@vodailoc/kilo-kit-mcp 1.1.0

package/skills/ai-media/geo-fundamentals/scripts/geo_checker.py

@@ -0,0 +1,289 @@
+#!/usr/bin/env python3
+"""
+GEO Checker - Generative Engine Optimization Audit
+Checks PUBLIC WEB CONTENT for AI citation readiness.
+
+PURPOSE:
+    - Analyze pages that will be INDEXED by AI engines (ChatGPT, Perplexity, etc.)
+    - Check for structured data, author info, dates, FAQ sections
+    - Help content rank in AI-generated answers
+
+WHAT IT CHECKS:
+    - HTML files (actual web pages)
+    - JSX/TSX files (React page components)
+    - NOT markdown files (those are developer docs, not public content)
+
+Usage:
+    python geo_checker.py <project_path>
+"""
+import sys
+import re
+import json
+from pathlib import Path
+
+# Fix Windows console encoding
+try:
+    sys.stdout.reconfigure(encoding='utf-8', errors='replace')
+    sys.stderr.reconfigure(encoding='utf-8', errors='replace')
+except AttributeError:
+    pass
+
+
+# Directories to skip (not public content)
+SKIP_DIRS = {
+    'node_modules', '.next', 'dist', 'build', '.git', '.github',
+    '__pycache__', '.vscode', '.idea', 'coverage', 'test', 'tests',
+    '__tests__', 'spec', 'docs', 'documentation'
+}
+
+# Files to skip (not public pages)
+SKIP_FILES = {
+    'jest.config', 'webpack.config', 'vite.config', 'tsconfig',
+    'package.json', 'package-lock', 'yarn.lock', '.eslintrc',
+    'tailwind.config', 'postcss.config', 'next.config'
+}
+
+
+def is_page_file(file_path: Path) -> bool:
+    """Check if this file is likely a public-facing page."""
+    name = file_path.stem.lower()
+    
+    # Skip config/utility files
+    if any(skip in name for skip in SKIP_FILES):
+        return False
+    
+    # Skip test files
+    if name.endswith('.test') or name.endswith('.spec'):
+        return False
+    if name.startswith('test_') or name.startswith('spec_'):
+        return False
+    
+    # Likely page indicators
+    page_indicators = ['page', 'index', 'home', 'about', 'contact', 'blog', 
+                       'post', 'article', 'product', 'service', 'landing']
+    
+    # Check if it's in a pages/app directory (Next.js, etc.)
+    parts = [p.lower() for p in file_path.parts]
+    if 'pages' in parts or 'app' in parts or 'routes' in parts:
+        return True
+    
+    # Check filename indicators
+    if any(ind in name for ind in page_indicators):
+        return True
+    
+    # HTML files are usually pages
+    if file_path.suffix.lower() == '.html':
+        return True
+    
+    return False
+
+
+def find_web_pages(project_path: Path) -> list:
+    """Find public-facing web pages only."""
+    patterns = ['**/*.html', '**/*.htm', '**/*.jsx', '**/*.tsx']
+    
+    files = []
+    for pattern in patterns:
+        for f in project_path.glob(pattern):
+            # Skip excluded directories
+            if any(skip in f.parts for skip in SKIP_DIRS):
+                continue
+            
+            # Check if it's likely a page
+            if is_page_file(f):
+                files.append(f)
+    
+    return files[:30]  # Limit to 30 pages
+
+
+def check_page(file_path: Path) -> dict:
+    """Check a single web page for GEO elements."""
