Individual skill

svg-redraw-comparison

0upvotes

用参考图制作高精度 SVG 临摹绘制过程视频，交付纯 SVG 网页、独立 SVG 和原图对照 MP4。禁止 Canvas、位图嵌入与外链，按构图、线稿、固有色、阴影、高光、细节重放；横图上下、竖图左右合成。

templates/drawing-process/svg-redraw-comparison/SKILL.md

Read pinned source

Source commit 47cc68e1fe7a04213eb9aa53db9f08cb9a06d317

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 9
Repository last updated: Sep 18, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
anime Repository topic
comfyui Repository topic
minimax-h3 Repository topic
video-generation Repository topic
video-recipes Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

LICENSEasset · 1,088 bytes
LICENSES.mddoc · 998 bytes
README.mddoc · 2,523 bytes
SKILL.mdcore · 3,914 bytes
assets/manifest.jsonasset · 320 bytes
assets/reference.pngasset · 2,871,516 bytes
examples/demo.htmlasset · 30,779 bytes
examples/foundations.svgasset · 611,321 bytes
examples/preview.mp4asset · 3,362,255 bytes
examples/redraw.svgasset · 16,339,494 bytes
examples/regions.jsonasset · 6,863 bytes
examples/validation.jsonasset · 2,180 bytes
profile.jsonasset · 2,273 bytes
prompts/author-original.prompt.txtdoc · 1,186 bytes
prompts/redraw.prompt.txtdoc · 1,186 bytes
references/validation.mddoc · 1,228 bytes
references/workflow.mddoc · 5,162 bytes
scripts/_contours.pyruns · 1,313 bytes
scripts/_regions.pyruns · 1,191 bytes
scripts/_validate_svg.pyruns · 1,488 bytes
scripts/build_demo.pyruns · 6,071 bytes
scripts/clean_png.pyruns · 2,125 bytes
scripts/export_video.cjsruns · 6,237 bytes
scripts/package_demo.pyruns · 3,456 bytes
scripts/trace_reference.pyruns · 5,076 bytes
sources.mddoc · 1,710 bytes
tests/check_player.cjsruns · 3,981 bytes
tests/test_pipeline.pyruns · 4,290 bytes
web/load-art.jsruns · 3,269 bytes
web/player.cssasset · 738 bytes
web/player.jsruns · 2,326 bytes

Read excerpt


# 基于大模型的SVG临摹重绘

**完成条件：用户拿到对比视频、可播放 Demo 和完整 SVG。只完成 SVG 或网页不算任务完成。**

## 1. 固定输入与方式

实际读取用户本次参考图。只有用户未提供图片时，才使用本模板示例。先保存原件，再无损重编码并去元数据；核对解码像素和比例。使用用户指定的大模型；不可用时说明缺项，不冒称模型来源。

阅读[完整作者提示词](prompts/author-original.prompt.txt)和[工作步骤](references/workflow.md)。作者要求完整构图、比例、轮廓、色彩、线条、细节与图层；不能擅自改成简化风格稿。

## 2. 先完成静态重绘，再制作过程

优先让大模型以参考图为唯一视觉依据，编写原生 SVG 与自包含 HTML。SVG图层/元素使用语义化名称，保持viewBox比例。页面不含Canvas、image/img、Base64图片、外链、外部字体/框架/脚本；JS/CSS须内联。