video-prompt SKILL.md skillA
video-prompt from uu889/uu889-drama is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add uu889/uu889-drama/video-prompt@git:20261014.f03ad80Pins git:20261014.f03ad80 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- uu889/uu889-drama
- Path
backend/workspace/skills/prompt-generator/video-prompt/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261014.f03ad80, committed Oct 14, 2026
- First version recorded
- Aug 8, 2026
- Size
- 5,606 bytes
- Repository stars
- 13
- License
- a license file GitHub does not identify
视频提示词规范 — 根据分镜段落内容生成按时间分段、段内可切镜的视频生成提示词.
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
# 视频提示词（分镜段落 → video_prompt） 根据单个分镜段落的 description（含【镜头N】子镜头结构与台词/旁白）/ atmosphere / duration，生成驱动 AI 视频生成的 `video_prompt`。**一个分镜段落 = 一段 4-15 秒的视频，内部允许切镜**：段与段之间可以是不同镜头（换景别/角度/对象），用硬切衔接；但**全程不跨场景**、不闪回。 ## 格式 `video_prompt` 的**第一行是信息头**：先介绍这条视频有哪些人物和场景，然后再接时间分段。人物、场景一律用 @ 引用（生成时会替换为对应参考图片标记，让视频模型先对上"谁"和"在哪"）。 ``` 出场人物：@小明、@小红；场景：@咖啡厅。 0-3秒：@咖啡厅，近景固定镜头，@小明低头看手机，手指反复敲桌面，表情焦虑。 3-6秒：切到门口全景，门铃响，@小红推门走入，带进一阵冷风。 6-9秒：切回中景，@小红微笑着走向小明坐下，小明说：「你终于来了。」 9-10秒：两人隔桌对视，@小红点头（无人说话）。 ``` 信息头规则： - 只列该分镜段落实际出场的人物和绑定的场景，不要列没出场的 - 有明显道具出场时可在信息头追加（如 `；道具：@信件`） - 信息头独立一行，以句号结尾 - 分镜有 `blocking`（站位）时，信息头下一行写「站位：…」，照抄 blocking 的开场站位（画面左右、前后、朝向），全程保持同样的左右关系 - 之后是时间分段 按 3 秒为一段，每段单独一行、用换行分隔，时间范围连续衔接（无重叠、无空缺）。 ## 与分镜描述的映射 `description` 是 video_prompt 的唯一内容来源（画面、动作、台词、旁白都在其中），转换规则： - `description` 的每个 `【镜头N】` 映射为 **1-2 个连续的 3 秒段**，顺序一致、不遗漏、不合并、不新增子镜头 - 台词/旁白从对应 `【镜头N】` 内的「角色名说：「…」」「旁白：…」提取，分配到该子镜头映射的段；**不要创作 description 之外的新台词** - 画面动作以 `description` 为准；`atmosphere` 只用于补各段的光线、色调与氛围描写 ## 段内结构 每一段按此顺序组织内容（可省略无内容的项，但动作/画面必须有）： **时间范围 ＋ 场景@引用 ＋ 景别/运镜 ＋ 角色@引用＋主体动作·表情 ＋ 对白/旁白 ＋ 氛围光线** - **第一段必须建立空间**：场景 + 机位 + 角色的位置与状态，让观众一眼知道在哪、看谁 …
Read the whole file at its exact version.
How to install
mdr add uu889/uu889-drama/video-prompt@sha256:71eca9186bc3e8f6The line at the top of this page pins the label git:20261014.f03ad80, 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_xs5nj3zlzwxyo5fc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 8, 2026 and Oct 14, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.f03ad80 latest | 2026-10-14 | f03ad80 | 5,606 B | A | view · diff |
| git:20260905.547df8e | 2026-09-05 | 547df8e | 4,586 B | A | view · diff |
| git:20260901.9564fdd | 2026-09-01 | 9564fdd | 4,023 B | A | view · diff |
| git:20260808.9998c3a | 2026-08-08 | 9998c3a | 4,032 B | A | view · diff |
| git:20260808.99e6680 | 2026-08-08 | 99e6680 | 3,406 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 (5606 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
uu889/uu889-drama · 13 stars · license a license file GitHub does not identify · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xs5nj3zlzwxyo5fc GET https://markdownregistry.com/api/v1/resolve?ref=uu889/uu889-drama/video-prompt GET https://markdownregistry.com/api/v1/blob/71eca9186bc3e8f6433c90535cd49bce44b2ae2ed52f7149fa066a92e63fecb8
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.
More from uu889/uu889-drama
Every file in uu889/uu889-drama