Video Prompt logo

Video Prompt

OrganizationPopular
chatfire-AI
video-prompt

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

Overview

Publisherchatfire-AI
Repositoryhuobao-drama
Skill namevideo-prompt
Stars
15.3K
Forks
2.8K
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by chatfire-AI on GitHub. Read the source before you install it.

Installation

Install the Video Prompt AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git /tmp/huobao-drama
mkdir -p .claude/skills
cp -r /tmp/huobao-drama/backend/workspace/skills/prompt-generator/video-prompt .claude/skills/video-prompt
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video Prompt in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Video Prompt on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Video Prompt is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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 8-15 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。」

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,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
  • 切镜:切镜后的段开头用"切到/切回"等衔接词,并重新交代景别与主体;切镜点应对齐分镜 description 中的 【镜头N】 结构
  • 景别/运镜:每段一个镜头状态(近景/中景/全景/特写;固定/推/拉/摇/跟);单个子镜头内运镜连续,切镜后可更换运镜方式
  • 动作:每段一个主动作,动词具体可见(走、转身、抬头、攥紧、停顿)
  • 情绪全部转为可见描写:不要"他很伤心/气氛紧张"这类抽象词,写成"他低下头、手指攥紧杯沿、呼吸变重"
  • 对白/旁白:写「角色名说:「台词」」,旁白写「旁白:内容」;3 秒念不完的长台词拆到多段;无对白的段可写环境音/动作音(如"机器持续轰鸣")

引用规则

  • @场景名 — 场景引用,名字必须与场景列表中的地点完全一致
  • @角色名 — 角色引用,名字必须与角色列表中的名字完全一致
  • @道具名 — 道具引用,名字必须与道具列表中的名字完全一致;道具在画面中明显可见、被使用或特写时引用
  • 生成时会自动把 @名字 替换为对应参考图片标记(如 @小明@图片1小明),因此名字必须精确匹配,不要缩写或加额外符号
  • 每段至少一个 @ 引用锚定画面;角色出场的段必须 @ 该角色;只引用该分镜段落已绑定的场景/角色/道具

时间轴规则

  • 段数 = 分镜段落 duration ÷ 3 秒(向上取整),各段时间范围相加必须等于段落总时长
  • 内容节奏:第一段建立 → 中段推进动作/冲突 → 末段落到结果或情绪点

禁止事项

  • 跨场景切换、闪回(一个段落只发生在一个场景内)
  • 引用列表之外的场景/角色名
  • 抽象心理描写、文学化比喻(模型只认可见画面)
  • 语言与会话语言指令不符

保存

调用 update_storyboard 仅更新该分镜段落的 video_prompt 字段,不要改动其他字段,不要重新拆分整集。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Video Prompt AI skill do?

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

Why use Video Prompt on TypingMind?

Because you install it once and use it with any model. Video Prompt is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Video Prompt in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/video-prompt. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Video Prompt?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Video Prompt?

As many as you like. As long as a model supports skills, you can use Video Prompt with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Video Prompt AI skill free?

It is published on GitHub by chatfire-AI. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