MCPInstall

epc-search

RAG search across EPC provisions, EPO Guidelines for Examination, and PCT rules for European and international patent law research

Installs
51
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/robthepcguy/claude-patent-creator --skill epc-search
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads epc-search automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

EPC/PCT Legal Search Skill

Hybrid RAG search across the European Patent Convention (EPC), EPO Guidelines for Examination, and PCT Rules for patent law research.

When to Use

Invoke this skill when users ask to:

  • Find EPC articles or rules on a specific topic
  • Search EPO Guidelines for Examination
  • Look up PCT rules or Administrative Instructions
  • Compare EPC requirements with USPTO/MPEP practice
  • Research EPO Board of Appeal case law principles
  • Understand European patent prosecution procedure
  • Find legal basis for EPO examination objections

What This Skill Does

Provides legal research across European and international patent law:

  1. EPC Search (European Patent Convention):

    • Articles 1-178 EPC
    • Rules 1-167 EPC (Implementing Regulations)
    • Protocol on Interpretation of Art. 69 EPC
    • Protocol on Centralisation
    • Protocol on Privileges and Immunities
  2. EPO Guidelines Search (Guidelines for Examination):

    • Part A: Guidelines for Formalities Examination
    • Part B: Guidelines for Search
    • Part C: Guidelines for Procedural Aspects of Substantive Examination
    • Part D: Guidelines for Opposition and Limitation/Revocation
    • Part E: Guidelines for General Procedural Matters
    • Part F: Guidelines for Substantive Examination (The Patent Application)
    • Part G: Guidelines for Patentability
    • Part H: Guidelines for Amendments and Corrections
  3. PCT Rules Search (Patent Cooperation Treaty):

    • PCT Articles 1-69
    • PCT Rules 1-96 (Regulations under the PCT)
    • Administrative Instructions under the PCT
    • WIPO Standards (ST.25, ST.26, ST.36)
  4. Cross-Jurisdiction Comparison:

    • EPC vs 35 USC mapping
    • EPO Guidelines vs MPEP equivalents
    • PCT requirements vs national requirements

Required Data

MCP Tools Available:

  • search_patent_law - Search EPC, EPO Guidelines, PCT rules with jurisdiction parameter
  • search_mpep - Search MPEP/35 USC/37 CFR for comparison

How to Use

When this skill is invoked:

  1. Determine jurisdiction:

    • EPO: search EPC articles/rules and EPO Guidelines
    • PCT: search PCT articles/rules and Administrative Instructions
    • Both: search across all sources
    • Comparison: search EPO + USPTO sources
  2. Execute search:

    EPC/EPO Guidelines search:

    results = search_patent_law(
        query="claim clarity requirements",
        jurisdiction="EPO",
        top_k=5
    )
    

    PCT rules search:

    results = search_patent_law(
        query="unity of invention",
        jurisdiction="PCT",
        top_k=5
    )
    

    Cross-jurisdiction comparison:

    epo_results = search_patent_law(query="sufficiency of disclosure", jurisdiction="EPO")
    us_results = search_mpep(query="enablement requirement")
    
  3. Present results:

    • Show relevant provisions with full text
    • Provide article/rule numbers and section references
    • Include EPO Guidelines commentary
    • Note practical implications for prosecution

Key EPC Provisions Reference

Patentability

ArticleTopicDescription
Art. 52Patentable inventionsWhat can be patented
Art. 52(2)ExclusionsDiscoveries, theories, programs "as such"
Art. 53ExceptionsMorality, plant/animal varieties, medical methods
Art. 54NoveltyAbsolute novelty, no grace period
Art. 55Non-prejudicial disclosures6-month grace for abuse or exhibitions
Art. 56Inventive stepProblem-solution approach
Art. 57Industrial applicabilityCapable of industrial application

The Patent Application

Article/RuleTopicDescription
Art. 78RequirementsWhat an EP application must contain
Art. 83DisclosureSufficiency of disclosure
Art. 84ClaimsClarity, conciseness, support
Rule 42DescriptionContent and form of description
Rule 43ClaimsTwo-part form, numbering, categories
Rule 46DrawingsForm and content requirements
Rule 47AbstractMax 150 words, figure designation

Examination Procedure

ArticleTopicDescription
Art. 90Formalities examinationInitial formality check
Art. 92European searchSearch report
Art. 94Substantive examinationExamination on request
Art. 97Grant/refusalDecision on application
Art. 99Opposition9-month opposition period

Key PCT Rules Reference

Application Requirements

RuleTopicDescription
Rule 4The requestForm PCT/RO/101 contents
Rule 5The descriptionRequired sections and order
Rule 6The claimsNumbering, form, categories
Rule 8The abstractMax 150 words, figure
Rule 11Physical requirementsPaper, margins, fonts
Rule 12LanguageAccepted languages

Unity and Search

RuleTopicDescription
Rule 13Unity of inventionSingle general inventive concept
Rule 33Relevant prior artISA search scope
Rule 39Subject matter not searchedExcluded from ISA search
Rule 43bisInternational search reportWritten opinion of ISA

