# Send vsum to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vsum",
    "name": "vsum",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Chrischaan/vsum",
    "canonicalUrl": "https://clawhub.ai/Chrischaan/vsum",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/vsum",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vsum",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "scripts/vsum.sh"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "vsum",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-05T07:07:36.410Z",
      "expiresAt": "2026-05-12T07:07:36.410Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vsum",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vsum",
        "contentDisposition": "attachment; filename=\"vsum-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "vsum"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/vsum"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vsum",
    "downloadUrl": "https://openagent3.xyz/downloads/vsum",
    "agentUrl": "https://openagent3.xyz/skills/vsum/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vsum/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vsum/agent.md"
  }
}
```
## Documentation

### Vsum

快速获取 YouTube/Bilibili 视频字幕并进行 AI 总结，输出 md 文件。

### 支持的平台

YouTube
Bilibili

### 依赖工具

yt-dlp - 用于获取视频字幕
AI API - 用于总结（支持 OpenAI、Anthropic、Google 等）

### YouTube

# 获取自动字幕（推荐）
yt-dlp --write-auto-subs --sub-lang en --skip-download "视频链接"

# 或者明确指定语言
yt-dlp --write-subs --sub-lang en --skip-download "视频链接"

# 列出可用字幕
yt-dlp --list-subs "视频链接"

注意: YouTube 需要使用 --write-auto-subs 才能下载自动生成的字幕。

### Bilibili

# 需要登录 cookie（浏览器需已登录 B站）
yt-dlp --cookies-from-browser chrome --write-subs --sub-lang ai-zh,zh-CN --skip-download "视频链接"

# 列出可用字幕
yt-dlp --cookies-from-browser chrome --list-subs "视频链接"

注意: B站字幕需要用户登录，需要使用 --cookies-from-browser chrome 从浏览器读取 cookie。

### 工作流程

获取视频链接 - 用户提供 YouTube 或 Bilibili 链接
识别平台 - 自动判断是 YouTube 还是 Bilibili
获取字幕 - 使用 yt-dlp 获取字幕
AI 总结 - 调用 AI API 对字幕进行总结
输出 md - 将总结保存为 md 文件

### YouTube

优先: en (英语), en-orig (原始英语)
其他: 根据视频内容选择

### Bilibili

优先: ai-zh (AI 中文字幕), zh-CN (中文字幕)

### 常见问题

Q: 视频没有字幕怎么办？
A:

尝试其他语言字幕
或告知用户该视频无法获取字幕

Q: B站提示需要登录怎么办？
A: 确保浏览器已登录 B站，使用 --cookies-from-browser chrome 读取 cookie

Q: YouTube 下载失败怎么办？
A: 尝试添加 --write-auto-subs 而非 --write-subs

Q: 支持哪些 AI 提供商？
A: 支持任何 OpenAI 兼容格式的 API（如 OpenAI、Anthropic、OpenRouter、jiekou.ai 等）。

### 输出格式

# [视频标题]

> 来源: YouTube/Bilibili | 时长: XX:XX

## 总结

[AI 生成的视频总结]

## 关键要点

- 要点 1
- 要点 2
- 要点 3

---

*总结时间: YYYY-MM-DD*

### 长视频处理

对于长视频（字幕内容较多）：

先做预览 - 只总结视频开头部分（约 30前% 内容）
询问用户 - "这是视频的开头总结，需要我继续总结完整内容吗？"
如需完整 - 可以分段处理，或使用支持长上下文的 AI

### 分段总结（可选）

如果用户需要完整总结，可以：

将字幕分成 2-3 个部分
分别发送 AI 总结
最后合并成一个完整的总结

### 示例对话

用户："帮我总结这个视频 https://youtu.be/xxx"

识别为 YouTube 视频
使用 yt-dlp 获取字幕（加 --write-auto-subs）
调用 AI 总结
询问用户保存路径或直接保存到桌面/下载目录
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Chrischaan
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-05T07:07:36.410Z
- Expires at: 2026-05-12T07:07:36.410Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/vsum)
- [Send to Agent page](https://openagent3.xyz/skills/vsum/agent)
- [JSON manifest](https://openagent3.xyz/skills/vsum/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/vsum/agent.md)
- [Download page](https://openagent3.xyz/downloads/vsum)