跳到正文
cccskills
免费在 GitHub 公开

youtube-summarizer

Automatically fetch YouTube transcripts, generate structured summaries, and send full transcripts to messaging platforms. Use when a request includes YouTube URLs and needs metadata, key insights, or downloadable transcripts.

中文简介正在准备中。当前显示原文说明。

集成工具YouTube
查看安装方法

包含的文件(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

YouTube Summarizer Skill

Automatically fetch transcripts from YouTube videos, generate structured summaries, and deliver full transcripts to messaging platforms.

When to Use

Activate this skill when:

  • User shares a YouTube URL (youtube.com/watch, youtu.be, youtube.com/shorts)
  • User asks to summarize or transcribe a YouTube video
  • User requests information about a YouTube video's content

Quick Method: Use summarize CLI

The summarize CLI already handles YouTube videos:

summarize "https://www.youtube.com/watch?v=VIDEO_ID" --youtube auto

This is the preferred method for YouTube summarization.

With model selection

summarize "https://youtu.be/VIDEO_ID" --model google/gemini-3-flash-preview --youtube auto

Length options

summarize "URL" --youtube auto --length short   # Brief summary
summarize "URL" --youtube auto --length long    # Detailed summary
summarize "URL" --youtube auto --length xl      # Very detailed

Alternative: MCP YouTube Transcript Server

For more control, use the MCP server directly:

Setup (if not installed)

cd /root/clawd
git clone https://github.com/kimtaeyoon83/mcp-server-youtube-transcript.git
cd mcp-server-youtube-transcript
npm install && npm run build

Fetch Transcript

cd /root/clawd/mcp-server-youtube-transcript && node --input-type=module -e "
import { getSubtitles } from './dist/youtube-fetcher.js';
const result = await getSubtitles({ videoID: 'VIDEO_ID', lang: 'en' });
console.log(JSON.stringify(result, null, 2));
" > /tmp/yt-transcript.json

URL Patterns

Extract video ID from these patterns:

  • https://www.youtube.com/watch?v=VIDEO_ID
  • https://youtu.be/VIDEO_ID
  • https://www.youtube.com/shorts/VIDEO_ID
  • Direct video ID: VIDEO_ID (11 characters)

Summary Template

When generating summaries manually, use this format:

📹 **Video:** [title]
👤 **Channel:** [author] | 👁️ **Views:** [views] | 📅 **Published:** [date]

**🎯 Main Thesis:**
[1-2 sentence core argument/message]

**💡 Key Insights:**
- [insight 1]
- [insight 2]
- [insight 3]
- [insight 4]
- [insight 5]

**📝 Notable Points:**
- [additional point 1]
- [additional point 2]

**🔑 Takeaway:**
[Practical application or conclusion]

Quality Guidelines

  • Be concise: Summary should be scannable in 30 seconds
  • Be accurate: Don't add information not in the transcript
  • Be structured: Use consistent formatting
  • Adjust for length:
    • Short videos (<5 min): Brief summary
    • Long videos (>30 min): More detailed breakdown

Error Handling

If transcript fetch fails:

  • Check if video has captions enabled
  • Try with lang: 'en' fallback
  • Inform user that transcript is not available

If video ID extraction fails:

  • Ask user to provide the full YouTube URL or video ID

Environment Variables (for MCP server)

If using APIFY fallback:

export APIFY_API_TOKEN="..."  # Optional, for YouTube fallback

Store in 1Password: op://Jarvis/Apify API/credential

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when working with the 1Password CLI (`op` command) for secrets management, retrieving API keys, injecting secrets into development environments, or any task involving 1Password vault operations. Triggers on: "1password", "op command", "secrets management", "api keys from vault", "op run", "op read", "service account token".

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Create and manage teams of specialized AI agents that work together on tasks. Use when setting up multi-agent workflows, agent squads for content/marketing/research pipelines, configuring heartbeat-based agent coordination, or managing agent personalities via SOUL.md files. Enables orchestration of multiple OpenClaw sessions as a coordinated team with shared task systems (Linear, Trello, etc.).

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Create algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use when users request generative art, algorithmic art, flow fields, or particle systems. Create original works rather than copying existing artists.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

CSS and UI animation patterns for responsive, polished interfaces. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Use when starting creative work (features, components, functionality, or behavior changes) to clarify user intent, requirements, and design before implementation.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

查看 thedaviddias 的全部技能

报告此技能的问题