National Phase

RuleTopicDescription
Rule 49Physical requirementsNational phase format
Rule 49.6TranslationLanguage requirements
Rule 51bisCertain national requirementsNational law compliance

EPO Guidelines Structure

Part A: Formalities Examination
├── Chapter I: Checking the application on filing
├── Chapter II: Filing and examination for formalities
├── Chapter III: Special cases (divisionals, PCT)
└── Chapter IV: Designation of inventor

Part F: The Patent Application
├── Chapter I: Description
├── Chapter II: Claims (MOST COMMONLY SEARCHED)
│   ├── F-IV, 2: Independent claims
│   ├── F-IV, 3: Two-part form
│   ├── F-IV, 4: Clarity
│   ├── F-IV, 6: Support by description
│   └── F-IV, 7: Dependent claims
├── Chapter III: Sufficiency of disclosure
├── Chapter V: Abstract
└── Chapter VI: Drawings

Part G: Patentability
├── Chapter I: Excluded subject matter
├── Chapter II: Non-technical subject matter
├── Chapter III: Novelty
├── Chapter V: Non-prejudicial disclosures
├── Chapter VI: Inventive step (problem-solution)
└── Chapter VII: Inventive step (combinability)

Presentation Format

Present search results as:

EPC/EPO LEGAL RESEARCH RESULTS
=================================

Query: "claim clarity requirements"
Jurisdiction: EPO (EPC + Guidelines)

[1] Art. 84 EPC - The Claims
    "The claims shall define the matter for which protection
    is sought. They shall be clear, concise and be supported
    by the description."

    EPO Guidelines F-IV, 4 - Clarity
    "Each claim should be read giving the words the meaning
    and scope which they normally have in the relevant art..."

    Key Points:
    - Claims must be clear on their own (not by reference to spec)
    - Technical terms given their normal meaning in the art
    - Relative terms need objective reference point
    - Functional features must be verifiable

[2] Rule 43(1) EPC - Form and content of claims
    "...shall contain: (a) a statement indicating the designation
    of the subject-matter and those technical features necessary
    for the definition... (preamble); and (b) a characterising
    portion preceded by 'characterised in that'..."

    EPO Guidelines F-IV, 3.2 - Two-part form
    "Independent claims should normally be in the two-part form..."

---

Related MPEP Comparison:
- MPEP 2173: Claims Must Particularly Point Out and Distinctly Claim
- 35 USC 112(b): Equivalent US clarity requirement
- Key difference: EPO applies stricter objective clarity standard

Cross-Jurisdiction Mapping

EPO (EPC)USPTO (35 USC)PCT
Art. 54 (Novelty)35 USC 102Art. 33(2)
Art. 56 (Inventive step)35 USC 103Art. 33(3)
Art. 83 (Sufficiency)35 USC 112(a) EnablementRule 5.1(a)(v)
Art. 84 (Clarity)35 USC 112(b)Rule 6.1
Art. 84 (Support)35 USC 112(a) Written desc.Rule 6.1
Rule 42 (Description)MPEP 608Rule 5
Rule 43 (Claims)37 CFR 1.75Rule 6
Rule 47 (Abstract)37 CFR 1.72Rule 8
Art. 52(2) (Exclusions)35 USC 101N/A
Art. 53(c) (Medical methods)N/A (allowed in US)N/A

Tools Available

  • Read: To load legal documents
  • Bash: To run legal search queries
  • Write: To save research results and legal memoranda

FAQ

What does the epc-search skill do?

RAG search across EPC provisions, EPO Guidelines for Examination, and PCT rules for European and international patent law research

How do I install epc-search?

Run npx skills add https://github.com/robthepcguy/claude-patent-creator --skill epc-search in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/epc-search/ (personal) or .claude/skills/epc-search/ (project).

Which AI agents can use epc-search?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is epc-search safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains epc-search?

It is published by robthepcguy in robthepcguy/claude-patent-creator. It has 51 recorded installs.

More from robthepcguy/claude-patent-creator

View all →

patent-application-creator

robthepcguy/claude-patent-creator

End-to-end patent campaign from ANY raw material ("here is some information; make a patent") to a filing-ready provisional package - invention mining, worth-it economics (design-around cost, detectability), exhaustive adversarial prior art, claims-first drafting, machine-verified compliance, hostile-examiner attack pass, and an honest no-go when nothing clears the bar or the fence is not worth the money

Testing & QA825 installs

patent-claims-analyzer

robthepcguy/claude-patent-creator

Automated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements - antecedent basis, definiteness, claim structure

Security451 installs

patent-diagram-generator

robthepcguy/claude-patent-creator

Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

Docs & Writing313 installs

prior-art-search

robthepcguy/claude-patent-creator

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification

Media & Creative247 installs

bigquery-patent-search

robthepcguy/claude-patent-creator

Fast, cloud-based patent searching across 100 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval

Data & Databases99 installs

patent-reviewer

robthepcguy/claude-patent-creator

Expert system for reviewing utility patent applications against USPTO MPEP guidelines.

86 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs