skills.rest
Nitrogen216
Nitrogen216COMMUNITY
Explore all skills by this author →
GitHub

figure-description

Generates formal patent drawing descriptions and reference numeral indexes from user-provided figures.

Updated Aug 18, 2026
Search Tags:#claims#patent#drawings#intellectual property#figure description#reference numerals#附图说明
One-click install
npx skills add https://github.com/Nitrogen216/awesome-dsh-mods --skill figure-description-nitrogen216
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: figure-description
Source: https://github.com/Nitrogen216/awesome-dsh-mods/tree/main/modes/dsh-autoresearch/vendor/aris-upstream/skills/figure-description
Command: npx skills add https://github.com/Nitrogen216/awesome-dsh-mods --skill figure-description-nitrogen216

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Drafting patent applications requires formal drawing descriptions and consistent reference numerals mapped to claim elements, which is tedious and error-prone when done manually across multiple figures. ## Core Features & Use Cases - Figure Discovery and Analysis: Searches the project directory for PNG, JPG, SVG, and PDF figures, then identifies components, connections, and flows in each image. - Reference Numeral Assignment: Assigns numerals using a consistent 100-series convention (FIG. 1 uses 100-199, FIG. 2 uses 200-299) and reuses numerals for components appearing in multiple figures. - Claim Cross-Referencing: Maps every numeral to claim elements and flags missing figures or numerals that the claims require. - Use Case: A patent drafter with three technical diagrams and a CLAIMS.md file can generate CN-style 附图说明 or US/EP-style drawing descriptions plus a complete numeral index table in one pass. ## Quick Start Ask the agent to process the patent figures in the project directory and generate drawing descriptions with a reference numeral index mapped to the claims.

Frequently Asked Questions about figure-description

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

FAQPage Schema
How do I generate patent figure descriptions with reference numerals?▼

Provide your figure files (PNG, JPG, SVG, or PDF) in the project directory along with INVENTION_DISCLOSURE.md and CLAIMS.md. The skill analyzes each image, assigns numerals in 100-series per figure, and writes figure_descriptions.md and numeral_index.md under patent/figures/.

What reference numeral convention do patent drawings use?▼

This skill assigns each figure its own 100-series range: FIG. 1 uses 100-199, FIG. 2 uses 200-299, and so on. Components appearing in multiple figures keep the same numeral across all figures for consistency.

Does it support Chinese patent drawing descriptions?▼

Yes, it generates CN jurisdiction descriptions in the formal 附图说明 style (e.g., 图1是...的系统结构示意图) as well as English US/EP style descriptions such as 'FIG. 1 is a block diagram illustrating...'.

Can it modify or annotate my original patent figures?▼

No, the skill explicitly does not modify user-provided figures. It only reads and describes them, assigning reference numerals in the accompanying documentation rather than editing the image files.

What happens if a claim element has no corresponding figure?▼

The skill flags gaps during cross-referencing with markers like [MISSING FIGURE: description needed] or [MISSING NUMERAL], so you know exactly which claim elements still need diagrams or numeral assignments.

Related Skills

Explore More Legal & Compliance Skills→
Shallow-WShallow-W

figure-description

Generate patent drawing descriptions and reference numeral indexes from figure files.

Community
Advanced
lightrain-alightrain-a

specification-writing

Generate a patent specification in Markdown from claims and invention disclosure.

Community
Advanced
echo-iceecho-ice

completeness-auditor

Verify completed skills have audit artifacts with at least five pass items.

Community
Advanced
kitcafkitcaf
1

paper-figure

Generate publication-ready plots, multi-panel figures, and LaTeX tables from experimental data.

Community
Advanced