repo2patent

Analyze repository Skill units and generate structured YAML metadata.

63|12|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/bb-boy/repo2patent --skill repo2patent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repo2patent
Source: https://github.com/bb-boy/repo2patent/tree/main
Command: npx skills add https://github.com/bb-boy/repo2patent --skill repo2patent

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates turning GitHub repos into auditable patent disclosures and initial novelty analysis, reducing manual drafting time and enabling traceability.

Core Features & Use Cases

  • Automatic extraction of evidence and generation of structured disclosure content.
  • Early-stage retrieval, claims extraction, and novelty matrix for patent screening.
  • End-to-end workflow: from repo analysis to disclosure.docx and prior art outputs.

Quick Start

Provide a repository path or URL and run the Skill end-to-end to obtain disclosure.docx and prior_art outputs.

Frequently Asked Questions about repo2patent

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

FAQPage Schema
How do I automate patent disclosure drafting from a GitHub repository?

Automating patent disclosure drafting from a GitHub repository involves analyzing code to extract evidence and generating structured content. This process identifies repository units, verifies metadata, and outputs auditable disclosure documents and prior art.

Can I generate a novelty matrix for patent screening directly from source code?

Yes, generating a novelty matrix for patent screening from source code is possible. The system performs early-stage retrieval and claims extraction directly from the repository analysis to build this matrix.

Does generating a patent disclosure require a specific repository structure?

Generating a patent disclosure requires the repository to contain valid units with SKILL.md frontmatter, including name and description fields. The system classifies optional resources and assembles comprehensive metadata from these specific structural elements.

What is the best way to extract claims and prior art from code for a patent application?

The best way to extract claims and prior art from code is to run an end-to-end workflow on the repository path or URL. This automatically performs retrieval, claims extraction, and outputs a disclosure.docx and prior art.

Do I need python-docx to output the patent disclosure document?

Yes, python-docx is required as a dependency to output the patent disclosure document. It enables the automated generation of the disclosure.docx file from the analyzed repository evidence.

Why does the patent disclosure workflow require structured metadata extraction?

The patent disclosure workflow requires structured metadata extraction to ensure traceability and auditable novelty analysis. Identifying repository units and verifying frontmatter guarantees the generated disclosure is accurate and comprehensive.