beauty-video-gen SKILL.md skillA
beauty-video-gen 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/beauty-video-gen@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/beauty-video-gen/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260911.3d58d1d, committed Sep 11, 2026
- First version recorded
- Sep 2, 2026
- Size
- 25,871 bytes
- Repository stars
- 40
- License
- a license file GitHub does not identify
生成超写实、真实感、亲近感的美女时尚竖屏短视频（MiniMax H3 云端生成）。当用户要求"生成美女视频 / 真实感美女 / 亲近感美女视频 / 美女短视频 / 时尚美女视频 / 定制美女视频"，或用"可爱、亲切、性感、清纯、轻熟"等风格词，或用"夸张身材 / 大长腿 / 丰满身材 / 腿占画面大半 / 低机位拉腿"等身材词要求生成真人女性视频时使用；即使用户没提"美女"二字，只要是"生成真人女性出镜的短视频"也应触发。整合《真人时尚短视频提示词写作框架》提示词写作、可选的人物面部参考图生成（仅用户明确要求"先定脸/出面部参考图"时执行，默认直接文生视频；生图优先用当前 Agent 自带的生图能力，备选 cursor-image-gen）、minimax-h3 全流程（AutoDL 开关机、工作流发现、提交轮询、本地归一化、抽帧验收）。.
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
# Skill: beauty-video-gen # 真实感·亲近感美女视频生成 生成超写实、真实感、亲近感的美女时尚竖屏短视频：按《真人时尚短视频提示词写作框架》写提示词， 可选先用人像生图定脸，再用 `minimax-h3` 技能在云端 GPU 上出片，最后本地归一化与抽帧验收。 ## 触发场景 用户要求"生成美女视频 / 真实感美女 / 亲近感美女视频 / 美女短视频 / 时尚美女视频"， 或用"可爱 / 亲切 / 性感 / 清纯 / 轻熟"等风格词，或用"夸张身材 / 大长腿 / 丰满 / 拉腿"等 身材词要求生成真人女性视频时使用（身材词命中时走 Step 3.5 夸张身材批量配方）。 ## 总流程 ```text 用户提需求 → [用户已自带参考图?] ──是──→ 直接进入 Step 3（Ref2VA 模式） → [用户明确要求先生成面部参考图?] ──否──→ 直接进入 Step 3（T2VA 模式，默认不出参考图、不询问） → ──是──→ Step 2 生成面部参考图 → 展示 → 询问是否修改（循环直到用户满意） → Step 3 按框架写 H3 提示词 → Step 4 minimax-h3 云端生成（开机→发现→提交→轮询→下载→秒级校验→**立即关机**） → Step 5 本地归一化 + 抽帧验收（关机后本地做） → Step 5.5 默认提亮 + 皮肤光泽滤镜（关机后本地做） → Step 6 交付 ``` ## Step 0 收集需求 从用户消息中提取；未提及的用默认值并告知用户，不要反复追问： | 项 | 默认值 | 说明 | |---|---|---| | 风格 | 可爱 + 亲切 + 性感（色情擦边零容忍，性感=露肩锁骨/S曲线/细高跟等 tasteful 表达） | 用户词原样保留进提示词意图 | | 画幅 | 9:16 竖屏 720×1280 | 用户要 1080P 时用 1080×1920 | | 时长 | 10 秒（5–15 内按动作量定） | 单场景 6–8 个动作节拍 ≈ 10s（轻快节奏）；H3 只支持 5–15s | | 动作节奏 | 轻快真实生活速度（每拍 1.2–1.5s，主动作用 quickly/briskly 连接） | 2026-08-28 实测：慢速少拍版被用户差评"动作很慢不像正常人"；快节奏版获明确认可，见 Step 3 第 6 条 | | 画面亮度 | 高调明亮布光 + 交付前默认跑 Step 5.5 提亮滤镜，滤镜版为推荐成片 | 提示词层写 bright airy high-key 场景，滤镜层再抬亮度与皮肤光泽 | …
Read the whole file at its exact version.
How to install
mdr add mini-yifan/open-source-video-gen-skill/beauty-video-gen@sha256:ee159886ad56c868The 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_cx3pzvboneaglaph)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 2, 2026 and Sep 11, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260911.3d58d1d latest | 2026-09-11 | 3d58d1d | 25,871 B | A | view · diff |
| git:20260902.18c321c | 2026-09-02 | 18c321c | 25,629 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 (25871 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_cx3pzvboneaglaph GET https://markdownregistry.com/api/v1/resolve?ref=mini-yifan/open-source-video-gen-skill/beauty-video-gen GET https://markdownregistry.com/api/v1/blob/ee159886ad56c8689940101bcf6edf88bdda8cd18c485f50e223caabd2d44a30
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.