video-prompt
chatfire-AI/huobao-drama · Agent Skill
Generates AI video prompts from scene descriptions, segmenting video by time with in-segment shot changes.
Jump to install ↓Overview
| Publisher |  chatfire-AIOrganization |
|---|---|
| Repository | chatfire-AI/huobao-drama ↗ |
| Skill folder | video-prompt |
| Stars | 14,828 |
| Bundled files | 1 |
| License | not specified — check with the author |
| Last updated | August 7, 2026 |
| Links | Skill source ↗ · Repository ↗ |
Mozgi check
What we found in the skill files. Details come with a subscription.
Installation
A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.
Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.
Install the “video-prompt” skill from mozgi.io (https://mozgi.io/skills/video-prompt/) for me. 1. Download the archive: https://mozgi.io/skills/video-prompt/download If it fails, take the skill folder from the source: https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/video-prompt 2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me. 3. Put the “video-prompt” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.). 4. Make sure <skills folder>/video-prompt/SKILL.md exists. 5. Briefly tell me what this skill does and offer to try it on my task. If you cannot do a step yourself, tell me what to click or type.
git clone --depth 1 --branch master 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 — the skill appears in the list; call it manually with /video-prompt. For all projects use ~/.claude/skills.
git clone --depth 1 --branch master https://github.com/chatfire-AI/huobao-drama.git /tmp/huobao-drama mkdir -p .agents/skills cp -r /tmp/huobao-drama/backend/workspace/skills/prompt-generator/video-prompt .agents/skills/video-prompt
Codex looks for skills in .agents/skills from the current folder up to the repo root; call one with /skills or $video-prompt. For all projects use ~/.agents/skills.
git clone --depth 1 --branch master https://github.com/chatfire-AI/huobao-drama.git /tmp/huobao-drama mkdir -p .cursor/skills cp -r /tmp/huobao-drama/backend/workspace/skills/prompt-generator/video-prompt .cursor/skills/video-prompt
Cursor picks the skill up on start; call it with “/” in Agent chat. Cursor also reads .claude/skills and .agents/skills. For all projects use ~/.cursor/skills.
git clone --depth 1 --branch master https://github.com/chatfire-AI/huobao-drama.git /tmp/huobao-drama mkdir -p .gemini/skills cp -r /tmp/huobao-drama/backend/workspace/skills/prompt-generator/video-prompt .gemini/skills/video-prompt
Gemini CLI offers to activate the skill when a task matches — you approve it. For all projects use ~/.gemini/skills.
Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.
SKILL.md contents
Original author text · read-only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 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。」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。
Frequently asked questions
What does the video-prompt skill do?
Generates AI video prompts from scene descriptions, segmenting video by time with in-segment shot changes.
How do I install video-prompt?
Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.
Which AI models work with video-prompt?
Skills are plain Markdown instructions (the Agent Skills format), so video-prompt works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.
Is video-prompt free?
The skill is published openly by chatfire-AI. The skill itself costs nothing — you only pay your AI provider for the tokens you use. No license is specified in the repository — check the terms with the author before commercial use.
Is it safe to install skills?
A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.
How is a skill different from an MCP server or a plugin?
An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.
Related skills
All skills →storyboard-breaker
Breaks down a script into video generation segments, each 8-15 seconds long, containing 2-4 shots with descriptions of actions, dialogue, and atmosphere.
chatfire-AI14.8k
remotion-video-creation
Provides 29 rules for creating videos in React using Remotion, covering 3D, animation, audio, and captions.
affaan-m258k
videodb
Processes video and audio: ingests, indexes, searches, edits, transcodes, generates media, and creates alerts.
affaan-m258k
ui-demo
Creates professional UI demo videos for web applications using Playwright, including cursor and natural pacing.
affaan-m258k
taste
Creates a creative direction for music videos and short-form edits in angelcore, cloud-trance, hyperpop styles, synchronizing visuals with music.
affaan-m258k
fal-ai-media
Generates images, videos, and audio using fal.ai models, including text-to-image, text-to-video, and text-to-speech.
affaan-m258k