{"skill":{"slug":"scientific-drawing-skill-1-0-0","displayName":"scientific-drawing-skill-1-0-0","summary":"基于 AutoFigure-Edit 的科研级科学插图生成与编辑系统，能够从长篇方法描述自动生成完全可编辑的矢量图（SVG），支持参考图风格迁移和浏览器内交互式编辑","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":75,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775617641918,"updatedAt":1775618507695},"latestVersion":{"version":"1.0.0","createdAt":1775617641918,"changelog":"Editable SVG Output: No longer generates static PNGs; instead, produces fully editable SVG files.\nStructured Components: Every icon, module, and connector is an independent, editable object.\nVector Precision: Infinitely scalable without quality loss, perfectly suited to academic publishing requirements.\n\nIntelligent Style Transfer:\nUpload a style reference image, and the AI automatically learns the color palette, typography, and icon style.\nMaintains visual consistency with a laboratory or journal’s design language.\n\nBuilt-in Interactive Editor:\nImmediately enters a visual editing interface after generation.\nSupports drag-and-drop operations to adjust layouts, modify annotations, and replace icons.\nWhat-you-see-is-what-you-get, with undo/redo support.\n\nFive-Stage Generation Pipeline:\nStyle-conditioned image generation → SAM3 segmentation and structural indexing → asset extraction → SVG template generation and refinement → asset injection","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"davidzhao30","userId":"s17fgb9z7nj3vcwed282fbayys84em7k","displayName":"davidzhao30","image":"https://avatars.githubusercontent.com/u/253612501?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775618507695}}