⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

article-extractor

michalparkola@michalparkola⭐ 576 stars· last commit 8mo ago· 1 open issues

Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐⭐⭐ 576 on GitHubGitHub ↗

Popular

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Tapestry Skills for AI Agents

A collection of productivity skills for AI agents like Claude Code that help you work faster and learn better.

Are you a founder of a tech company? Check out Tapestry – the AI planning partner that helps everyone on your team make better decisions faster.

SkillWhat it does
Learn ThisOne command to extract content from any URL and turn it into an action plan.
Ship-Learn-NextTransform learning content into a 5-rep action plan you can ship.
YouTube TranscriptDownload and clean YouTube video transcripts with deduplication.
Article ExtractorExtract clean, readable text from web articles and blog posts.
Scrum SageAI Scrum Master and agile coach grounded in Sutherland, Ohno, and First Principles.
Session LogSummarize your session and append it to a weekly agent-log file.
Unblock ActionTurn a vague stuck task into a concrete next action in under 2 minutes.

Skills Included

0. Learn This ⭐

The unified workflow that orchestrates everything. Just say learn-this <URL> and it:

  1. Detects content type (YouTube, article, PDF)
  2. Extracts clean content
  3. Automatically creates a Ship-Learn-Next action plan

One command. Complete workflow. From learning to shipping.

1. YouTube Transcript Downloader

Download and clean YouTube video transcripts with automatic deduplication and readable formatting.

Features:

  • Downloads transcripts using yt-dlp
  • Removes duplicate lines (YouTube VTT format issue)
  • Uses video title for filename
  • Fallback to Whisper transcription if no subtitles available
  • Automatic cleanup of temporary files

Use cases:

  • Get transcripts from educational videos
  • Extract content from tutorials
  • Archive important talks/interviews

2. Article Extractor

Extract clean, readable content from web articles and blog posts, removing ads, navigation, and clutter.

Features:

  • Uses Mozilla Readability or trafilatura for extraction
  • Removes ads, navigation, and newsletter signups
  • Saves as clean plain text
  • Uses article title for filename
  • Multiple extraction methods with automatic fallback

Use cases:

  • Save articles for offline reading
  • Extract tutorial content
  • Archive important blog posts
  • Get clean text without distractions

3. Scrum Sage

AI-powered Scrum Master and Enterprise Agility Coach based on Jeff Sutherland, Taiichi Ohno, and First Principles thinking.

Features:

  • Sprint analysis (basic and expert modes)
  • Backlog refinement and story sizing guidance
  • Anti-pattern detection and impediment radar
  • Flow efficiency and cognitive load analysis
  • Scrum@Scale advice for growing organizations
  • Retrospective synthesis and predictive modeling

Use cases:

  • Get coaching on Scrum mechanics, ceremonies, and artifacts
  • Analyze sprint health, velocity trends, and predictability
  • Remove impediments and detect systemic bottlenecks
  • Plan scaling strategy (with Scrum@Scale, not SAFe)
  • Facilitate retrospectives and backlog refinement
  • Optimize team dynamics and sustainable pace

4. Session Log

Summarize your Claude Code conversation and append it to a weekly agent-log file.

Features:

  • Reverse chronological daily entries
  • Automatic ISO week file naming (YYYY-wWW agent-log.md)
  • CHUNK markers for reusable outputs (plans, summaries, frameworks)
  • Appends without overwriting existing entries
  • Multi-day session support with date attribution

Use cases:

  • Log what you accomplished in a session
  • Build a searchable weekly work journal
  • Track decisions, outputs, and topics across sessions

5. Unblock Action

Get unstuck on vague or overwhelming tasks. Clarifies the intended output, scopes it to today, and identifies the concrete next physical action.

Features:

  • Socratic but fast — 2-3 questions max
  • Turns fuzzy goals into concrete deliverables
  • Scopes multi-day projects to today's completable slice
  • Outputs a clean action card with deliverable, scope, and next step

Use cases:

  • "I need to work on marketing but can't start"
  • "I'm stuck on pricing"
  • "I have to do something about onboarding"
  • Any vague task you keep avoiding

6. Ship-Learn-Next Action Planner

Transform passive learning content (transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework.

