tapestry

Activate when the user:

• Says "tapestry [URL]"
• Says "weave [URL]"
• Says "help me plan [URL]"
• Says "extract and plan [URL]"
• Says "make this actionable [URL]"
• Says "turn [URL] into a plan"
• Provides a URL and asks to "learn and implement from this"
• Wants the full Tapestry workflow (extract → plan)

Keywords to watch for: tapestry, weave, plan, actionable, extract and plan, make a plan, turn into action

Complete Workflow:

1. Detect URL type (YouTube, article, PDF)
2. Extract content using appropriate skill:

- YouTube → youtube-transcript skill

- Article → article-extractor skill

- PDF → download and extract text

1. Create action plan using ship-learn-next skill
2. Save both content file and plan file
3. Present summary to user

YouTube Videos

Patterns to detect:

• youtube.com/watch?v=
• youtu.be/
• youtube.com/shorts/
• m.youtube.com/watch?v=

Action: Use youtube-transcript skill

Web Articles/Blog Posts

Patterns to detect:

• http:// or https://
• NOT YouTube, NOT PDF
• Common domains: medium.com, substack.com, dev.to, etc.
• Any HTML page

Action: Use article-extractor skill

PDF Documents

Patterns to detect:

• URL ends with .pdf
• URL returns Content-Type: application/pdf

Action: Download and extract text

Other Content

Fallback:

• Try article-extractor (works for most HTML)
• If fails, inform user of unsupported type

Step 1: Detect Content Type

```bash

URL="$1"

# Check for YouTube

if [[ "$URL" =~ youtube\.com/watch || "$URL" =~ youtu\.be/ || "$URL" =~ youtube\.com/shorts ]]; then

CONTENT_TYPE="youtube"

# Check for PDF

elif [[ "$URL" =~ \.pdf$ ]]; then

CONTENT_TYPE="pdf"

# Check if URL returns PDF

elif curl -sI "$URL" | grep -i "Content-Type: application/pdf" > /dev/null; then

CONTENT_TYPE="pdf"

# Default to article

else

CONTENT_TYPE="article"

fi

echo "📍 Detected: $CONTENT_TYPE"

```

Step 2: Extract Content (by Type)

#### YouTube Video

```bash

# Use youtube-transcript skill workflow

echo "📺 Extracting YouTube transcript..."

# 1. Check for yt-dlp

if ! command -v yt-dlp &> /dev/null; then

echo "Installing yt-dlp..."

brew install yt-dlp

fi

# 2. Get video title

VIDEO_TITLE=$(yt-dlp --print "%(title)s" "$URL" | tr '/' '_' | tr ':' '-' | tr '?' '' | tr '"' '')

# 3. Download transcript

yt-dlp --write-auto-sub --skip-download --sub-langs en --output "temp_transcript" "$URL"

# 4. Convert to clean text (deduplicate)

python3 -c "

import sys, re

seen = set()

vtt_file = 'temp_transcript.en.vtt'

try:

with open(vtt_file, 'r') as f:

for line in f:

line = line.strip()

if line and not line.startswith('WEBVTT') and not line.startswith('Kind:') and not line.startswith('Language:') and '-->' not in line:

clean = re.sub('<[^>]*>', '', line)

clean = clean.replace('&', '&').replace('>', '>').replace('<', '<')

if clean and clean not in seen:

print(clean)

seen.add(clean)

except FileNotFoundError:

print('Error: Could not find transcript file', file=sys.stderr)

sys.exit(1)

" > "${VIDEO_TITLE}.txt"

# 5. Cleanup

rm -f temp_transcript.en.vtt

CONTENT_FILE="${VIDEO_TITLE}.txt"

echo "✓ Saved transcript: $CONTENT_FILE"

```

#### Article/Blog Post

```bash

# Use article-extractor skill workflow

echo "📄 Extracting article content..."

# 1. Check for extraction tools

if command -v reader &> /dev/null; then

TOOL="reader"

elif command -v trafilatura &> /dev/null; then

TOOL="trafilatura"

else

TOOL="fallback"

fi

echo "Using: $TOOL"

# 2. Extract based on tool

case $TOOL in

reader)

reader "$URL" > temp_article.txt

ARTICLE_TITLE=$(head -n 1 temp_article.txt | sed 's/^# //')

;;

trafilatura)

METADATA=$(trafilatura --URL "$URL" --json)

ARTICLE_TITLE=$(echo "$METADATA" | python3 -c "import json, sys; print(json.load(sys.stdin).get('title', 'Article'))")

trafilatura --URL "$URL" --output-format txt --no-comments > temp_article.txt

;;

fallback)

ARTICLE_TITLE=$(curl -s "$URL" | grep -oP '