qinghu-ai skillA
qinghu-ai is agent-read markdown (skill) from autoagc/linkpix-skills: 调用青虎 AI 媒体能力:AI 生图(套图/电商详情图/自定义生图家族实时清单:智慧模型、图片 5.0 Lite、专图模型、图片 5.0 Pro 等 + 提示词润色)、批量生图玩法(批量生图/批量改图/批量替换/主图复刻/姿势套图/批量译图)、AI 生视频(模型清单实时读取线上目录,含 Seedance2.5、Seedance2.0、阿里wanx3.0、MiniMax H3、全能电商2.0、Happy Horse、可灵3.0 Omni、品牌质感大片等多模型多时长 5–30 秒,支持多参考视频与参考音频)、一键成片、角色替换/模特换脸、视频翻译、去水印/去字幕/画质提升、复刻爆款视频出脚本、爆款视频转图文、分镜脚本与分镜图、广告素材模板批量出片(视频/图片)、POD 印花素材(印花提取/贴合/裂变 + 产品图库)、青虎工作台「AI 应用」的 AI 工作流(电影质感 TVC 广告大片、爆款视频模仿与仿拍、模特换装高一致性还原、超清修复与去 AI 感、图像去水印、短视频与达人数据引擎),均含任务状态查询。当用户要求生成/制作商品图、主图、详情图、营销图、广告视频、带货视频、口播视频,或要求批.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# 青虎AI 青虎AI 是青虎工作台的全栈电商内容生产能力:从商品图、主图、详情页、电商套图,到批量修图、广告投放素材、带货视频与电影质感 TVC 广告大片;从 POD 印花、视频翻译与视频编辑,到爆款复刻、视频转图文、分镜创作及短视频/达人数据分析,均可在一个入口完成。 它不是单一的生图或生视频模型,而是把“做图 → 做视频 → 翻译与优化 → 复刻与分析”串成闭环的 AI 电商素材工作流。生图与生视频模型按线上实时目录选择,可响应用户对豆包生图、Seedream 5.0、Seedance、阿里万相 Wanx、MiniMax H3、可灵、HappyHorse、Vidu 等模型的使用需求。 ## 0. 意图路由:用户想要什么 → 用哪个命令 | 用户意图(示例说法) | 命令 | 产物 | |---|---|---| | 生成商品图/主图/套图、"给这张图做几张营销图" | `image`(套图模式) | 图片 | | 按文字描述直出一张商业大图(可带参考图) | `image`(自定义生图家族,实时清单:智慧模型 / 图片 5.0 Lite / 专图模型 / 图片 5.0 Pro 等,`uploadedImages` 可选) | 图片 | | 生成电商详情页长图 | `image`(电商详情图) | 图片 | | "帮我写一条生图提示词"、按商品图/卖点出提示词 | `image`(`polish`) | 提示词文本 | | 一张产品图 × 多条提示词各出一张、"批量出 N 张不同的图" | `image-batch`(批量生图) | 图片 | | 多张图批量执行同一条修改指令(如批量白底图) | `image-batch`(批量改图) | 图片 | | "把我的产品换进这些参考图里" | `image-batch`(批量替换) | 图片 | | "照这张爆款主图的风格,给我的产品做主图" | `image-batch`(主图复刻) | 图片 | | 服装图出多姿势模特套图 | `image-batch`(姿势套图) | 图片 | | 翻译图片上的文字(批量译图) | `image-batch`(批量译图) | 图片 | | 做广告视频/产品视频(有参考图) | `video` | 视频 | | "把这几张图做成一条带货视频"、一键成片 | `video-quick` | 视频 | | 换人/换模特/换脸(对已有视频) | `video-replace` | 视频 | | 翻译视频、配外语音、加外语字幕 | `video-translate` | 视频 | | 去水印 / 去字幕 / 画质提升(超分) | `video-edit` | 视频 | …
Read the whole file at its exact version.
How to install
mdr add autoagc/linkpix-skills/qinghu-ai@git:20260918.ed5b0abmdr add autoagc/linkpix-skills/qinghu-ai@sha256:833ebbddcbd9fda5Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_o4m6f6wq6tyva5ff)
1 badge views in 30 days
Versions
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 (41019 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
autoagc/linkpix-skills · 14 stars · license MIT · pushed 2026-09-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_o4m6f6wq6tyva5ff GET https://markdownregistry.com/api/v1/resolve?ref=autoagc/linkpix-skills/qinghu-ai GET https://markdownregistry.com/api/v1/blob/833ebbddcbd9fda5ca3c93f461abe07e078706c21893f382be1bfd1f6ed0c5fc
Your agent 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.