Back to Skills

patent-claims-analyzer

RobThePCGuy
Updated Today
32 views
2
2
View on GitHub
Designaiautomationdesign

About

This skill analyzes patent claims for USPTO compliance, specifically checking for antecedent basis and definiteness under 35 USC 112(b). Use it to automatically review claim structure, identify drafting issues like missing term introductions, and validate claims before filing. It performs automated checks across claims to flag subjective language and improper references.

Documentation

Patent Claims Analyzer Skill

Automated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements.

When to Use

Invoke this skill when users ask to:

  • Review patent claims for definiteness
  • Check antecedent basis in claims
  • Analyze claim structure
  • Find claim drafting issues
  • Validate claims before filing
  • Fix USPTO office action issues related to claims

What This Skill Does

Performs comprehensive automated analysis:

  1. Antecedent Basis Checking:

    • Finds terms used without prior introduction
    • Detects missing "a/an" before first use
    • Identifies improper "said/the" before first use
    • Tracks term references across claims
  2. Definiteness Analysis (35 USC 112(b)):

    • Identifies subjective/indefinite terms
    • Detects relative terms without reference
    • Finds ambiguous claim language
    • Checks for clear claim boundaries
  3. Claim Structure Validation:

    • Parses independent vs. dependent claims
    • Validates claim dependencies
    • Checks claim numbering
    • Identifies claim type (method, system, etc.)
  4. Issue Categorization:

    • Critical: Must fix before filing
    • Important: May cause rejection
    • Minor: Best practice improvements

Required Data

This skill uses the automated claims analyzer from: Location: ${CLAUDE_PLUGIN_ROOT}/python\claims_analyzer.py

How to Use

When this skill is invoked:

  1. Load the claims analyzer:

    import sys
    sys.path.insert(0, os.path.join(os.environ.get('CLAUDE_PLUGIN_ROOT', '.'), 'python'))
    from python.claims_analyzer import ClaimsAnalyzer
    
    analyzer = ClaimsAnalyzer()
    
  2. Analyze claims:

    claims_text = """
    1. A system comprising:
        a processor;
        a memory; and
        said processor configured to...
    """
    
    results = analyzer.analyze_claims(claims_text)
    
  3. Present analysis:

    • Show compliance score (0-100)
    • List issues by severity (critical, important, minor)
    • Provide MPEP citations for each issue
    • Suggest specific fixes

Analysis Output Structure

{
    "claim_count": 20,
    "independent_count": 3,
    "dependent_count": 17,
    "compliance_score": 85,  # 0-100
    "total_issues": 12,
    "critical_issues": 2,
    "important_issues": 7,
    "minor_issues": 3,
    "issues": [
        {
            "category": "antecedent_basis",
            "severity": "critical",
            "claim_number": 1,
            "term": "said processor",
            "description": "Term 'processor' used with 'said' before first introduction",
            "mpep_cite": "MPEP 2173.05(e)",
            "suggestion": "Change 'said processor' to 'the processor' or introduce with 'a processor' first"
        },
        # ... more issues
    ]
}

Common Issues Detected

  1. Antecedent Basis Errors:

    • Using "said/the" before "a/an" introduction
    • Terms appearing in dependent claims not in parent
    • Missing antecedent in claim body
  2. Definiteness Issues:

    • Subjective terms: "substantially", "about", "approximately"
    • Relative terms: "large", "small", "thin"
    • Ambiguous language: "and/or", "optionally"
  3. Structure Issues:

    • Means-plus-function without adequate structure
    • Improper claim dependencies
    • Missing preamble or transition

Presentation Format

Present analysis as:

CLAIMS ANALYSIS REPORT
======================

Summary:
- Total Claims: 20 (3 independent, 17 dependent)
- Compliance Score: 85/100
- Issues Found: 12 (2 critical, 7 important, 3 minor)

CRITICAL ISSUES (Must Fix):

[Claim 1] Antecedent Basis Error
  Issue: Term 'processor' used with 'said' before introduction
  Location: "said processor configured to..."
  MPEP: 2173.05(e)
  Fix: Change to 'the processor' or introduce with 'a processor' first

[Claim 5] Indefinite Term
  Issue: Subjective term 'substantially' without definition
  Location: "substantially similar to..."
  MPEP: 2173.05(b)
  Fix: Define 'substantially' in specification or use objective criteria

IMPORTANT ISSUES:
...

MINOR ISSUES:
...

Integration with MPEP

For each issue, the skill can:

  1. Search MPEP for relevant guidance
  2. Provide specific MPEP section citations
  3. Show examiner guidance on similar issues
  4. Suggest fixes based on USPTO practice

Tools Available

  • Read: To load claims from files
  • Bash: To run Python analyzer
  • Write: To save analysis reports

Quick Install

/plugin add https://github.com/RobThePCGuy/Claude-Patent-Creator/tree/main/patent-claims-analyzer

Copy and paste this command in Claude Code to install this skill

GitHub 仓库

RobThePCGuy/Claude-Patent-Creator
Path: skills/patent-claims-analyzer
bigqueryclaude-codeclaude-code-pluginfaissmcp-servermpep

Related Skills

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill