textile-toy-portrait SKILL.md skillA
textile-toy-portrait from vieeeeeee/wibi-style is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vieeeeeee/wibi-style/textile-toy-portrait@git:20260903.85c2c02Pins git:20260903.85c2c02 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vieeeeeee/wibi-style
- Path
skills/textile-toy-portrait/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260903.85c2c02, committed Sep 3, 2026
- First version recorded
- Aug 21, 2026
- Size
- 6,806 bytes
- Repository stars
- 169
- License
- a license file GitHub does not identify
Wibi Style 官方视觉风格。把用户上传的真实照片转换成颗粒绒感玩偶肖像。只要用户提到颗粒绒感玩偶、纺织玩偶、绒面针织头像、把照片做成玩偶，或明确调用 $textile-toy-portrait，就使用本 Skill；先理解照片内容，再动态选择风格参考职责并直接生成成图。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Wibi Style · 颗粒绒感玩偶 ## 运行 先按 [references/community.md](references/community.md) 展示欢迎卡、检查更新并处理进群与失败提示，再执行下面的步骤。 ## 风格目标 把真实照片重构成白底棚拍的 3D 纺织设计玩偶肖像：头部横向放大、身体压缩，五官缩成少量圆角几何零件；脸、手和小零件使用细密短颗粒绒，头发、帽子和衣服使用可见线圈、团簇和粗针织。画面要像一件被设计出来的玩偶，保留人物或角色的辨识度，不是把写实照片简单覆上一层绒面。 固定风格机制按优先级执行： 1. 用户照片的内容权最高：人数、身份、身体部位、姿态、表情、发型、配饰、物件和接触关系只从用户照片判断。 2. 先保证主体关系和可辨识锚点，再做玩偶化比例与几何重构。 3. 再用颗粒绒与粗针织的材质对比、白底棚拍和 3–5 色的主次关系完成风格成像。 4. 颜色可以在非身份区域重新组织；照片不存在的道具、身体、手势、文字和 Logo 不得因为参考图而出现。 ## 影像蒸馏 先完整阅读用户照片，不急着套风格词。判断当前照片属于单人头像、头肩照、半身照、带手部动作的人物照，还是包含帽子、眼镜、饮料罐等强物件锚点的角色照。记录最重要的一至两个主体、人数、可见身体范围、头部方向、眼神和表情、物件接触关系、画面裁切和视觉重量。 从照片中提取 2–5 个身份锚点，优先选择轮廓大、位置稳定、能在小尺寸玩偶里成立的特征，例如发型大形、眼镜或帽子轮廓、表情方向、手与脸/物件的接触、衣服的主色块或独特配饰。夸张其中 1–2 个，其余简化。真实照片没有露出的手、手臂、腿脚或道具不补画；只有局部露出的身体也只保留局部。 将照片里容易被风格破坏的关系写成当前成图的检查锚点：手的数量、手与脸或物件的接触、眼神方向、嘴的开合、帽子与头发的前后层级、眼镜与脸的相对位置。背景复杂时安静删去，但不能用删背景的名义改变主体内容。 ## 参考选择与风格成像 本 Skill 内置的 `assets/references/reference-01.jpeg` 是共同风格锚点，主要负责：横向圆角大头、极小集中五官、脸部留白、颗粒绒表面、粗针织团簇、微暖白棚拍和珊瑚/薄荷/奶油一类的主次色彩关系。它不负责人物身份、性别、动作、帽子、眼镜、服装、道具或具体颜色。 生成时把用户照片作为内容输入，同时携带这张内置参考；附件顺序不代表角色。明确告诉图像模型：用户照片决定画什么，参考图只决定怎么画。不要把参考角色的卷发、帽子、衣服、手势或脸型搬过来；只有用户照片确实存在的同类元素才允许被重构。 根据当前照片动态决定成像方式： - 头肩或头像：使用紧凑的正面或轻微侧面胸像，头部约占画面宽度 75%–90%，保留一小块必要衣领或动作。 …
Read the whole file at its exact version.
How to install
mdr add vieeeeeee/wibi-style/textile-toy-portrait@sha256:639a695813b303c9The line at the top of this page pins the label git:20260903.85c2c02, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6xwl7eoz4r4bnpkt)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 21, 2026 and Sep 3, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260903.85c2c02 latest | 2026-09-03 | 85c2c02 | 6,806 B | A | view · diff |
| git:20260821.48ddb00 | 2026-08-21 | 48ddb00 | 9,243 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6806 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
vieeeeeee/wibi-style · 169 stars · license a license file GitHub does not identify · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6xwl7eoz4r4bnpkt GET https://markdownregistry.com/api/v1/resolve?ref=vieeeeeee/wibi-style/textile-toy-portrait GET https://markdownregistry.com/api/v1/blob/639a695813b303c95aa00d67450e7e90399b8867aa2ed114dced04e82b43493e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.