Patent Claims Analyzer

This analyzes patent claims for USPTO compliance before filing, checking antecedent basis errors (like using "said processor" before introducing it with "a/an"), definiteness issues under 35 USC 112(b) (subjective terms like "substantially"), and claim structure problems. It categorizes findings as critical, important, or minor, includes MPEP citations for each issue, and gives you a compliance score. The Python analyzer lives in the skill root and outputs structured JSON you can present as a report. Honestly most useful when you're cleaning up claims before submission or responding to office actions, since it catches the mechanical errors examiners flag routinely. Won't replace a patent attorney's judgment on scope or novelty, but it'll save you from embarrassing antecedent basis rejections.

skills.sh installs: 457
GitHub stars: 211
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add robthepcguy/claude-patent-creator --skill patent-claims-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

Patent Claims Analyzer Skill

Antecedent checking is disabled by default. Report it as skipped unless checks_run includes antecedent_basis; retain the reason in checks_skipped. Enabling PATENT_ENABLE_ANTECEDENT_CHECK=1 requires a server restart. Even when enabled, this is a low-confidence pattern check requiring manual review.

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:

Antecedent Basis Checking (opt-in):
- 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

SKILL.md on GitHub