Omniailab Promo Video Deconstruct logo

Omniailab Promo Video Deconstruct

Community
tomatoparkdao
omniailab-promo-video-deconstruct

视频拆解与逐镜复刻 —— 宣传片线方向之一:拆解用户提供的视频或关键帧,提取镜头顺序、运镜、光影与节奏证据,编译为逐镜复刻提示词。

Overview

Publishertomatoparkdao
Repositoryomniailab-ai-director
Skill nameomniailab-promo-video-deconstruct
Stars
62
Forks
14
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

    Published by tomatoparkdao on GitHub. Read the source before you install it.

Installation

Install the Omniailab Promo Video Deconstruct 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.
    https://github.com/tomatoparkdao/omniailab-ai-director/tree/main/references/promo/video-deconstruct
  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/tomatoparkdao/omniailab-ai-director.git /tmp/omniailab-ai-director
mkdir -p .claude/skills
cp -r /tmp/omniailab-ai-director/references/promo/video-deconstruct .claude/skills/omniailab-promo-video-deconstruct
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omniailab Promo Video Deconstruct 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 Omniailab Promo Video Deconstruct 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 Omniailab Promo Video Deconstruct 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.

在本 skill 中的位置:拆解用户提供的视频或关键帧,提取镜头顺序、运镜、光影与节奏证据,编译为逐镜复刻提示词。由宣传片线总调度 references/PROMO SKILL.md 在判定为该方向后接入。 生成口径:提示词编译完成后,统一在 OmniAiLab 画布 中选择 MiniMax H3 生成视频;图像与资产类提示词仍按主线层级执行(references/LIRA SKILL.md/references/STYLE SKILL.md/references/ASSET-SYSTEM SKILL.md/references/PROMPT-DOCTRINE SKILL.md)。 与主干的关系:本文件是宣传片线的方向细则,不改变 P0→P6 主干与确认门禁;涉及资产、表演、情绪、站位与光学时照常调用主线对应层。 暂停点:素材与文字确认 → 方向与风格确认 → 提示词确认 → 生成 → 验收;每一步都等创作者确认后再继续,不得一次跑完。 触发词:视频复刻/结构保留重制/提示词反推/逐镜分析/视频拆解

视频拆解与逐镜复刻

以证据为先:先读视频和关键帧,再写结论与复刻合同。不要把“分析”当作直接生成的替代品,也不要把截图推测说成已读取的视频事实。

输入与证据链

  1. 用户上传视频时,先用 媒体分析步骤 读取元信息和语义;记录时长、画幅、分辨率、主体、场景、动作、镜头、光影、节奏和可听声音。
  2. 语义分析失败、过粗,或用户要求精细复刻时,用 媒体拼接步骤 建立高密度关键帧拼图:15 秒内至少 10–12 帧;更长视频按可读的连续片段分拼图;快动作、转场密集时提高到约每秒一帧。拼图容量不得小于实际抽帧数。
  3. 将关键帧拼图写入画布;完整 Markdown 报告也写入画布,并用 来源节点关联 关联关键帧。只有截图或文字描述时,明确标注哪些动作、声音或时序仅为推测。
  4. 仅给 URL 时,不承诺下载外部视频;请用户上传视频、关键帧或足够的文字描述。

拆解报告

用户未指定重点时,默认深拆角色/主体、剧情/动作、镜头/运镜、光影/风格与节奏;已指定时不重复问。报告包含:

  1. 元信息、分析依据与一句话定性;
  2. 关键帧数量、拼图数量和覆盖时间;
  3. 角色与视觉锚点、场景、动作时间线、镜头、光影色彩、风格材质、剪辑节奏、声音;
  4. 可复刻事实、不可确定项和风险(人脸、手部、多人身份、文字、快速运动或风格漂移);
  5. H3 复刻计划、统一约束和自检结论。

为每个主体保留同一名称与可见识别点;用可观察证据描述景别、机位、运镜、光源、材质和动作,不用“电影感”“高级”等空词代替分析。

编译视频复刻合同

先查看当前能力摘要,确认当前选定视频模型支持的时长、画幅、分辨率、音频和参考素材范围。用户未指定模型时默认选择 MiniMax H3;用户锁定其它模型时,按该模型的能力说明编译,不静默换回 H3。

