Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
# Agent Skills

**Languages:** English | [简体中文](README.zh-CN.md)

A growing collection of reusable Agent Skills for practical SaaS workflows—from image generation and video creation to subtitling and automation.

Each skill is a self-contained directory built around the open [`SKILL.md`](https://agentskills.io/specification) format. Copy or symlink the directory you need into an agent-compatible skills location, such as `.agents/skills/` in a repository or `~/.agents/skills/` for personal use.
Expand All @@ -8,25 +10,25 @@ Each skill is a self-contained directory built around the open [`SKILL.md`](http

Turn a local audio or video file into polished, timed subtitles—and deliver it as an SRT/VTT/ASS file, a video with permanent subtitles, or a video with a selectable subtitle track.

![Chinese burned-in subtitle preview](skills/video-subtitle-translator/examples/测试视频.中文字幕预览.gif)
![Chinese burned-in subtitle preview](skills/video-subtitle-translator/examples/test-video-zh-preview.gif)

The preview above is taken from the included [**测试视频** demo](skills/video-subtitle-translator/examples/测试视频.中文字幕烧录版.mp4): English speech transcribed, translated to Simplified Chinese, and burned into the video.
The preview above is taken from the included [**Test Video** demo](skills/video-subtitle-translator/examples/test-video-zh-burned.mp4): English speech transcribed, translated to Simplified Chinese, and burned into the video.

| Skill | What it does | Requirements |
| --- | --- | --- |
| [`video-subtitle-translator`](skills/video-subtitle-translator/) | Alibaba Qwen ASR transcription, timed subtitle generation, translation, CJK-aware layout, and hard or soft subtitle export. | Node.js 18+, FFmpeg, OO CLI, Fusion ASR, and OO LLM access |
| [`video-subtitle-translator`](skills/video-subtitle-translator/) | [Built with oo CLI](https://oomol.com): Alibaba Qwen ASR transcription, timed subtitle generation, translation, CJK-aware layout, and hard or soft subtitle export. [English overview](skills/video-subtitle-translator/README.md) · [中文说明](skills/video-subtitle-translator/README.zh-CN.md) | Node.js 18+, FFmpeg, [oo CLI](https://oomol.com), Fusion ASR, and OO LLM access |

Read the [English video subtitle translator overview](skills/video-subtitle-translator/README.md) or the [简体中文说明](skills/video-subtitle-translator/README.zh-CN.md) for the workflow, formats, languages, and delivery options.

Read the [video subtitle translator overview and demo](skills/video-subtitle-translator/README.md) for the workflow, formats, languages, and delivery options.
## Add this skill to your agent

