Image to Prompt
Analyze one or more reference images and reconstruct faithful, reusable image-generation prompts in Chinese and English. Use when users want to reverse-engineer, infer, restore, imitate, or write prompts from visual references.
Install
npx skills add jiemianduan/image-to-prompt --skill image-to-promptgit clone --depth 1 https://github.com/jiemianduan/image-to-prompt.git /tmp/image-to-prompt
mkdir -p ~/.claude/skills
cp -r /tmp/image-to-prompt/. ~/.claude/skills/image-to-promptPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Image to Prompt Reconstruct prompts from visible evidence. Describe what can be reproduced, distinguish observation from inference, and never pretend to know the original prompt, seed, model, lens, or generation settings. ## Workflow 1. Confirm that at least one usable image is available. If not, ask the user to upload it. 2. Inspect the image at the highest available detail. For a local file, use the image-viewing tool before analyzing it. 3. Identify the image category: photograph, illustration, anime, 3D render, product image, poster/editorial graphic, UI, architecture/interior, or mixed media. 4. Decompose the image using the analysis order below. 5. Resolve the user's target: - Default: produce a model-neutral reconstruction prompt. - If a model is named, adapt syntax and parameter suggestions to that model. - If the user wants only the prompt, keep analysis brief but still perform it internally. - For every image, also produce a complete editable version of the prompt. Keep the standard Chinese and English prompts concrete so they remain usable without editing. 6. Produce the output in the prescribed format. 7. State material uncertainty only when it affects reproducibility. ## Analysis Order Prioritize high-impact visual facts: 1. **Subject and action** — identity category, count, pose, expression, interaction, clothing, props.
Details
- Skill name
image-to-prompt- Repository
- jiemianduan/image-to-prompt
- License
- MIT
- Repo updated
- 7 August 2026
FAQ
What does the Image to Prompt skill do?
Analyze one or more reference images and reconstruct faithful, reusable image-generation prompts in Chinese and English. Use when users want to reverse-engineer, infer, restore, imitate, or write prompts from visual references.
How do I install the Image to Prompt skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add jiemianduan/image-to-prompt --skill image-to-prompt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Image to Prompt popular?
It lives in jiemianduan/image-to-prompt, which has 34 GitHub stars and 3 forks.
Related skills
FigFox Gen Skill
33LawrenceRiver/FigFox-Gen-skill
Use when turning a scientific Methodology, with an optional reference image, into one evidence-grounded, human-editable final PNG figure.
Animated Sketch Diagram
31OLDyade/animated-sketch-diagram
生成"黑墨手绘涂鸦"风格的动画架构图/流程图：米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML（SVG+CSS），可一键导出无缝循环 GIF。当用户想画架构图、流程图、信息图、技术示意图、对比图、pipeline/workflow 可视化，或提到"手绘风""涂鸦风""动图""animated diagram""GIF 架构图"时使用；即使用户没明说要动画，做技术概念科普配图时也应优先考虑本 skill。
Blender Claymation
28angrypenguinpng/blender-claymation-skill
Make stop-motion claymation videos in Blender from a one-line idea. Builds a miniature clay set and puppet in Python, animates it "on twos" at 12 fps with hand-made boil, renders with Cycles, encodes an mp4, and presents it in a video player. Use when the user asks for a claymation, stop-motion, plasticine or clay animation, a clay character or short film made in Blender, or "an animation that looks like a real studio made it".
Factory
32AirsupHQ/factory-skill
Turn a one line description of a factory ("a line that makes 2,000 e-bike motors a day", "a bakery that bakes 10,000 croissants an hour", "a battery cell gigafactory") into a single self-contained HTML page with a live 3D tilt-shift miniature of that factory, driven by a real discrete event simulation (stations, cycle times, batches, finite buffers, shifts, breakdowns, scrap) with a live HUD for throughput against target, takt, utilization, WIP, lead time and the bottleneck, where clicking a station lets you add a machine or change a cycle time and watch the bottleneck move. Use it whenever so
Live2d Halfbody
29bellisji233/live2d-halfbody-skill
从一张立绘或一段角色描述，做出能在 VTube Studio 里直播用的半身 Live2D 皮套，不用手动建模、不开 Cubism Editor：图像模型出图、See-through 拆层、代码补细节和绑定、自查后装进 VTS。默认带小角度转头、歪头、身体跟随、呼吸、眨眼和单眼眨眼、口型、四个表情、头发分段摆动（短发、过肩长发或双马尾，刘海可有可无，侧发可别在耳后）、挂件和耳坠摆动、眼镜、招手/摊手/指向三个手势和脸红。用于用户想新做一个皮套（有立绘、只有描述、或已有分层文件）、检查皮套素材、或调整已有角色的动作幅度时。Builds a half-body Live2D avatar for VTube Studio from one character illustration or a text description.
Interflow Video Cut
33derek-zhuolin/interflow-video-cut
Turn a local talking-head / 口播 video into metadata, transcript, and an AI-composed card-based video where the agent composes cards by cloning styled templates and filling them (designing bespoke only when content needs it), then renders to MP4. Ships with the Interflow AI club sign-off ("Interflow AI 出品"). Use when the user asks for interflow-video-cut, 口播成片, talking-head repurposing, video takeaways, transcript cleanup, or turning a spoken video into a captioned card video.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.