applications + grants3-4sFree*
EPO OPSAll EPFull text + legal status1-3sFree**

*BigQuery free tier: 1TB queries/month (~20,000 searches) **EPO OPS: Fair use (2.5GB data traffic per week)

Tools Available

  • Bash: To run search scripts
  • Read: To load saved search results
  • Write: To save patent search results

Frequently asked questions

What does the Epo Patent Search AI skill do?

Search European patents using EPO OPS API (full-text, legal status, families) and BigQuery (100M+ patents, EP filter) for prior art, competitive intelligence, and freedom-to-operate analysis

Why use Epo Patent Search on TypingMind?

Because you install it once and use it with any model. Epo Patent Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Epo Patent Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/skills/epo-patent-search. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Epo Patent Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Epo Patent Search?

As many as you like. As long as a model supports skills, you can use Epo Patent Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Epo Patent Search AI skill free?

Yes. It is published on GitHub by RobThePCGuy under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