+    try:
+        content = file_path.read_text(encoding='utf-8', errors='ignore')
+    except Exception as e:
+        return {'file': str(file_path.name), 'passed': [], 'issues': [f"Error: {e}"], 'score': 0}
+    
+    issues = []
+    passed = []
+    
+    # 1. JSON-LD Structured Data (Critical for AI)
+    if 'application/ld+json' in content:
+        passed.append("JSON-LD structured data found")
+        if '"@type"' in content:
+            if 'Article' in content:
+                passed.append("Article schema present")
+            if 'FAQPage' in content:
+                passed.append("FAQ schema present")
+            if 'Organization' in content or 'Person' in content:
+                passed.append("Entity schema present")
+    else:
+        issues.append("No JSON-LD structured data (AI engines prefer structured content)")
+    
+    # 2. Heading Structure
+    h1_count = len(re.findall(r'<h1[^>]*>', content, re.I))
+    h2_count = len(re.findall(r'<h2[^>]*>', content, re.I))
+    
+    if h1_count == 1:
+        passed.append("Single H1 heading (clear topic)")
+    elif h1_count == 0:
+        issues.append("No H1 heading - page topic unclear")
+    else:
+        issues.append(f"Multiple H1 headings ({h1_count}) - confusing for AI")
+    
+    if h2_count >= 2:
+        passed.append(f"{h2_count} H2 subheadings (good structure)")
+    else:
+        issues.append("Add more H2 subheadings for scannable content")
+    
+    # 3. Author Attribution (E-E-A-T signal)
+    author_patterns = ['author', 'byline', 'written-by', 'contributor', 'rel="author"']
+    has_author = any(p in content.lower() for p in author_patterns)
+    if has_author:
+        passed.append("Author attribution found")
+    else:
+        issues.append("No author info (AI prefers attributed content)")
+    
+    # 4. Publication Date (Freshness signal)
+    date_patterns = ['datePublished', 'dateModified', 'datetime=', 'pubdate', 'article:published']
+    has_date = any(re.search(p, content, re.I) for p in date_patterns)
+    if has_date:
+        passed.append("Publication date found")
+    else:
+        issues.append("No publication date (freshness matters for AI)")
+    
+    # 5. FAQ Section (Highly citable)
+    faq_patterns = [r'<details', r'faq', r'frequently.?asked', r'"FAQPage"']
+    has_faq = any(re.search(p, content, re.I) for p in faq_patterns)
+    if has_faq:
+        passed.append("FAQ section detected (highly citable)")
+    
+    # 6. Lists (Structured content)
+    list_count = len(re.findall(r'<(ul|ol)[^>]*>', content, re.I))
+    if list_count >= 2:
+        passed.append(f"{list_count} lists (structured content)")
+    
+    # 7. Tables (Comparison data)
+    table_count = len(re.findall(r'<table[^>]*>', content, re.I))
+    if table_count >= 1:
+        passed.append(f"{table_count} table(s) (comparison data)")
+    
+    # 8. Entity Recognition (E-E-A-T signal) - NEW 2025
+    entity_patterns = [
+        r'"@type"\s*:\s*"Organization"',
+        r'"@type"\s*:\s*"LocalBusiness"', 
+        r'"@type"\s*:\s*"Brand"',
+        r'itemtype.*schema\.org/(Organization|Person|Brand)',
+        r'rel="author"'
+    ]
+    has_entity = any(re.search(p, content, re.I) for p in entity_patterns)
+    if has_entity:
+        passed.append("Entity/Brand recognition (E-E-A-T)")
+    
+    # 9. Original Statistics/Data (AI citation magnet) - NEW 2025
+    stat_patterns = [
+        r'\d+%',                    # Percentages
+        r'\$[\d,]+',                # Dollar amounts
+        r'study\s+(shows|found)',   # Research citations
+        r'according to',            # Source attribution
+        r'data\s+(shows|reveals)',  # Data-backed claims
+        r'\d+x\s+(faster|better|more)', # Comparison stats
+        r'(million|billion|trillion)', # Large numbers
+    ]
+    stat_matches = sum(1 for p in stat_patterns if re.search(p, content, re.I))
+    if stat_matches >= 2:
+        passed.append("Original statistics/data (citation magnet)")
+    
+    # 10. Conversational/Direct answers - NEW 2025
+    direct_answer_patterns = [
+        r'is defined as',
+        r'refers to',
+        r'means that',
+        r'the answer is',
+        r'in short,',
+        r'simply put,',
+        r'<dfn'
+    ]
+    has_direct = any(re.search(p, content, re.I) for p in direct_answer_patterns)
+    if has_direct:
+        passed.append("Direct answer patterns (LLM-friendly)")
+    
+    # Calculate score
+    total = len(passed) + len(issues)
+    score = (len(passed) / total * 100) if total > 0 else 0
+    
+    return {
+        'file': str(file_path.name),
+        'passed': passed,
+        'issues': issues,
+        'score': round(score)
+    }
+
+
+def main():
+    target = sys.argv[1] if len(sys.argv) > 1 else "."
+    target_path = Path(target).resolve()
+    
+    print("\n" + "=" * 60)
+    print("  GEO CHECKER - AI Citation Readiness Audit")
+    print("=" * 60)
+    print(f"Project: {target_path}")
+    print("-" * 60)
+    
+    # Find web pages only
+    pages = find_web_pages(target_path)
+    
+    if not pages:
+        print("\n[!] No public web pages found.")
