character-three-view SKILL.md skillA
character-three-view from mini-yifan/open-source-video-gen-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mini-yifan/open-source-video-gen-skill/character-three-view@git:20260911.3d58d1dPins git:20260911.3d58d1d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mini-yifan/open-source-video-gen-skill
- Path
skills/character-three-view/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260911.3d58d1d, committed Sep 11, 2026
- First version recorded
- Sep 2, 2026
- Size
- 5,489 bytes
- Repository stars
- 40
- License
- a license file GitHub does not identify
Prepares reference art for video production from a script or asset list: character reference sheets (including outfit-state variants), prop references, and scene concept images, then verifies each generated image. Works for any project style — photoreal, anime, cartoon, fantasy creatures. Use when the user asks for 美术设定集, 人物三视图, 道具三视图, 场景概念图, 角色立绘, or visual refs before video. Prefer the running agent's own image generation tool (e.g. Codex ImageGen); use cursor-image-gen only when no native…
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
# 美术参考图
从剧本或资产清单抽出需要锁定的形象资产（人物/形象、关键道具、主要场景），生成给后续视频当参考的设定图，逐张验收。本技能不规定每张图的版式与画法，只沉淀生图执行方式和这个环节踩过的坑。
## 出什么图
三类资产，共同目的都是给视频模型当外观与场景的锁定参考：
- **人物三视图**：把同一角色放进同一张图——常见做法是全身的正面、侧面、背面，外加一个面部特写；视频模型靠它从任意机位认出同一个人。用几个角度、怎么排布、什么背景，按项目需要定；核心是"一张图 = 一个角色的完整外观档案"。
- **道具三视图**：同一件关键道具的多个视角（大件可改用关闭/半开/打开等多个状态）放进同一张图，让道具在生成视频里保持同一外观。
- **场景概念图**：主要地点的单幅环境图，只画场景、不进主要角色（原因见坑 4）。
参考图画幅建议与成片一致（竖屏剧的场景图就用竖幅），避免模型从参考图学到错误构图；用户或项目已有样例图时，版式跟样例走。
## 生图工具
不绑定唯一 API。用户点名生图工具时以点名为准（点名 Cursor 即用 `cursor-image-gen`）；未点名时按默认顺序：
1. **当前 Agent 自带的生图能力（首选）**：环境自带生图工具或技能（如 Codex 的 ImageGen）就直接用；有样例或已有图就把图作为参考图传给生图工具。
2. **`cursor-image-gen`（备选）**：环境没有自带生图能力时，读 [`cursor-image-gen`](../cursor-image-gen/SKILL.md) 生成，可用 `reference_image_paths`。
3. **Seedream（可选兜底，本仓库不附带）**：默认执行器被拦截、拒生、重试后仍不合格，或需要精确像素/多张本地参考图时，若本机另装了 `seedream-image-gen`（常见路径 `~/.cursor/skills/seedream-image-gen/SKILL.md`），再读它生成。没有该技能就停下来告诉用户，不要假装已安装。
生成后把文件放进设定集目录（如 `美术设定集/{人物三视图, 道具三视图, 场景概念图}/`），统一按 `NN_名称.jpg` 命名。
## 踩过的坑
1. **参考图质感会被视频模型继承进成片**。动手前先从用户需求或 Brief 确认项目质感——写实、动漫、Q 版、幻想生物都可以——所有参考图与目标质感保持一致，不要混风格。
…Read the whole file at its exact version.
How to install
mdr add mini-yifan/open-source-video-gen-skill/character-three-view@sha256:0ab2d47775225937The line at the top of this page pins the label git:20260911.3d58d1d, 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_4pv4xxoua4ecph3g)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 2, 2026 and Sep 11, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260911.3d58d1d latest | 2026-09-11 | 3d58d1d | 5,489 B | A | view · diff |
| git:20260906.fe772b9 | 2026-09-06 | fe772b9 | 5,268 B | A | view · diff |
| git:20260904.ec83cad | 2026-09-04 | ec83cad | 6,808 B | A | view · diff |
| git:20260902.9f33575 | 2026-09-02 | 9f33575 | 6,511 B | A | view · diff |
| git:20260902.e686e77 | 2026-09-02 | e686e77 | 5,372 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 (5489 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
mini-yifan/open-source-video-gen-skill · 40 stars · license a license file GitHub does not identify · pushed 2026-09-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4pv4xxoua4ecph3g GET https://markdownregistry.com/api/v1/resolve?ref=mini-yifan/open-source-video-gen-skill/character-three-view GET https://markdownregistry.com/api/v1/blob/0ab2d477752259373406ff5e86c9d9ad2ee9badc0e3c5dd2917c3c3857825d74
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.