Features:

  • Converts advice into concrete, shippable iterations (reps)
  • Creates 5-rep action plans with timelines
  • Focuses on DOING over studying
  • Includes reflection questions after each rep
  • Saves plan to markdown file

Use cases:

  • Turn YouTube tutorials into action plans
  • Extract implementation steps from articles
  • Create learning quests from course content
  • Build by shipping, not just consuming

Installation

Quick Install for Claude Code

# Clone the repository
git clone https://github.com/michalparkola/tapestry-skills.git

# Run the installation script
cd tapestry-skills
chmod +x install.sh
./install.sh

Manual Installation

Option 1: Personal Skills (Available in all projects)

# Create personal skills directory if it doesn't exist
mkdir -p ~/.claude/skills

# Copy skills
cp -r learn-this ~/.claude/skills/
cp -r youtube-transcript ~/.claude/skills/
cp -r article-extractor ~/.claude/skills/
cp -r ship-learn-next ~/.claude/skills/
cp -r scrum-sage ~/.claude/skills/
cp -r session-log ~/.claude/skills/
cp -r unblock-action ~/.claude/skills/

Option 2: Project Skills (Only in specific project)

# In your project directory
mkdir -p .claude/skills

# Copy skills
cp -r /path/to/tapestry-skills-for-claude-code/learn-this .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/youtube-transcript .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/article-extractor .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/ship-learn-next .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/scrum-sage .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/session-log .claude/skills/
cp -r /path/to/tapestry-skills-for-claude-code/unblock-action .claude/skills/

Usage

Learn This (Recommended - Use This!)

The simplest way to use Tapestry skills. One command extracts content and creates your action plan:

"learn-this https://www.youtube.com/watch?v=VIDEO_ID"
"weave https://example.com/article"
"help me plan https://example.com/paper.pdf"
"make this actionable https://blog.com/post"

All these phrases work: learn-this, learn this, weave, help me plan, extract and plan, make this actionable

The skill will:

  1. Detect content type (YouTube/article/PDF)
  2. Extract clean content
  3. Create a Ship-Learn-Next action plan automatically
  4. Save both files
  5. Ask: "When will you ship Rep 1?"

YouTube Transcript Downloader

Once installed, Claude will automatically use this skill when you ask to download YouTube transcripts:

"Download the transcript for https://www.youtube.com/watch?v=VIDEO_ID"

The skill will:

  1. Check if yt-dlp is installed (install if needed)
  2. List available subtitles
  3. Try manual subtitles first, then auto-generated
  4. Convert to readable plain text with video title as filename
  5. Remove duplicate lines
  6. Clean up temporary files

Article Extractor

Claude will use this skill when you ask to extract content from a URL:

"Extract the article from https://example.com/blog-post"
"Download this article without the ads"

The skill will:

  1. Check for extraction tools (reader or trafilatura)
  2. Download and extract clean article content
  3. Remove ads, navigation, and clutter
  4. Save as plain text with article title as filename
  5. Show preview of extracted content

Scr

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • article-extractor/SKILL.md7.8 KBupstream ↗
    ---
    name: article-extractor
    description: Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
    allowed-tools: Bash,Write
    ---
    
    # Article Extractor
    
    This skill extracts the main content from web articles and blog posts, removing navigation, ads, newsletter signups, and other clutter. Saves clean, readable text.
    
    ## When to Use This Skill
    
    Activate when the user:
    - Provides an article/blog URL and wants the text content
    - Asks to "download this article"
    - Wants to "extract the content from [URL]"
    - Asks to "save this blog post as text"
    - Needs clean article text without distractions
    
    ## How It Works
    
    ### Priority Order:
    1. **Check if tools are installed** (reader or trafilatura)
    2. **Download and extract article** using best available tool
    3. **Clean up the content** (remove extra whitespace, format properly)
    4. **Save to file** with article title as filename
    5. **Confirm location** and show preview
    
    ## Installation Check
    
    Check for article extraction tools in this order:
    