+        print("    Looking for: HTML, JSX, TSX files in pages/app directories")
+        print("    Skipping: docs, tests, config files, node_modules")
+        output = {"script": "geo_checker", "pages_found": 0, "passed": True}
+        print("\n" + json.dumps(output, indent=2))
+        sys.exit(0)
+    
+    print(f"Found {len(pages)} public pages to analyze\n")
+    
+    # Check each page
+    results = []
+    for page in pages:
+        result = check_page(page)
+        results.append(result)
+    
+    # Print results
+    for result in results:
+        status = "[OK]" if result['score'] >= 60 else "[!]"
+        print(f"{status} {result['file']}: {result['score']}%")
+        if result['issues'] and result['score'] < 60:
+            for issue in result['issues'][:2]:  # Show max 2 issues
+                print(f"    - {issue}")
+    
+    # Average score
+    avg_score = sum(r['score'] for r in results) / len(results) if results else 0
+    
+    print("\n" + "=" * 60)
+    print(f"AVERAGE GEO SCORE: {avg_score:.0f}%")
+    print("=" * 60)
+    
+    if avg_score >= 80:
+        print("[OK] Excellent - Content well-optimized for AI citations")
+    elif avg_score >= 60:
+        print("[OK] Good - Some improvements recommended")
+    elif avg_score >= 40:
+        print("[!] Needs work - Add structured elements")
+    else:
+        print("[X] Poor - Content needs GEO optimization")
+    
+    # JSON output
+    output = {
+        "script": "geo_checker",
+        "project": str(target_path),
+        "pages_checked": len(results),
+        "average_score": round(avg_score),
+        "passed": avg_score >= 60
+    }
+    print("\n" + json.dumps(output, indent=2))
+    
+    sys.exit(0 if avg_score >= 60 else 1)
+
+
+if __name__ == "__main__":
+    main()

package/skills/ai-media/media-processing/SKILL.md

@@ -0,0 +1,358 @@
+---
+name: media-processing
+description: Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
+license: MIT
+---
+
+# Media Processing Skill
+
+Process video, audio, and images using FFmpeg and ImageMagick command-line tools for conversion, optimization, streaming, and manipulation tasks.
+
+## When to Use This Skill
+
+Use when:
+- Converting media formats (video, audio, images)
+- Encoding video with codecs (H.264, H.265, VP9, AV1)
+- Processing images (resize, crop, effects, watermarks)
+- Extracting audio from video
+- Creating streaming manifests (HLS/DASH)
+- Generating thumbnails and previews
+- Batch processing media files
+- Optimizing file sizes and quality
+- Applying filters and effects
+- Creating composite images or videos
+
+## Tool Selection Guide
+
+### FFmpeg: Video/Audio Processing
+Use FFmpeg for:
+- Video encoding, conversion, transcoding
+- Audio extraction, conversion, mixing
+- Live streaming (RTMP, HLS, DASH)
+- Video filters (scale, crop, rotate, overlay)
+- Hardware-accelerated encoding
+- Media file inspection (ffprobe)
+- Frame extraction, concatenation
+- Codec selection and optimization
+
+### ImageMagick: Image Processing
+Use ImageMagick for:
+- Image format conversion (PNG, JPEG, WebP, GIF)
+- Resizing, cropping, transformations
+- Batch image processing (mogrify)
+- Visual effects (blur, sharpen, sepia)
+- Text overlays and watermarks
+- Image composition and montages
+- Color adjustments, filters
+- Thumbnail generation
+
+### Decision Matrix
+
+| Task | Tool | Why |
+|------|------|-----|
+| Video encoding | FFmpeg | Native video codec support |
+| Audio extraction | FFmpeg | Direct stream manipulation |
+| Image resize | ImageMagick | Optimized for still images |
+| Batch images | ImageMagick | mogrify for in-place edits |
+| Video thumbnails | FFmpeg | Frame extraction built-in |
