Make Ai Video logo

Make Ai Video

Community
wanghui2323
make-ai-video

协助把想法、文章、提纲、已有口播、资料包或音频制作成有来源、可审核、可恢复的 AI 视频,并可选接入本地声音克隆。适用于用户提出“帮我把这个思路做成视频”“文章转视频”“整理口播和分镜”“用我的声音生成”“制作课程视频或短视频”“检查字幕、渲染或发布状态”等任务;也适用于需要区分首次声纹建档、本次配音、视频渲染和人工发布门禁的场景。

Overview

Publisherwanghui2323
Repositoryai-video-maker
Skill namemake-ai-video
Stars
99
Forks
0
Bundled files
29
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.

  • 29 bundled files

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

  • Open source

    Published by wanghui2323 on GitHub. Read the source before you install it.

Installation

Install the Make Ai 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/wanghui2323/ai-video-maker/tree/main/make-ai-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/wanghui2323/ai-video-maker.git /tmp/ai-video-maker
mkdir -p .claude/skills
cp -r /tmp/ai-video-maker/make-ai-video .claude/skills/make-ai-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Make Ai 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 Make Ai 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 Make Ai 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.

AI 视频制作助手

从用户已有的想法或素材开始,先判断输入和当前阶段,再协助完成内容、声音、画面与审核。不要把文章当作默认入口,也不要把首次声音建档、本次正式配音和整片发布合并成一次生成。

启动即执行

触发 Skill 后,立即进入工作流并执行当前可安全完成的步骤,不要只复述流程、列菜单或让用户自己拼命令。

  1. 先运行 node scripts/doctor.mjs --json 检查基础能力。定位或创建本次生产包,检查已有文件、设备、运行时和当前状态;没有生产包时运行 node scripts/create-package.mjs --dir <目录> --input-mode <类型> --summary <摘要>,不要临时拼接一套不可复用目录。
  2. 把用户现有输入写入 video-brief.json,明确缺失项,并继续执行到下一个真实人工门禁。
  3. 可逆的本地检查、建目录、生成合同对象和校验应主动执行。安装依赖、下载大模型或需要额外系统权限时,说明体积、目录和用途后发起所需批准;获准后继续,不要退回成教程。
  4. 只有授权/权利不明、核心事实待核验、口播确认、声音所有者选声、整片审核和发布授权等人工门禁才暂停。
  5. 每次暂停或交付都报告:当前阶段 / 已完成动作 / 产物路径 / 校验结果 / 需要用户做的一个决定 / 批准后下一步。

用户说“帮我做成视频”代表持续推进到下一个人工门禁;用户明确要求本人克隆声音且没有可用 Profile 时,按下文时钟 A 先执行本地声音建档,然后自动回到时钟 B。不要把“给一句开始话术”当作完成。

读取所需合同

  1. 先读 references/input-routing.md,把用户输入整理为 VideoBrief。
  2. 设计内容时读 references/content-contract.md。
  3. 选择画幅和分镜时读 references/visual-routing.md。
  4. 使用声音、渲染或报告状态前读 references/production-gates.md。
  5. 只有用户要求克隆或复用克隆声音时,才读 references/voice-cloning.md。
  6. 进入画面与渲染阶段时读 references/rendering-adapter.md。如果当前项目没有渲染适配器,继续交付内容、声音、字幕和 video-unit.json,但不得声称已经可以生成正式 MP4。
  7. assets/example-package/ 只用于理解完整对象和测试,不作为新项目直接改写;需要首次本地声纹建档时,再复制 assets/voice-clone-starter/。

使用两条时钟

时钟 A:低频声音能力建立

仅在用户明确选择克隆声音且没有可用 VoiceProfile 时执行:

text
授权与私有范围
→ 参考录音和准确逐字稿
→ 三个校准候选
→ 机器 QA
→ 声音所有者选择
→ production-pilot VoiceProfile

这条链通常只在首次建档、参考或模型漂移、授权范围变化时重跑。它先于完整视频生产,但不生成本次正式口播。

时钟 B:每条视频自己的生产

每个视频项目都执行:

text
VideoBrief
→ ContentDecision
→ VideoContentPlan
→ 口播人工确认
→ 本次 VoiceRun 或其他配音
→ 正式时序
→ 视觉预检
→ 渲染与技术检查
→ 整片人工审核
→ 发布候选