  1. 按连续性分组,而不是按固定 15 秒切段。主体、场景、动作流、声音意图和 refs 兼容时尽量组成最长可行 clip group;跨场景、主体/风格硬切、首尾帧依赖或运行时能力限制时才拆分。
  2. 为每组写清起始状态、连续动作和可承接的末态。下一组从上一组的可见末态或明确切换开始,不能只以“保持一致”代替事实。
  3. 当前模型为 MiniMax H3 时,按以下顺序生成最终 Prompt:全局基准 → 每个参考素材的角色 → 环境光影 → 空间基准 →(有对白时)角色声音签名 → 画面演进 → 声音设计 → 画面风格。逐镜头按顺序写景别、机位/观察方向、一个主运镜、主体行为、重要背景反馈、对白或同步声音与末态;其它模型只使用其对应的能力说明。
  4. 使用用户给定的素材和画布中的有效证据。每个 @图片N、@视频N、@音频N 都逐项说明锁定的身份、场景、风格、动作或声音;保持用户附件顺序。普通参考图不是首尾帧,只有用户明确指定时才按首帧、尾帧或关键帧处理。
  5. 模型的自动优化只能补足未指定内容:不得删改主体、动作、空间关系、构图、镜头顺序、声音或否定要求;用户要求静音、无对白、无音乐或仅保留指定声音时严格保留。精确 UI、文字或图形要求必须逐字锁定,不以“禁止文字/Logo”一律删除。
  6. 当前模型为 MiniMax H3 且写实人物清晰可见时,写自然哑光肤质、正常肤色、真实细节和镜头实际需要的光线;多人镜头先用全景建立关系,再用不同信息量的中近景/近景承接互动,避免脸部混合与重复面孔。
  7. 当前模型为 MiniMax H3 时以当前能力说明作为工程事实来源;多参考素材时一并读取并遵守 references/minimax-h3-multi-ref.md 的 refs 绑定规则。

交付与执行

  1. 默认在画布交付“视频拆解报告”和“视频复刻计划”两个文档节点。复刻计划列出每个 clip group 的时长/画幅/模型锁、refs、Prompt、起止状态和风险点。
  2. 用户只要分析或提示词时,停在可编辑复刻计划,不启动生成;用户明确要求生成时,按确认的模型锁和有序 refs 使用 视频生成。
  3. 完成后检查:关键帧证据已上画布;每个结论有证据或推测标记;最终 Prompt 符合当前模型的完整合同,且具备逐镜头动作/声音;refs 与素材顺序一一对应;不存在遗留模板变量、无依据新增剧情或被丢失的用户限制。

边界

  • 不把固定“每 15 秒一条时间戳 Prompt”作为通用规则,也不向非 Seedance 模型输出其专用模板。
  • 不因拆解任务自动生成字幕、可读 Logo 或水印;但用户明确要求的精确文字/UI 要保留并采用确定性叠加路径。
  • 只做普通剪辑、字幕、压缩、转码或影评时不触发本 Skill。

© OmniAiLab | 开发者:Mochiball | OmniAiLab AI导演完整版(omniailabx.com)— 未经授权禁止复制、传播或二次分发。

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 Omniailab Promo Video Deconstruct AI skill do?

视频拆解与逐镜复刻 —— 宣传片线方向之一:拆解用户提供的视频或关键帧,提取镜头顺序、运镜、光影与节奏证据,编译为逐镜复刻提示词。

Why use Omniailab Promo Video Deconstruct on TypingMind?

Because you install it once and use it with any model. Omniailab Promo Video Deconstruct 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 Omniailab Promo Video Deconstruct in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tomatoparkdao/omniailab-ai-director/tree/main/references/promo/video-deconstruct. 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 Omniailab Promo Video Deconstruct?

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 Omniailab Promo Video Deconstruct?

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

Is the Omniailab Promo Video Deconstruct AI skill free?

Yes. It is published on GitHub by tomatoparkdao under the MIT license. 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 👇