visual-reverse-engineer
视觉逆向工程:从用户上传的图片或视频反向提取完整 Visual DNA,再重构出可复现原始视觉效果的图片/视频提示词。当用户要求「反推提示词」「逆向分析这张图」「照着这张图写提示词」「提取画面参数」「还原这张图」「分析这段视频的运镜」,或上传图片/视频要求生成 Prompt、Negative Prompt、分镜脚本时使用。Reverse-engineers an image or video into a structured Visual DNA and a reproducible image/video prompt. Works with Midjourney, Stable Diffusion, Flux, Seedance, Kling, Runway, Doubao and similar models.
Source facts
- Repository
- sundny8/visual-reverse-engineer
- Last source activity
- September 11, 2026 at 10:23
- Detected SKILL.md language
- Chinese
- Stars
- 5
- Forks
- 0
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
- name
- visual-reverse-engineer
- description
- 视觉逆向工程:从用户上传的图片或视频反向提取完整 Visual DNA,再重构出可复现原始视觉效果的图片/视频提示词。当用户要求「反推提示词」「逆向分析这张图」「照着这张图写提示词」「提取画面参数」「还原这张图」「分析这段视频的运镜」,或上传图片/视频要求生成 Prompt、Negative Prompt、分镜脚本时使用。Reverse-engineers an image or video into a structured Visual DNA and a reproducible image/video prompt. Works with Midjourney, Stable Diffusion, Flux, Seedance, Kling, Runway, Doubao and similar models.
- agent_created
- true