## Install a skill locally
No terminal commands to memorize. Copy this request to your agent:

```bash
git clone https://github.com/alwaysmavs/agent-skills.git
mkdir -p .agents/skills
cp -R agent-skills/skills/video-subtitle-translator .agents/skills/
```text
Install the video-subtitle-translator skill from https://github.com/alwaysmavs/agent-skills into my current agent's skills directory. Follow its SKILL.md instructions. Check that Node.js 18+, FFmpeg/FFprobe, and an authenticated oo CLI with Fusion ASR and OO LLM access are available. If something is missing, tell me exactly what I need to set up; otherwise confirm that the skill is ready to use.
```

Restart or reload your agent after installing a skill. See the skill's `SKILL.md` for the agent-facing prerequisites, data handling, workflow details, and output conventions.
The skill is [built with oo CLI](https://oomol.com). Its `SKILL.md` contains the agent-facing prerequisites, data handling, workflow details, and output conventions.

## Contributing

Expand Down
39 changes: 39 additions & 0 deletions README.zh-CN.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# Agent Skills

**语言:** [English](README.md) | 简体中文

一组可复用的 Agent Skills,面向图像生成、视频制作、字幕、自动化等实用 SaaS 工作流。

每个 skill 都是独立目录,并遵循开放的 [`SKILL.md`](https://agentskills.io/specification) 格式。将所需目录复制或软链接到兼容的 skills 目录即可,例如项目内的 `.agents/skills/`,或个人目录 `~/.agents/skills/`。

## 推荐:视频字幕生成器

把本地音频或视频转成带时间轴的字幕,并按观众实际需要导出为 SRT/VTT/ASS、烧录字幕 MP4,或带可选字幕轨的 MKV。

![简体中文字幕烧录预览](skills/video-subtitle-translator/examples/test-video-zh-preview.gif)

上方预览来自仓库中附带的 [**Test Video** 示例视频](skills/video-subtitle-translator/examples/test-video-zh-burned.mp4):英文讲话先被转写,再翻译为简体中文,最后直接烧录进画面。

| Skill | 能力简介 | 环境要求 |
| --- | --- | --- |
| [`video-subtitle-translator`](skills/video-subtitle-translator/) | [基于 oo CLI 构建](https://oomol.com):使用阿里 Qwen ASR 转写,生成带时间轴的字幕、翻译、优化中日韩字幕换行,并导出硬字幕或软字幕。 [English](skills/video-subtitle-translator/README.md) · [中文说明](skills/video-subtitle-translator/README.zh-CN.md) | Node.js 18+、FFmpeg、[oo CLI](https://oomol.com)、Fusion ASR 与 OO LLM 权限 |

查看 [视频字幕生成器中文说明](skills/video-subtitle-translator/README.zh-CN.md),或阅读 [English overview](skills/video-subtitle-translator/README.md),了解完整流程、支持语言、格式和交付方式。

## 让你的 Agent 安装 skill

无需记忆终端命令。将以下提示词直接复制给你的 Agent:

```text
请将 https://github.com/alwaysmavs/agent-skills 中的 video-subtitle-translator skill 安装到我当前 Agent 的 skills 目录,并遵循该 skill 的 SKILL.md 说明。请检查 Node.js 18+、FFmpeg/FFprobe,以及已认证且具备 Fusion ASR 和 OO LLM 权限的 oo CLI 是否可用;如有缺失,请明确告诉我需要完成哪些配置;如果环境已就绪,请确认该 skill 可以使用。
```

该 skill [基于 oo CLI 构建](https://oomol.com)。面向 Agent 的前置条件、数据处理、具体命令和输出约定请参阅对应 skill 的 `SKILL.md`。

## 参与贡献

请让每个 skill 聚焦于一个明确任务、保持自包含,并确保在执行前可以安全审阅。只有能提升可靠性的场景才加入确定性脚本;同时记录外部依赖和数据流,并为确定性逻辑提供可运行测试。

## 许可证

本仓库以 [MIT License](LICENSE) 发布。
26 changes: 15 additions & 11 deletions skills/video-subtitle-translator/README.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,18 @@
# Video Subtitle Translator

**Languages:** English | [简体中文](README.zh-CN.md)

**Repository:** [All skills](../../README.md) | [全部技能(中文)](../../README.zh-CN.md)

**Give any video readable, natural subtitles—then export exactly the format your audience needs.**

`video-subtitle-translator` is an OO-powered Agent Skill for turning local audio and video into timed captions, translated subtitle files, hard-subtitled MP4s, or videos with selectable subtitle tracks. It combines Alibaba Qwen ASR transcription with deterministic subtitle processing, so the output is ready for sharing rather than a loose block of transcript text.
`video-subtitle-translator` is an Agent Skill [built with oo CLI](https://oomol.com) for turning local audio and video into timed captions, translated subtitle files, hard-subtitled MP4s, or videos with selectable subtitle tracks. It combines Alibaba Qwen ASR transcription with deterministic subtitle processing, so the output is ready for sharing rather than a loose block of transcript text.

## See the result

![测试视频:英文语音已翻译并烧录为简体中文字幕](examples/测试视频.中文字幕预览.gif)
![Test Video: English speech translated and burned in as Simplified Chinese subtitles](examples/test-video-zh-preview.gif)

This preview comes from [**测试视频** — download or play the complete burned-in MP4](examples/测试视频.中文字幕烧录版.mp4). The source is English; the finished video has natural, bottom-centered Simplified Chinese subtitles with a high-contrast outline.
This preview comes from [**Test Video** — download or play the complete burned-in MP4](examples/test-video-zh-burned.mp4). The source is English; the finished video has natural, bottom-centered Simplified Chinese subtitles with a high-contrast outline.

## What it does

Expand Down Expand Up @@ -44,21 +48,21 @@ Alibaba Qwen ASR supports automatic detection or an explicit source language. Th
| A video editor or platform needs a subtitle file | SRT or VTT |
| Matching typography and placement matter | ASS sidecar or styled MKV |

## Install
## Add it to your agent

Copy this request to your agent—no terminal commands required:

```bash
git clone https://github.com/alwaysmavs/agent-skills.git
mkdir -p .agents/skills
cp -R agent-skills/skills/video-subtitle-translator .agents/skills/
```text
Install the video-subtitle-translator skill from https://github.com/alwaysmavs/agent-skills into my current agent's skills directory. Follow its SKILL.md instructions. Check that Node.js 18+, FFmpeg/FFprobe, and an authenticated oo CLI with Fusion ASR and OO LLM access are available. If something is missing, tell me exactly what I need to set up; otherwise confirm that the skill is ready to use.
```

The implementation guide for agents, including setup, commands, data handling, and recovery steps, is in [SKILL.md](SKILL.md). It requires Node.js 18+, FFmpeg/FFprobe, an authenticated `oo` CLI, Fusion API access, and an OO LLM configuration.
The implementation guide for agents, including setup, commands, data handling, and recovery steps, is in [SKILL.md](SKILL.md). It uses [oo CLI](https://oomol.com) and requires Node.js 18+, FFmpeg/FFprobe, Fusion API access, and an OO LLM configuration.

## Included demo

| Asset | Details |
| --- | --- |
| [`测试视频.中文字幕烧录版.mp4`](examples/测试视频.中文字幕烧录版.mp4) | Complete 2:46 demo video with Simplified Chinese subtitles permanently burned in; MP4 title metadata: `测试视频`. |
| [`测试视频.中文字幕预览.gif`](examples/测试视频.中文字幕预览.gif) | Short, autoplaying preview used in this page and the repository home page. |
| [`test-video-zh-burned.mp4`](examples/test-video-zh-burned.mp4) | Complete 2:46 demo video with Simplified Chinese subtitles permanently burned in; MP4 title metadata: `Test Video`. |
| [`test-video-zh-preview.gif`](examples/test-video-zh-preview.gif) | Short, autoplaying preview used in this page and the repository home page. |

The demo is included solely to show the generated subtitle result. No raw transcript, API key, uploaded-media URL, or intermediate job data is committed.
68 changes: 68 additions & 0 deletions skills/video-subtitle-translator/README.zh-CN.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
# 视频字幕生成器

**语言:** [English](README.md) | 简体中文

**仓库导航:** [全部 skills(English)](../../README.md) | [全部 skills(中文)](../../README.zh-CN.md)

**让任何视频拥有自然、清晰、便于观看的字幕,并按受众所需格式直接交付。**

`video-subtitle-translator` 是一个[基于 oo CLI 构建](https://oomol.com) 的 Agent Skill,可将本地音频或视频转为带时间轴的字幕、翻译后的字幕文件、烧录字幕 MP4,或带可选字幕轨的视频。它将阿里 Qwen ASR 转写与确定性的字幕处理结合起来,输出的是可以直接交付的字幕和成片,而不仅是一段没有时间信息的逐字稿。

## 查看效果

![Test Video:英文语音已翻译并烧录为简体中文字幕](examples/test-video-zh-preview.gif)

此预览来自 [**Test Video** — 下载或播放完整烧录字幕 MP4](examples/test-video-zh-burned.mp4)。原始语音为英语;最终视频使用自然、底部居中、黑色描边的简体中文字幕。