    ### Option 1: reader (Recommended - Mozilla's Readability)
    
    ```bash
    command -v reader
    ```
    
    If not installed:
    ```bash
    npm install -g @mozilla/readability-cli
    # or
    npm install -g reader-cli
    ```
    
    ### Option 2: trafilatura (Python-based, very good)
    
    ```bash
    command -v trafilatura
    ```
    
    If not installed:
    ```bash
    pip3 install trafilatura
    ```
    
    ### Option 3: Fallback (curl + simple parsing)
    
    If no tools available, use basic curl + text extraction (less reliable but works)
    
    ## Extraction Methods
    
    ### Method 1: Using reader (Best for most articles)
    
    ```bash
    # Extract article
    reader "URL" > article.txt
    ```
    
    **Pros:**
    - Based on Mozilla's Readability algorithm
    - Excellent at removing clutter
    - Preserves article structure
    
    ### Method 2: Using trafilatura (Best for blogs/news)
    
    ```bash
    # Extract article
    trafilatura --URL "URL" --output-format txt > article.txt
    
    # Or with more options
    trafilatura --URL "URL" --output-format txt --no-comments --no-tables > article.txt
    ```
    
    **Pros:**
    - Very accurate extraction
    - Good with various site structures
    - Handles multiple languages
    
    **Options:**
    - `--no-comments`: Skip comment sections
    - `--no-tables`: Skip data tables
    - `--precision`: Favor precision over recall
    - `--recall`: Extract more content (may include some noise)
    
    ### Method 3: Fallback (curl + basic parsing)
    
    ```bash
    # Download and extract basic content
    curl -s "URL" | python3 -c "
    from html.parser import HTMLParser
    import sys
    
    class ArticleExtractor(HTMLParser):
        def __init__(self):
            super().__init__()
            self.in_content = False
            self.content = []
            self.skip_tags = {'script', 'style', 'nav', 'header', 'footer', 'aside'}
            self.current_tag = None
    
        def handle_starttag(self, tag, attrs):
            if tag not in self.skip_tags:
                if tag in {'p', 'article', 'main', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'}:
                    self.in_content = True
            self.current_tag = tag
    
        def handle_data(self, data):
            if self.in_content and data.strip():
                self.content.append(data.strip())
    
        def get_content(self):
            return '\n\n'.join(self.content)
    
    parser = ArticleExtractor()
    parser.feed(sys.stdin.read())
    print(parser.get_content())
    " > article.txt
    ```
    
    **Note:** This is less reliable but works without dependencies.
    
    ## Getting Article Title
    
    Extract title for filename:
    
    ### Using reader:
    ```bash
    # reader outputs markdown with title at top
    TITLE=$(reader "URL" | head -n 1 | sed 's/^# //')
    ```
    
    ### Using trafilatura:
    ```bash
    # Get metadata including title
    TITLE=$(trafilatura --URL "URL" --json | python3 -c "import json, sys; print(json.load(sys.stdin)['title'])")
    ```
    
    ### Using curl (fallback):
    ```bash
    TITLE=$(curl -s "URL" | grep -oP '<title>\K[^<]+' | sed 's/ - .*//' | sed 's/ | .*//')
    ```
    
    ## Filename Creation
    
    Clean title for filesystem:
    
    ```bash
    # Get title
    TITLE="Article Title from Website"
    
    # Clean for filesystem (remove special chars, limit length)
    FILENAME=$(echo "$TITLE" | tr '/' '-' | tr ':' '-' | tr '?' '' | tr '"' '' | tr '<' '' | tr '>' '' | tr '|' '-' | cut -c 1-100 | sed 's/ *$//')
    
    # Add extension
    FILENAME="${FILENAME}.txt"
    ```
    
    ## Complete Workflow
    
    ```bash
    ARTICLE_URL="https://example.com/article"
    
    # Check for tools
    if command -v reader &> /dev/null; then
        TOOL="reader"
        echo "Using reader (Mozilla Readability)"
    elif command -v trafilatura &> /dev/null; then
        TOOL="trafilatura"
        echo "Using trafilatura"
    else
        TOOL="fallback"
        echo "Using fallback method (may be less accurate)"
    fi
    