如果已有可用声音档案,在项目开始时做一次 preflight,口播确认后再生成本次三个候选。不要在口播未冻结时提前生成正式音频。

执行工作流

1. 建立 video-brief.json

识别 idea、article、outline、script、source-pack 或 audio 输入。记录受众、期望变化、来源、权利、证据成熟度、时长/画幅偏好和声音意图。

用户只有想法时,协助展开方向,但把假设与待核验事实写入 verificationNeeds;不要编造个人经历、数据或案例。

2. 检查声音依赖

  • none、human 或普通 synthetic:按相应合同继续。
  • cloned 且已有 Profile:立即 preflight;漂移则阻断。
  • cloned 且没有 Profile:读取 references/voice-cloning.md,先做设备与本地模型预检;缺少模型时按该参考执行下载与锁定,随后走时钟 A,再自动进入完整生产。

3. 建立 content-decision.json

根据输入成熟度生成 2–6 个候选,每个候选只回答一个问题,包含核心判断、观众动作、来源锚点、待核验项、时长建议和画幅建议。一次只推荐一个;保留其余候选。

4. 建立 video-content-plan.json

按内容密度选择时长:

  • quick:35–50 秒,一个纠偏或动作;
  • standard:60–85 秒,一个机制、比较或诊断;
  • deep:90–120 秒,一个带证据的案例;
  • course-master:130–180 秒,只用于一个需要 3–5 个相互依赖章节的问题。

每段绑定来源、时间预算、口播职责、情绪和唯一视觉任务。先建立具体冲突,再引入术语;结尾给出动作或边界。

5. 冻结内容和口播

向用户展示主问题、核心判断、事实边界、时长、画幅和完整口播。content_plan_reviewed 与 narration_reviewed 未通过时,不生成本次克隆配音,也不做完整渲染。

6. 生成本次声音

克隆声音时先重新 preflight,再按认知章节整段生成三个候选。机器淘汰坏音频;声音所有者明确选择其中一个。本次选择只批准该 VoiceRun,不批准整片或发布。

7. 建立正式时序与 video-unit.json

把已审内容和选定声音翻译成连续 beat。每个 beat 只使用一个 visualJob:conflict、mechanism、comparison、evidence、action 或 conclusion。

估算字幕只能用于草案。使用转写或人工对齐后,才能把 timing_ready 标为通过。

8. 预览、渲染与检查

先检查当前项目是否存在可用的 Remotion、剪辑工程或其他渲染适配器。存在时,先检查开场、核心解释、证据/动作和结尾代表帧,再渲染完整视频;检查尺寸、帧率、编码、音频、字幕范围、缺失资产和隐私残留。不存在时,明确报告 rendering_adapter_required,保留已完成产物,不得把视觉计划写成已经生成成片。

9. 记录真实状态

分别记录 local_package、review_candidate、release_candidate,以及各平台 draft、previewed、scheduled、published。自动校验、文件存在、本人选声和整片发布是不同事实。

校验生产包

在 Skill 目录运行:

bash
node scripts/validate-package.mjs --dir <生产包>

加 --json 获取机器可读结果。修复错误后再推进状态;警告必须在交付说明中解释。

停止条件

遇到以下情况时停止并报告精确阻塞点:

  • 用户意图、输入类型或权利边界不明确;
  • 待核验事实会改变核心结论;
  • 请求时长会删除结论边界;
  • 声音授权、Profile、模型、参考或哈希漂移;
  • 口播未审却准备生成本次克隆音频;
  • 估算字幕被当成正式时序;
  • 渲染命令结束但目标文件不存在;
  • 自动检查被用来推断人工批准。

保留已完成对象,从失败阶段恢复,不要重做整条链。

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 Make Ai Video AI skill do?

协助把想法、文章、提纲、已有口播、资料包或音频制作成有来源、可审核、可恢复的 AI 视频,并可选接入本地声音克隆。适用于用户提出“帮我把这个思路做成视频”“文章转视频”“整理口播和分镜”“用我的声音生成”“制作课程视频或短视频”“检查字幕、渲染或发布状态”等任务;也适用于需要区分首次声纹建档、本次配音、视频渲染和人工发布门禁的场景。

Why use Make Ai Video on TypingMind?

Because you install it once and use it with any model. Make Ai 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 Make Ai Video in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wanghui2323/ai-video-maker/tree/main/make-ai-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 Make Ai 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 Make Ai Video?

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

Is the Make Ai Video AI skill free?

Yes. It is published on GitHub by wanghui2323 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 👇