## 核心能力

### 1. 使用阿里 Qwen ASR 生成带逐词时间戳的逐字稿

skill 会先通过 OO 工作流上传标准化音频,再经 Fusion API 提交至 **Alibaba Qwen ASR FileTrans**。转写结果包含句级和词级时间戳,而不只是纯文本;正是这些时间戳让字幕能够准确跟随说话节奏。

### 2. 将逐字稿整理成易读的 SRT 字幕

内置转换工具会将带时间戳的词语组合成适合屏幕阅读的字幕条目。它会综合停顿、单条时长、字符数和词数等边界条件,并输出通用 SRT 文件;需要时也可生成 VTT。原始逐字稿和逐词时间轴字幕会一并保留,方便复核。

### 3. 翻译时保留原始时间轴

用户要求翻译时,配置好的 OO LLM 只翻译每一条字幕文本,同时保留所有字幕序号和时间戳。长视频会使用检查点保存已完成的批次,支持中断后继续;还可以传入术语表、领域、受众和风格说明,保证名称和专业术语前后一致。

### 4. 交付观众真正能使用的字幕

- **烧录字幕 MP4:** 字幕永久显示,适合社交媒体、移动端播放和上传后仍需稳定显示字幕的场景。
- **软字幕 MKV:** 不重新编码视频,提供可开关、可编辑的字幕轨。
- **SRT、VTT 与 ASS:** 提供给剪辑软件、播放器和需要独立字幕资产的工作流。
- **CJK 排版优化:** 中文、日文、韩文会按适合两行显示的规则自动换行,不会套用英文字幕的字符长度假设。

## 支持语言

Alibaba Qwen ASR 支持自动识别语言,也可指定源语言。当前工作流支持中文、粤语、英语、日语、韩语、德语、法语、西班牙语、葡萄牙语、意大利语、阿拉伯语、俄语、印地语、印尼语、泰语、土耳其语、越南语,以及更多欧洲与东南亚语言。目标翻译语言由配置的 OO LLM 提供,因此同一套流程可以为多语言受众制作字幕。

## 如何选择输出格式

| 需求 | 推荐输出 |
| --- | --- |
| 希望字幕始终显示 | 烧录字幕 MP4 |
| 希望观众自行开关字幕 | 软字幕 MKV |
| 剪辑软件或平台需要单独字幕文件 | SRT 或 VTT |
| 需要一致的字体、描边和位置 | ASS 外挂字幕或带 ASS 的 MKV |

## 让 Agent 安装

无需运行终端命令。将以下提示词直接复制给你的 Agent:

```text
请将 https://github.com/alwaysmavs/agent-skills 中的 video-subtitle-translator skill 安装到我当前 Agent 的 skills 目录,并遵循该 skill 的 SKILL.md 说明。请检查 Node.js 18+、FFmpeg/FFprobe,以及已认证且具备 Fusion ASR 和 OO LLM 权限的 oo CLI 是否可用;如有缺失,请明确告诉我需要完成哪些配置;如果环境已就绪,请确认该 skill 可以使用。
```

面向 Agent 的实现说明、环境要求、具体命令、数据处理和恢复步骤请阅读 [SKILL.md](SKILL.md)。该 skill 使用 [oo CLI](https://oomol.com),并需要 Node.js 18+、FFmpeg/FFprobe、Fusion API 权限和 OO LLM 配置。

## 附带示例

| 资源 | 说明 |
| --- | --- |
| [`test-video-zh-burned.mp4`](examples/test-video-zh-burned.mp4) | 完整 2 分 46 秒示例,已永久烧录简体中文字幕;MP4 标题元数据为 `Test Video`。 |
| [`test-video-zh-preview.gif`](examples/test-video-zh-preview.gif) | 自动播放的短预览,同时用于本页和仓库首页。 |

示例仅用于展示字幕生成效果;仓库不会提交原始逐字稿、API Key、上传媒体地址或中间任务数据。