This Claude skill provides high-efficiency summarization of web pages and YouTube videos, featuring automated semantic topic extraction tailored for Logseq and Obsidian. By integrating with the Z.AI service, it offers a cost-effective solution for transforming online content into structured, networked notes in markdown or plain text formats, significantly enhancing research productivity and knowledge retention.

When should I use web-summary?

web-summary is useful in the following scenarios: • YouTube Content Distillation: Extract full transcripts and generate concise summaries of educational or long-form videos to save time. • Personal Knowledge Management (PKM): Automatically format web summaries with semantic [[topic]] links for seamless integration into Logseq and Obsidian graphs. • Web Research & Archiving: Quickly convert blog posts, news articles, and documentation into structured markdown notes for long-term study. • Semantic Topic Mapping: Identify and extract key concepts from dense text to build a networked knowledge base with automated cross-referencing.

name	web-summary
description	>
version	2.0.0
author	turbo-flow-claude
mcp_server	true
protocol	fastmcp
entry_point	mcp-server/server.py

Web Summary Skill

URL content summarization and topic extraction via FastMCP, using Z.AI service for LLM processing.

When to Use This Skill

Summarize web articles, blog posts, documentation
Extract and summarize YouTube video transcripts
Generate semantic topic links for note-taking (Logseq, Obsidian)
Create short, medium, or long summaries
Extract key concepts from text

Architecture

┌─────────────────────────────┐
│  Claude Code / VisionFlow   │
│  (MCP Client)               │
└──────────────┬──────────────┘
               │ MCP Protocol (stdio)
               ▼
┌─────────────────────────────┐
│  Web Summary MCP Server     │
│  (FastMCP - Python only)    │
└──────────────┬──────────────┘
               │ HTTP (port 9600)
               ▼
┌─────────────────────────────┐
│  Z.AI Service               │
│  (Cost-effective Claude)    │
└─────────────────────────────┘

Tools

Tool	Description
`summarize_url`	Summarize content from any URL (web or YouTube)
`youtube_transcript`	Extract full transcript from YouTube video
`generate_topics`	Generate semantic topic links from text
`health_check`	Verify Z.AI service connectivity

Examples

# Summarize a web article
summarize_url({
    "url": "https://example.com/article",
    "length": "medium",
    "include_topics": True,
    "format": "logseq"
})

# Get YouTube transcript
youtube_transcript({
    "video_id": "dQw4w9WgXcQ",  # or full URL
    "language": "en"
})

# Generate topic links
generate_topics({
    "text": "Your text content here...",
    "max_topics": 10,
    "format": "obsidian"
})

Output Formats

Logseq

- [[Topic One]]
- [[Topic Two]]
- [[Machine Learning]]

Obsidian

- [[Topic One]]
- [[Topic Two]]
- [[Machine Learning]]

Plain

- Topic One
- Topic Two
- Machine Learning

Environment Variables

Variable	Default	Description
`ZAI_URL`	`http://localhost:9600/chat`	Z.AI service endpoint
`ZAI_TIMEOUT`	`60`	Request timeout in seconds

Troubleshooting

Z.AI connection failed:

# Check Z.AI service status
supervisorctl status claude-zai

# Test Z.AI directly
curl -X POST http://localhost:9600/chat \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Hello"}'

VisionFlow Integration

This skill exposes web-summary://capabilities resource for discovery by VisionFlow's MCP TCP client on port 9500.

web-summary

When & Why to Use This Skill

Use Cases