laohan-fenjingtishici skillA
laohan-fenjingtishici is agent-read markdown (skill) from hanzhcn/laohan-skills: 生成专业分镜图片提示词，适配扩散模型（FLUX/SDXL/Gemini）。校验质量后拆分为独立文件，或直接生成带产品描述的 Gemini 提示词模板。Use when 用户说"生成分镜提示词""校验分镜""拆分镜""分镜""分镜图"或提到视频分镜/镜头提示词/产品分镜模板。.
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
# 分镜提示词生成与校验
为产品带货/短视频生成分镜图片提示词，并校验输出质量。
## 不适用场景
- 生成视频本身 → 这是分镜图片提示词，不是视频生成
- 生成封面图 → 用 laohan-fengmianqiuzhi
- 生成口播稿 → 用 laohan-chuangzuo
- 没有产品描述 → 模式1必须提供产品视觉描述才能生成
## 使用
```
# 模式1：生成 Gemini 提示词模板
/laohan-fenjingtishici <视频秒数> <产品视觉描述>
# 模式2：校验并拆分 Gemini 返回的分镜
/laohan-fenjingtishici <用户粘贴的 Gemini 输出>
```
## 模式1：生成提示词模板
输入视频秒数和产品描述，输出可直接粘贴到 Gemini 的提示词（内嵌所有规则）。
提示词模板内容见 `references/prompt_template.md`。
模板中需要替换的变量：
- `{VIDEO_LENGTH}` → 实际视频秒数
- `{FRAME_COUNT}` → 向上取整(视频秒数 ÷ 5)
- `{PRODUCT_DESCRIPTION}` → 产品的视觉特征（颜色、材质、形状）
## 模式2：校验并拆分
用户把 Gemini 返回的分镜结果粘贴过来，按检查清单逐项验证，通过后拆分为独立文件。
### 检查清单
校验以下 8 项，每项通过/失败+具体问题：
| # | 检查项 | 通过标准 |
|---|--------|---------|
| 1 | 帧数正确 | 帧数 = 向上取整(视频秒数 ÷ 5) |
| 2 | 产品占位符一致 | 所有帧中产品位置都使用 [PRODUCT] 占位符（除非物理状态变化） |
| 3 | 动势预设 | 每帧都有 mid-action / 动态姿势描述 |
| 4 | 正负分离 | Positive Prompt 和 Negative Prompt 已分离 |
| 5 | 无填充词 | 没有 "Generate an image..."、"HIGH RESOLUTION" 等对话式指令 |
| 6 | 无 meta-tags | 没有 "(Product reference: ...)" 标签，产品用 [PRODUCT] 占位 |
| 7 | 摄影术语 | 包含景别、角度、f值、焦距、光源方向、色温K值、照明技法 |
| 8 | 场景一致性 | 所有帧的 [SCENE] 描述完全相同（背景/环境/氛围不可跳变），只允许机位和光位变化 |
### 校验失败处理
- 项 1（帧数错误）：自动修正帧数，提示用户重新生成
- 项 2（占位符不一致）：标出差异帧，建议统一替换为 [PRODUCT]
…Read the whole file at its exact version.
How to install
mdr add hanzhcn/laohan-skills/laohan-fenjingtishici@v1mdr add hanzhcn/laohan-skills/laohan-fenjingtishici@sha256:b72eee6906dd3b68Pin 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_a4el7t2lyptgnfzy)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1 latest | 2026-05-22 | fa0389f | 4,756 B | A | view · diff |
| git:20260522.ee29bcc | 2026-05-22 | ee29bcc | 4,743 B | A | view · diff |
| git:20260522.5ef7159 | 2026-05-22 | 5ef7159 | 4,482 B | A | view · diff |
| git:20260427.dd5385c | 2026-04-27 | dd5385c | 4,652 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 (4756 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
hanzhcn/laohan-skills · 11 stars · license MIT · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a4el7t2lyptgnfzy GET https://markdownregistry.com/api/v1/resolve?ref=hanzhcn/laohan-skills/laohan-fenjingtishici GET https://markdownregistry.com/api/v1/blob/b72eee6906dd3b6845551ec895785057df29bcdf428e764f1c3c07c409343210
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.