    # Extract article
    case $TOOL in
        reader)
            # Get content
            reader "$ARTICLE_URL" > temp_article.txt
    
            # Get title (first line after # in markdown)
            TITLE=$(head -n 1 temp_article.txt | sed 's/^# //')
            ;;
    
        trafilatura)
            # Get title from metadata
            METADATA=$(trafilatura --URL "$ARTICLE_URL" --json)
            TITLE=$(echo "$METADATA" | python3 -c "import json, sys; print(json.load(sys.stdin).get('title', 'Article'))")
    
            # Get clean content
            trafilatura --URL "$ARTICLE_URL" --output-format txt --no-comments > temp_article.txt
            ;;
    
        fallback)
            # Get title
            TITLE=$(curl -s "$ARTICLE_URL" | grep -oP '<title>\K[^<]+' | head -n 1)
            TITLE=${TITLE%% - *}  # Remove site name
            TITLE=${TITLE%% | *}  # Remove site name (alternate)
    
            # Get content (basic extraction)
            curl -s "$ARTICLE_URL" | python3 -c "
    from html.parser import HTMLParser
    import sys
    
    class ArticleExtractor(HTMLParser):
        def __init__(self):
            super().__init__()
            self.in_content = False
            self.content = []
            self.skip_tags = {'script', 'style', 'nav', 'header', 'footer', 'aside', 'form'}
    
        def handle_starttag(self, tag, attrs):
            if tag not in self.skip_tags:
                if tag in {'p', 'article', 'main'}:
                    self.in_content = True
            if tag in {'h1', 'h2', 'h3'}:
                self.content.append('\n')
    
        def handle_data(self, data):
            if self.in_content and data.strip():
                self.content.append(data.strip())
    
        def get_content(self):
            return '\n\n'.join(self.content)
    
    parser = ArticleExtractor()
    parser.feed(sys.stdin.read())
    print(parser.get_content())
    " > temp_article.txt
            ;;
    esac
    
    # Clean filename
    FILENAME=$(echo "$TITLE" | tr '/' '-' | tr ':' '-' | tr '?' '' | tr '"' '' | tr '<>' '' | tr '|' '-' | cut -c 1-80 | sed 's/ *$//' | sed 's/^ *//')
    FILENAME="${FILENAME}.txt"
    
    # Move to final filename
    mv temp_article.txt "$FILENAME"
    
    # Show result
    echo "✓ Extracted article: $TITLE"
    echo "✓ Saved to: $FILENAME"
    echo ""
    echo "Preview (first 10 lines):"
    head -n 10 "$FILENAME"
    ```
    
    ## Error Handling
    
    ### Common Issues
    
    **1. Tool not installed**
    - Try alternate tool (reader → trafilatura → fallback)
    - Offer to install: "Install reader with: npm install -g reader-cli"
    
    **2. Paywall or login required**
    - Extraction tools may fail
    - Inform user: "This article requires authentication. Cannot extract."
    
    **3. Invalid URL**
    - Check URL format
    - Try with and without redirects
    
    **4. No content extracted**
    - Site may use heavy JavaScript
    - Try fallback method
    - Inform user if extraction fails
    
    **5. Special characters in title**
    - Clean title for filesystem
    - Remove: `/`, `:`, `?`, `"`, `<`, `>`, `|`
    - Replace with `-` or remove
    
    ## Output Format
    
    ### Saved File Contains:
    - Article title (if available)
    - Author (if available from tool)
    - Main article text
    - Section headings
    - No navigation, ads, or clutter
    
    ### What Gets Removed:
    - Navigation menus
    - Ads and promotional content
    - Newsletter signup forms
    - Related articles sidebars
    - Comment sections (optional)
    - Social media buttons
    - Cookie notices
    
    ## Tips for Best Results
    
    **1. Use reader for most articles**
    - Best all-around tool
    - Based on Firefox Reader View
    - Works on most news site
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/michalparkola-tapestry-skills-article-extractor.md

// REPO STATS

576 stars
1 open issues
Last commit: 8mo ago