+| GIF creation | FFmpeg or ImageMagick | FFmpeg for video source, ImageMagick for images |
+| Streaming | FFmpeg | Live streaming protocols |
+| Image effects | ImageMagick | Rich filter library |
+
+## Installation
+
+### macOS
+```bash
+brew install ffmpeg imagemagick
+```
+
+### Ubuntu/Debian
+```bash
+sudo apt-get install ffmpeg imagemagick
+```
+
+### Windows
+```bash
+# Using winget
+winget install ffmpeg
+winget install ImageMagick.ImageMagick
+
+# Or download binaries
+# FFmpeg: https://ffmpeg.org/download.html
+# ImageMagick: https://imagemagick.org/script/download.php
+```
+
+### Verify Installation
+```bash
+ffmpeg -version
+ffprobe -version
+magick -version
+# or
+convert -version
+```
+
+## Quick Start Examples
+
+### Video Conversion
+```bash
+# Convert format (copy streams, fast)
+ffmpeg -i input.mkv -c copy output.mp4
+
+# Re-encode with H.264
+ffmpeg -i input.avi -c:v libx264 -crf 22 -c:a aac output.mp4
+
+# Resize video to 720p
+ffmpeg -i input.mp4 -vf scale=-1:720 -c:a copy output.mp4
+```
+
+### Audio Extraction
+```bash
+# Extract audio (no re-encoding)
+ffmpeg -i video.mp4 -vn -c:a copy audio.m4a
+
+# Convert to MP3
+ffmpeg -i video.mp4 -vn -q:a 0 audio.mp3
+```
+
+### Image Processing
+```bash
+# Convert format
+magick input.png output.jpg
+
+# Resize maintaining aspect ratio
+magick input.jpg -resize 800x600 output.jpg
+
+# Create square thumbnail
+magick input.jpg -resize 200x200^ -gravity center -extent 200x200 thumb.jpg
+```
+
+### Batch Image Resize
+```bash
+# Resize all JPEGs to 800px width
+mogrify -resize 800x -quality 85 *.jpg
+
+# Output to separate directory
+mogrify -path ./output -resize 800x600 *.jpg
+```
+
+### Video Thumbnail
+```bash
+# Extract frame at 5 seconds
+ffmpeg -ss 00:00:05 -i video.mp4 -vframes 1 -vf scale=320:-1 thumb.jpg
+```
+
+### HLS Streaming
+```bash
+# Generate HLS playlist
+ffmpeg -i input.mp4 \
+  -c:v libx264 -preset fast -crf 22 -g 48 \
+  -c:a aac -b:a 128k \
+  -f hls -hls_time 6 -hls_playlist_type vod \
+  playlist.m3u8
+```
+
+### Image Watermark
+```bash
+# Add watermark to corner
+magick input.jpg watermark.png -gravity southeast \
+  -geometry +10+10 -composite output.jpg
+```
+
+## Common Workflows
+
+### Optimize Video for Web
+```bash
+# H.264 with good compression
+ffmpeg -i input.mp4 \
+  -c:v libx264 -preset slow -crf 23 \
+  -c:a aac -b:a 128k \
+  -movflags +faststart \
+  output.mp4
+```
+
+### Create Responsive Images
+```bash
+# Generate multiple sizes
+for size in 320 640 1024 1920; do
+  magick input.jpg -resize ${size}x -quality 85 "output-${size}w.jpg"
+done
+```
+
+### Extract Video Segment
+```bash
+# From 1:30 to 3:00 (re-encode for precision)
+ffmpeg -i input.mp4 -ss 00:01:30 -to 00:03:00 \
+  -c:v libx264 -c:a aac output.mp4
+```
+
+### Batch Image Optimization
+```bash
+# Convert PNG to optimized JPEG
+mogrify -path ./optimized -format jpg -quality 85 -strip *.png
+```
+
+### Video GIF Creation
+```bash
+# High quality GIF with palette
+ffmpeg -i input.mp4 -vf "fps=15,scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" output.gif
+```
+
+### Image Blur Effect
+```bash
+# Gaussian blur
+magick input.jpg -gaussian-blur 0x8 output.jpg
+```
+
+## Advanced Techniques
+
+### Multi-Pass Video Encoding
+```bash
+# Pass 1 (analysis)
+ffmpeg -y -i input.mkv -c:v libx264 -b:v 2600k -pass 1 -an -f null /dev/null
+
+# Pass 2 (encoding)
+ffmpeg -i input.mkv -c:v libx264 -b:v 2600k -pass 2 -c:a aac output.mp4
+```
+
+### Hardware-Accelerated Encoding
+```bash
+# NVIDIA NVENC
+ffmpeg -hwaccel cuda -i input.mp4 -c:v h264_nvenc -preset fast -crf 22 output.mp4
+
+# Intel QuickSync
+ffmpeg -hwaccel qsv -c:v h264_qsv -i input.mp4 -c:v h264_qsv output.mp4
+```
+
+### Complex Image Pipeline
