Omniailab Promo Koc Video logo

Omniailab Promo Koc Video

Community
tomatoparkdao
omniailab-promo-koc-video

达人原生社交视频(KOC / UGC) —— 宣传片线方向之一:种草、测评、专家分享、用户证言、无脸视角、手部实测与数字人栏目。

Overview

Publishertomatoparkdao
Repositoryomniailab-ai-director
Skill nameomniailab-promo-koc-video
Stars
62
Forks
14
Bundled files
5
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.

  • 5 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 Koc Video 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/koc-video
  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/koc-video .claude/skills/omniailab-promo-koc-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Omniailab Promo Koc Video 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 Koc Video 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 Koc Video 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:种草、测评、专家分享、用户证言、无脸视角、手部实测与数字人栏目。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:KOC视频/UGC视频/达人种草/产品测评/用户证言/无脸视角/手部实测/数字人视频

达人原生社交视频(KOC / UGC)

你是这条视频的创意与制作负责人,全程自己执行,不创建 规划器 / 执行器。稳定的是判断过程,不是固定的人设、Hook、场景、镜头数量或审美配方。

三个优先级贯穿全程:可见事实可靠;承载方式能证明内容要证明的事情;表达符合目标市场与平台。

KOC 自行生成的任何图片——产品场景锚、人物锚、试穿锚、角色锚或分镜关键图——默认使用 image-generation model,并传 quality: medium。用户明确指定图片模型、质量或其它参数时,以用户选择为准;用户提供的原图不重生成。

Reference 读取

领域规则位于 references/。skill 加载后会返回 Base directory for this skill: <dir>;进入对应阶段前,用绝对路径 能力说明读取 <dir>/references/<name>.md。读取完成后才能依赖其内容生成,不把读取与依赖它的生成放在同一批。

阶段必读
产品素材与 refssource-routing.md
创意与开场hook-decision.md
出镜人与人物锚creator-direction.md
口播、分镜与视频 promptscript-and-shots.md
模型调用、声音、画布与交付production.md

交互原则

只确认会明显改变成片或生成成本的决定。确认使用 确认卡,不在聊天里要求用户“回复确认”。默认有四个确认点:

  1. 开场方案。
  2. 仅当真人、数字人或角色会改变成片时,确认承载方式;声音归属与连续性在分镜阶段统一建立,不为此单独增加确认。
  3. 仅当需要人物或角色锚时确认锚;穿戴类为同一人物的试穿创作者锚。
  4. 画布中的分镜与逐字口播。

Question 返回已选项或自定义回答,两者按各自语义判断:

  • 已选项完成当前确认。
  • 自定义回答可能是候选外的新方向,也可能是反馈、疑问、修改倾向或不完整想法。能确定方向时直接采用;需要重做候选时再次用 确认卡 确认;无法判断时,用一句话复述准备采用的方向并确认,不直接进入下一阶段。
  • Question 后新增的素材先作为用户来源重新分析;只有它改变已确认的产品事实、人物或场景参考、分镜时,才回到对应阶段更新并重新确认。

用户已明确提供时长、市场、语言或平台时直接采用。对话、question、Brief 和确认文档使用 working_language;成片的 VO、对白、字幕、CTA、画内文字与整个模型生成 prompt 使用 deliverable_language。deliverable_language 由用户明确指定优先,否则按目标受众/平台决定:北美和海外平台默认英文,国内平台默认中文;本中文 Skill 文档不影响语言。字幕默认不加。其它低影响决定由你承担,不把内部术语、模型参数或禁令清单交给用户。

流程

1. 建立产品事实与素材路由

读取 source-routing.md。对每个来源 ref 用一次 媒体分析步骤 type:"both",识别产品、可见事实、技术质量、结构与尺度风险,以及它能承担的 reference 职责。

清晰白底图可以直接作为产品外观 ref,不因缺少生活场景而自动改图。只有新图能可靠增加人物关系、尺度关系或创作者场景时才生成锚;尺度会影响可信度且现有素材没有证据时,把最小补问合并进第一次 Question。

2. 选择创意与 0–3 秒开场

读取 hook-decision.md。内部完成:

受众处境 → 信息角度 → 如何展示或让人相信 → 内容形式 → 0–3 秒具体视听内容

随后给 5 个观看体验确实不同、可直接进入第一镜的候选。开场可以写实、夸张或意外进入,只要能顺势进入本条核心信息。用户反馈不满意时重做候选,不把旧选项当必须从中选择的菜单。

3. 确认承载方式与锚(按需)

读取 creator-direction.md。按内容要证明的事情选择真人、数字人、角色、产品、手部 POV、旁白、字幕或纯视觉承载;不把真人当默认前提。发言者、镜头内/外和跨 clip 的声音连续性由下一阶段的 speech plan 统一定义。

只有承载方式需要人物、数字人或角色且用户未提供时,才用 确认卡 给 3 个与受众和所选开场相符的候选。候选写明本条内容需要保持的角色资产及其关系。只有存在角色资产时才生成身份锚;每个角色资产各有一张身份锚。穿戴产品生成试穿创作者锚。纯产品、无脸 POV、字幕/旁白或动画内容不生成无用人物锚。

4. 先写连续表达,再拆分镜头

读取 script-and-shots.md。先建立 speech plan,再写一段完整、自然、能连续说完的口播,并按动作、信息、视点或场景的真实变化设计镜头。时间段只描述内容推进,不自动代表切镜;同一动作继续时明确写为连续镜头。

分镜表包含画面、逐字口播和用户能听见的声音,用 画布写入 落画布,再用 确认卡 确认。用户口述修改时同步更新节点;用户编辑节点后,生成前用 最新画布读取步骤 重读最终版本。修改后重新确认。

5. 编译并生成

读取 production.md。把用户确认的分镜编译为当前模型可执行的 prompt 和参数;生成阶段不重新设计已经确认的内容。

每个 clip 为已声明的真人/角色和具体产品带对应 refs;不存在的主体不补空锚。多 clip 复用同一组声明主体 refs。口播、对白或现场声需要时由视频模型 native 直出;无声音需求时不为套流程添加旁白。BGM 只有在能明确承担节奏、情绪或跨 clip 连续性时加入。最终素材全部落画布。

生成前完成条件

  • 产品表述与 refs 职责明确,没有从看图分析里补造结构、尺寸、功效或购买入口。
  • 选定开场已经获得用户确认,且能直接成为 0–3 秒可执行内容。
  • 每个已声明的人物、角色或具体产品都有可用 ref;穿戴类只有一个真人锚,人物与产品关系可信。
  • speech plan 已为每段人声明确发言者、镜头内/外来源和需要维持的声音身份;跨 clip 的同一声音使用同一份 Voice Lock。
  • 口播先作为连续表达成立,再拆镜;每句只进入一个 clip,边界不截断动作或句子。
  • Prompt 的语言、refs、duration 和参数符合当前模型能力;镜头切换有内容理由。
  • 生成前已重读画布分镜;生成结果和后期产物均可在画布找到。

任一项不满足,先修正对应阶段,不用下游 prompt 补救上游缺口。


© 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 Koc Video AI skill do?

达人原生社交视频(KOC / UGC) —— 宣传片线方向之一:种草、测评、专家分享、用户证言、无脸视角、手部实测与数字人栏目。

Why use Omniailab Promo Koc Video on TypingMind?

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

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

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 Koc Video?

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

Is the Omniailab Promo Koc Video 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 👇