
Summarize
- 1 installs
- 6 repo stars
- Updated August 3, 2026
- avivsinai/telclaude
summarize is a Claude Code skill that extracts and summarizes web content from URLs, including articles and YouTube videos, via the telclaude summarize CLI.
About
This skill extracts readable content from URLs and summarizes articles, YouTube videos, podcasts, and web pages via the telclaude summarize CLI. A developer uses it when a user shares a link and wants key points without visiting the page. It supports max-char limits, output format, timeout, and automatic YouTube caption extraction.
- Extracts and summarizes articles, YouTube videos, podcasts, and web pages from URLs
- Auto-extracts YouTube captions and supports text or markdown output
- Configurable max-chars and timeout with per-user rate limits
Summarize by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,980 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
summarize capabilities & compatibility
- Capabilities
- research · web scraping · token optimization
- Use cases
- research · web scraping
- Pricing
- Free
What summarize says it does
Extract readable content from URLs — articles, YouTube videos, podcasts, and web pages.
YouTube URLs automatically extract captions — no special flags needed
npx skills add https://github.com/avivsinai/telclaude --skill summarizeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 6 |
| Last updated | August 3, 2026 |
| Repository | avivsinai/telclaude ↗ |
What it does
Summarize an article, web page, or YouTube video from a URL shared in chat.
Who is it for?
Condensing an article or video into key points from a shared link.
Skip if: Pages that require JavaScript rendering, which are not currently supported.
When should I use this skill?
A user shares a URL or asks to read, summarize, or extract a web page or video.
What you get
Returns structured metadata plus extracted, optionally summarized content from a URL.
By the numbers
- 8000-char default extraction limit
- 30 requests/hour, 100/day per user
Files
Summarize Skill
Extract readable content from URLs — articles, YouTube videos, podcasts, and web pages.
When to Use
Use this skill when users:
- Share a URL and want a summary or key points
- Ask to "read", "summarize", or "extract" a web page
- Paste a YouTube link and want transcript/content
- Want to understand an article without visiting it
How to Summarize
Use the telclaude summarize CLI command via Bash:
# Basic usage — extract content from URL
telclaude summarize "https://example.com/article"
# Limit output size (default: 8000 characters)
telclaude summarize "https://example.com/article" --max-chars 4000
# Get markdown-formatted output
telclaude summarize "https://example.com/article" --format markdown
# Custom timeout (default: 30000ms)
telclaude summarize "https://example.com/article" --timeout 60000Output Format
The command outputs structured metadata followed by the extracted content:
Title: Article Title Here
Site: example.com
Words: 1234
Transcript: youtube-captions (only for video/audio content)
Note: Content was truncated (only if content exceeded max-chars)
---
[Extracted text content here]Supported Content Types
- Articles/blog posts: HTML extraction via readability
- YouTube videos: Automatic caption/transcript extraction
- Podcasts: Audio transcript when available
- General web pages: Best-effort content extraction
Options
| Flag | Description | Default |
|---|---|---|
--max-chars <n> | Maximum characters to extract | 8000 |
--format <fmt> | Output format: text or markdown | text |
--timeout <ms> | Request timeout in milliseconds | 30000 |
Rate Limits
- 30 requests per hour per user
- 100 requests per day per user
Tips
- For long articles, use
--max-chars 16000to get more content - Use
--format markdownwhen the user wants formatted output with headings/links - YouTube URLs automatically extract captions — no special flags needed
- If extraction fails, the URL may require JavaScript rendering (not currently supported)