+```bash
+# Resize, crop, border, adjust
+magick input.jpg \
+  -resize 1000x1000^ \
+  -gravity center \
+  -crop 1000x1000+0+0 +repage \
+  -bordercolor black -border 5x5 \
+  -brightness-contrast 5x10 \
+  -quality 90 \
+  output.jpg
+```
+
+### Video Filter Chains
+```bash
+# Scale, denoise, watermark
+ffmpeg -i video.mp4 -i logo.png \
+  -filter_complex "[0:v]scale=1280:720,hqdn3d[v];[v][1:v]overlay=10:10" \
+  -c:a copy output.mp4
+```
+
+### Animated GIF from Images
+```bash
+# Create with delay
+magick -delay 100 -loop 0 frame*.png animated.gif
+
+# Optimize size
+magick animated.gif -fuzz 5% -layers Optimize optimized.gif
+```
+
+## Media Analysis
+
+### Inspect Video Properties
+```bash
+# Detailed JSON output
+ffprobe -v quiet -print_format json -show_format -show_streams input.mp4
+
+# Get resolution
+ffprobe -v error -select_streams v:0 \
+  -show_entries stream=width,height \
+  -of csv=s=x:p=0 input.mp4
+```
+
+### Image Information
+```bash
+# Basic info
+identify image.jpg
+
+# Detailed format
+identify -verbose image.jpg
+
+# Custom format
+identify -format "%f: %wx%h %b\n" image.jpg
+```
+
+## Performance Tips
+
+1. **Use CRF for quality control** - Better than bitrate for video
+2. **Copy streams when possible** - Avoid re-encoding with `-c copy`
+3. **Hardware acceleration** - GPU encoding 5-10x faster
+4. **Appropriate presets** - Balance speed vs compression
+5. **Batch with mogrify** - In-place image processing
+6. **Strip metadata** - Reduce file size with `-strip`
+7. **Progressive JPEG** - Better web loading with `-interlace Plane`
+8. **Limit memory** - Prevent crashes on large batches
+9. **Test on samples** - Verify settings before batch
+10. **Parallel processing** - Use GNU Parallel for multiple files
+
+## Reference Documentation
+
+Detailed guides in `references/`:
+
+- **ffmpeg-encoding.md** - Video/audio codecs, quality optimization, hardware acceleration
+- **ffmpeg-streaming.md** - HLS/DASH, live streaming, adaptive bitrate
+- **ffmpeg-filters.md** - Video/audio filters, complex filtergraphs
+- **imagemagick-editing.md** - Format conversion, effects, transformations
+- **imagemagick-batch.md** - Batch processing, mogrify, parallel operations
+- **format-compatibility.md** - Format support, codec recommendations
+
+## Common Parameters
+
+### FFmpeg Video
+- `-c:v` - Video codec (libx264, libx265, libvpx-vp9)
+- `-crf` - Quality (0-51, lower=better, 23=default)
+- `-preset` - Speed/compression (ultrafast to veryslow)
+- `-b:v` - Video bitrate (e.g., 2M, 2500k)
+- `-vf` - Video filters
+
+### FFmpeg Audio
+- `-c:a` - Audio codec (aac, mp3, opus)
+- `-b:a` - Audio bitrate (e.g., 128k, 192k)
+- `-ar` - Sample rate (44100, 48000)
+
+### ImageMagick Geometry
+- `800x600` - Fit within (maintains aspect)
+- `800x600!` - Force exact size
+- `800x600^` - Fill (may crop)
+- `800x` - Width only
+- `x600` - Height only
+- `50%` - Scale percentage
+
+## Troubleshooting
+
+**FFmpeg "Unknown encoder"**
+```bash
+# Check available encoders
+ffmpeg -encoders | grep h264
+
+# Install codec libraries
+sudo apt-get install libx264-dev libx265-dev
+```
+
+**ImageMagick "not authorized"**
+```bash
+# Edit policy file
+sudo nano /etc/ImageMagick-7/policy.xml
+# Change <policy domain="coder" rights="none" pattern="PDF" />
+# to <policy domain="coder" rights="read|write" pattern="PDF" />
+```
+
+**Memory errors**
+```bash
+# Limit memory usage
+ffmpeg -threads 4 input.mp4 output.mp4
+magick -limit memory 2GB -limit map 4GB input.jpg output.jpg
+```
+
+## Resources
+
+- FFmpeg: https://ffmpeg.org/documentation.html
+- FFmpeg Wiki: https://trac.ffmpeg.org/
+- ImageMagick: https://imagemagick.org/
+- ImageMagick Usage: https://imagemagick.org/Usage/