Ah Talking Head Edit logo

Ah Talking Head Edit

Community
ahang008
ah-talking-head-edit

独立口播剪辑试用版。用授权本地视频、现成时间戳逐字稿或 SRT、审核后的源区间,产出自有可编辑 JSON 工程、MP4、同步 SRT 和媒体校验报告。仅在用户明确说独立口播剪辑、ah-talking-head-edit、不依赖旧引擎剪片,或明确选择本项目时使用。普通剪映剪辑、剪映原生草稿、写口播稿、ASR 转写和封面制作不自动触发本 Skill。

Overview

Publisherahang008
Repositoryah-skills
Skill nameah-talking-head-edit
Stars
58
Forks
4
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

    Published by ahang008 on GitHub. Read the source before you install it.

Installation

Install the Ah Talking Head Edit 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/ahang008/ah-skills/tree/main/skills/ah-talking-head-edit
  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/ahang008/ah-skills.git /tmp/ah-skills
mkdir -p .claude/skills
cp -r /tmp/ah-skills/skills/ah-talking-head-edit .claude/skills/ah-talking-head-edit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ah Talking Head Edit 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 Ah Talking Head Edit 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 Ah Talking Head Edit 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.

阿杭独立口播剪辑

执行本项目自有时间线和 FFmpeg 导出流程。第一版标记为 trial,不把未经对照验收的结果称为优于其他方案。功能动机致敬 yichen-skill;不得据此宣称复制、获得其授权或背书。

交付边界

  • 保留原素材,默认原速 1、无音乐。以当次用户参数覆盖示例和默认值,不把固定时长、语速或口头习惯固化为通用规则。
  • 交付本项目格式 ah-talking-head-project revision 1 的 JSON 工程、独立 MP4、同步 SRT、媒体校验报告。JSON 可以编辑后重验重导。
  • 字幕局部修改只作用于外置 SRT。源画面已有烧录字幕时,本版保留画面内字幕,不抹去、替换或自动校正它;交付时注明画面旧字幕与外置字幕是否存在差异。
  • 将剪映原生草稿、导入剪映、剪映工程回放标记为本版未实现。不得把自有 JSON 称为剪映原生草稿。
  • 只用本项目脚本。不得调用、加载或借助旧 yichen、jianying-headless 引擎、私有 Skill、模板、测试或 schema 完成本任务。

定位资源

以此 SKILL.md 所在目录为 Skill 根目录,在该目录执行命令。读取 workflow.md 获取完整可移植请求、计划和 CLI 顺序;读取 project-format.md 确认字段和边界规则。先执行 python3 scripts/clip.py doctor 和各子命令 --help,再按实际接口操作。搬移或独立安装时保留整个 Skill 目录及其脚本和 references。

执行步骤

  1. 核对素材使用授权、实际源文件、时间戳逐字稿或 SRT、目标输出和当次参数。只读取用户授权的本地输入。已有逐字稿须保留其已给出的时间戳;需要 SRT 时据现有时间戳转换,不补猜 ASR 端点。
  2. 分析完整表达、重复录制、孤立语气词和保留上下文的需要。把删除理由与对应源区间逐项记录。静音长度只能提供审听候选,不得自动作为删除依据。缺少可用字幕或可靠区间时,先完成已有素材核查,再索取缺失输入。
  3. 按原音审听候选切口,确认前后音节完整、词尾未被截断、连读没有被误删。用 protected_speech 标注已确认应保留的发音区间。没有实际审听就明确标记尚未审听,不把转写、波形、静音扫描或机器验证当作听音验收。未经确认的边界不得擅自缩入词内;要求精确删除时,须先取得审听结果或用户明确提供的审核边界。
  4. 将确认保留的源区间写入计划 clips,每段填写非空 decision,速度默认 1。源区间决定真实剪辑,输出时间由脚本计算,不手写猜测的最终时间线。保护区间必须全部在所属 clip 内。
  5. 逐条检查跨切口字幕。完整保留的 cue 可沿用原文;只保留 cue 部分时,给该 clip 的每个保留片段填写 caption_edits,明确原 cue 编号、保留源边界和实际保留文字。禁止为部分发音保留完整 cue 文案。无法确认片段文字时,不截取该 cue 的发音,或等待用户提供明确文字和边界。
  6. 用 create 生成新工程,再用 inspect 和 validate 读回真实源区间、字幕映射、速度、保护区间、哈希和计算时间线。遇错直接修复计划并重建,不跳过拒绝条件。保留可追溯的修改版本。
  7. 用 render 导出到新的输出目录,再用 audit 重验落盘产物。确认 MP4 可完整解码、实际媒体信息及 SRT 与计算时间线一致;文字与声音对齐仍须审听,报告文件存在不等于所有检查通过。失败时依据错误修复后重新验证和导出。
  8. 在可用播放器中核听切口和成片,记录真实核听范围与结果。没有完整核听时,分别报告机器验证通过范围、已经听过的区间和剩余人工验收,不宣称完成全部人工听音。

回复结果

使用中文,先称呼阿杭,再用简短列表给出工程、视频、字幕、报告的实际路径和验证结果。说明原速或用户指定速度、字幕局部替换、人工听音范围、剩余限制。交付为试用版;只有实测证据支持的能力才标记完成。未生成文件、不存在的路径和未实现的原生工程不得列作交付。

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 Ah Talking Head Edit AI skill do?

独立口播剪辑试用版。用授权本地视频、现成时间戳逐字稿或 SRT、审核后的源区间,产出自有可编辑 JSON 工程、MP4、同步 SRT 和媒体校验报告。仅在用户明确说独立口播剪辑、ah-talking-head-edit、不依赖旧引擎剪片,或明确选择本项目时使用。普通剪映剪辑、剪映原生草稿、写口播稿、ASR 转写和封面制作不自动触发本 Skill。

Why use Ah Talking Head Edit on TypingMind?

Because you install it once and use it with any model. Ah Talking Head Edit 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 Ah Talking Head Edit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ahang008/ah-skills/tree/main/skills/ah-talking-head-edit. 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 Ah Talking Head Edit?

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 Ah Talking Head Edit?

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

Is the Ah Talking Head Edit AI skill free?

It is published on GitHub by ahang008. 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 👇