patent-assistant

name	patent-assistant
title	Patent Technical Disclosure Document
description	Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty.
author	aipoch
author_url	https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Academic Writing/patent-assistant
license	MIT
version	0.1.0
execution_mode	open
jurisdiction	general
practice	ip
language	en

Source: https://github.com/aipoch/medical-research-skills

When to Use

Use this skill in the following scenarios:

1. Drafting a patent technical disclosure from an inventor’s informal or incomplete technical description.
2. Structuring an invention description into standard patent-style sections (field, background, summary, embodiments, drawings).
3. Preparing for a novelty search by extracting keywords, synonyms, and IPC suggestions from a technical solution.
4. Finding related patents and producing a similarity comparison against the user’s key technical features.
5. Improving patent readiness by identifying missing technical details and proposing claim-writing directions (non-legal, for drafting support).

Key Features

• Converts colloquial technical descriptions into a structured patent technical disclosure document.
• Uses a guided information-collection checklist to fill gaps (problem, prior art defects, core solution, features, effects).
• Generates a disclosure with a consistent section template (Title, Field, Background, Summary, Detailed Description, Drawings, Keywords).
• Performs multi-platform patent search orchestration via a CLI script and supports optional similarity analysis.
• Produces novelty-oriented analysis: similarity ranking, key-feature comparison, and preliminary novelty judgment.
• Provides post-draft optimization suggestions (claim directions, expansion ideas, missing details to supplement).

Dependencies

• Python >= 3.9
• (Optional, if enabled by the project) Common Python packages for HTTP parsing and analysis, such as:
  • requests >= 2.28
  • beautifulsoup4 >= 4.11
  • lxml >= 4.9

Note: Exact runtime dependencies may vary depending on how scripts/patent_search.py is implemented in your repository.

Example Usage

1) Generate a Patent Technical Disclosure Document

User prompt

Help me write a patent disclosure document:
I designed a system that uses an on-device model to detect abnormal vibration patterns in industrial motors.
It compresses sensor streams, runs anomaly detection locally, and only uploads event snippets to reduce bandwidth.