patent-figure

Generate and refine USPTO-style patent figures from markdown files.

10|1|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/pbc-os/agent-skills-public --skill patent-figure
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: patent-figure
Source: https://github.com/pbc-os/agent-skills-public/tree/main/skills/tier-x-experimental/patent-figure
Command: npx skills add https://github.com/pbc-os/agent-skills-public --skill patent-figure

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation and refinement of formal USPTO-style patent figure drawings, a critical but time-consuming part of the patent application process.

Core Features & Use Cases

  • Automated Generation: Creates patent figures from provisional patent application markdown files.
  • Iterative Refinement: Allows for targeted, single-fix edits to improve existing figures.
  • Use Case: Generate FIG. 1 for your new invention's system architecture, ensuring it meets all USPTO drawing standards, and then make a specific arrow adjustment based on attorney feedback.

Quick Start

Generate FIG. 1 for my patent application using the provisional file located at ~/patents/my_invention.md.

Frequently Asked Questions about patent-figure

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate USPTO-style patent figures from a markdown file?

Iterative patent figure refinement allows targeted single-fix edits to existing drawings, enabling you to make specific adjustments like arrow corrections based on attorney feedback without regenerating the entire illustration.

What is the best way to ensure my patent drawings meet USPTO drawing standards?

The best way to meet USPTO drawing standards is to assess generated patent figures against strict USPTO style guidelines, ensuring your intellectual property illustrations comply with formal application requirements automatically.

Can I make targeted single-fix edits to an existing patent illustration?

Yes, you can make targeted single-fix edits to an existing patent illustration, allowing specific adjustments like arrow corrections based on attorney feedback without regenerating the entire drawing.

Do I need the Gemini API and nano-banana skill to create patent drawings?

Yes, creating patent drawings requires the Gemini API and nano-banana skill to build structured prompts and assess generated images against strict USPTO style guidelines for compliance.

How does automated patent figure generation handle reference numerals?

Automated patent figure generation parses your markdown files to extract reference numerals, incorporating them into structured prompts so the generated drawings accurately label the described invention components.