home / skills / openclaw / skills / youtube-instant-article

youtube-instant-article skill

/skills/viticci/youtube-instant-article

This skill converts YouTube videos into Telegraph Instant View articles with slides and timestamped summaries for easy sharing.

npx playbooks add skill openclaw/skills --skill youtube-instant-article

Review the files below or copy the command above to add this skill to your agents.

Files (6)
SKILL.md
3.7 KB
---
name: youtube-instant-article
description: Transform YouTube videos into Telegraph Instant View articles with visual slides and timestamped summaries. Use this skill whenever a user shares a YouTube URL (youtube.com or youtu.be) and asks to summarize, explain, or process the video. This is the DEFAULT skill for all YouTube video requests - do NOT use the generic summarize tool for YouTube.
argument-hint: <youtube-url>
allowed-tools: Bash(summarize:*), Bash(curl:*), Bash(jq:*)
---

# YouTube Instant Article

Transform YouTube videos into Telegraph Instant View articles with visual slides and timestamped summaries.

## When to Use

**ALWAYS use this skill when:**
- User shares a YouTube URL (any youtube.com or youtu.be link)
- "Summarize this video"
- "What's this video about?"
- "Turn this into an article"
- "Give me the gist of this video"

**Only use generic `summarize` for:**
- Non-YouTube URLs (articles, websites, PDFs)
- Explicit "just give me the transcript" requests

## Quick Start

```bash
source /Users/viticci/clawd/.env && {baseDir}/scripts/generate.sh "$ARGUMENTS"
```

## Options

| Flag | Default | Description |
|------|---------|-------------|
| `--slides-max N` | 6 | Maximum slides to extract |
| `--debug` | off | Keep temp files for debugging |

## Environment Variables

Required environment variables are loaded from `/Users/viticci/clawd/.env`:
- `TELEGRAPH_TOKEN` - Telegraph API access token
- `OPENAI_API_KEY` - For GPT-5.2 summarization

## Output

Telegraph Instant View article with:
- 📺 Video link at top
- 🖼️ Slides interleaved with timestamped sections
- ⏱️ Key moments with timestamps
- 💬 Notable quotes as blockquotes
- ✨ Proper title from YouTube

## Architecture

```
YouTube URL
    │
    ├─► summarize --extract (get video title)
    │
    ├─► summarize --slides (extract key frames)
    │
    ├─► summarize --timestamps (GPT-5.2 summary)
    │
    ├─► catbox.moe (upload images)
    │
    └─► Telegraph API (create article)
```

## Key Features

### Image Hosting: catbox.moe
- No API key required
- No expiration
- Reliable CDN
- Direct URL embedding

### LLM: OpenAI GPT-5.2
- Fast (~4-5 seconds)
- High quality summaries
- Automatic timestamp extraction

### Layout: Interleaved Images
- Images distributed across timestamp sections
- Not grouped at top
- Each major section gets a relevant slide

## ⚠️ Important Notes

### Instant View Timing
Telegram needs **1-2 minutes** to generate Instant View for new pages. If the ⚡ button doesn't appear immediately, wait and try again.

### Script Requirements
- Uses **zsh** (not bash) for associative array support
- Requires: `summarize`, `jq`, `curl`
- Optional: `ffmpeg` (for local video processing)

### Always Use the Script
**NEVER manually create Telegraph content.** Always use `generate.sh`:
- Ensures proper h4 headers (required for Instant View)
- Distributes images correctly
- Extracts video title automatically

## Dependencies

- `summarize` v0.10.0+ (`brew install steipete/tap/summarize`)
- `jq` (`brew install jq`)
- `curl` (pre-installed on macOS)
- OpenAI API key with GPT-5.2 access

## Processing Time

| Video Length | Approx. Time |
|--------------|--------------|
| < 15 min | 20-30s |
| 15-30 min | 30-45s |
| 30+ min | 45-60s+ |

## Troubleshooting

### "Failed to get summary"
- Check `OPENAI_API_KEY` is set
- Verify API key has GPT-5.2 access
- Try with `--debug` flag

### No Instant View button
- Wait 1-2 minutes for Telegram to process
- Verify article has content (not empty)
- Check images loaded (visit Telegraph URL directly)

### Images not showing
- catbox.moe might be temporarily down
- Check upload succeeded in debug output
- Verify URLs are HTTPS

Overview

This skill transforms YouTube videos into Telegraph Instant View articles with visual slides, timestamped summaries, and notable quotes. It automates extracting the title, key frames, and GPT-5.2-powered section summaries, then uploads images and publishes a properly formatted Instant View page.

How this skill works

Given a youtube.com or youtu.be URL, the tool extracts the video title, captures representative slides, and runs a GPT-5.2 summarization pass to produce timestamped sections and key moments. Images are uploaded to catbox.moe and interleaved with the corresponding timestamped text. A Telegraph Instant View article is created via the Telegraph API, ready for Telegram to index.

When to use it

  • User shares any YouTube URL and asks to summarize, explain, or convert the video.
  • You want a readable article with visual slides and timestamped key moments.
  • You need a shareable Instant View page for Telegram that preserves visual context.
  • You want automatic extraction of quotes and a polished title from the video.

Best practices

  • Always provide a direct youtube.com or youtu.be link; this skill is the default for YouTube content.
  • Use the --slides-max flag to control how many visual slides are included for long videos.
  • Set TELEGRAPH_TOKEN and OPENAI_API_KEY with GPT-5.2 access before running the tool.
  • Use --debug when troubleshooting to keep temp files and inspect uploads.
  • Allow 1–2 minutes after publishing for Telegram to generate the Instant View button.

Example use cases

  • Convert a lecture or tutorial into an article with clear timestamped sections and supporting images.
  • Summarize a long interview into key moments with notable quotes highlighted.
  • Create a quick shareable Instant View article for social distribution from a product demo video.
  • Archive important videos as readable articles for a project documentation site.

FAQ

What input links does this support?

Any youtube.com or youtu.be URL — always use this skill for YouTube links.

Where are images hosted?

Images are uploaded to catbox.moe for stable direct URLs and CDN delivery.

How long does processing take?

Roughly 20–30s for videos under 15 minutes, ~30–45s for 15–30 minutes, and 45–60s+ for longer videos.