@trieungoctam/vibekit 1.0.0

package/skills/ai/ai-multimodal/scripts/check_setup.py

@@ -0,0 +1,315 @@
+#!/usr/bin/env python3
+"""
+Validate ai-multimodal skill setup and configuration.
+
+Checks:
+- API key presence and format
+- Python dependencies
+- Centralized resolver availability
+- Directory structure
+"""
+
+import os
+import sys
+from pathlib import Path
+
+# Fix Windows cp1252 encoding: Unicode symbols (✓, ⚠, ✗) can't encode on Windows.
+# Reconfigure stdout to UTF-8 with replacement (Python 3.7+).
+if sys.stdout.encoding and sys.stdout.encoding.lower() != "utf-8":
+    if hasattr(sys.stdout, 'reconfigure'):
+        sys.stdout.reconfigure(encoding="utf-8", errors="replace")
+    if hasattr(sys.stderr, 'reconfigure'):
+        sys.stderr.reconfigure(encoding="utf-8", errors="replace")
+
+# Color codes for terminal output
+GREEN = '\033[92m'
+YELLOW = '\033[93m'
+RED = '\033[91m'
+BLUE = '\033[94m'
+RESET = '\033[0m'
+BOLD = '\033[1m'
+
+
+def print_header(text):
+    """Print section header."""
+    print(f"\n{BOLD}{BLUE}{'='*60}{RESET}")
+    print(f"{BOLD}{BLUE}{text}{RESET}")
+    print(f"{BOLD}{BLUE}{'='*60}{RESET}\n")
+
+
+def print_success(text):
+    """Print success message."""
+    print(f"{GREEN}✓ {text}{RESET}")
+
+
+def print_warning(text):
+    """Print warning message."""
+    print(f"{YELLOW}⚠ {text}{RESET}")
+
+
+def print_error(text):
+    """Print error message."""
+    print(f"{RED}✗ {text}{RESET}")
+
+
+def print_info(text):
+    """Print info message."""
+    print(f"{BLUE}ℹ {text}{RESET}")
+
+
+def check_dependencies():
+    """Check if required Python packages are installed."""
+    print_header("Checking Python Dependencies")
+
+    dependencies = {
+        'google.genai': 'google-genai',
+        'dotenv': 'python-dotenv',
+        'PIL': 'pillow'
+    }
+
+    missing = []
+
+    for module_name, package_name in dependencies.items():
+        try:
+            __import__(module_name)
+            print_success(f"{package_name} is installed")
+        except ImportError:
+            print_error(f"{package_name} is NOT installed")
+            missing.append(package_name)
+
+    if missing:
+        print_error("\nMissing dependencies detected!")
+        print_info(f"Install with: pip install {' '.join(missing)}")
+        return False
+
+    return True
+
+
+def check_centralized_resolver():
+    """Check if centralized resolver is available."""
+    print_header("Checking Centralized Resolver")
+
+    claude_root = Path(__file__).parent.parent.parent.parent
+    resolver_path = claude_root / 'scripts' / 'resolve_env.py'
+
+    if resolver_path.exists():
+        print_success(f"Centralized resolver found: {resolver_path}")
+
+        # Try to import it
+        sys.path.insert(0, str(resolver_path.parent))
+        try:
+            from resolve_env import resolve_env
+            print_success("Centralized resolver can be imported")
+            return True
+        except ImportError as e:
+            print_error(f"Centralized resolver exists but cannot be imported: {e}")
+            return False
+    else:
+        print_warning(f"Centralized resolver not found: {resolver_path}")
+        print_info("Skill will use fallback resolution logic")
+        return True  # Not critical, fallback works
+
+
+def find_api_key():
+    """Find and validate API key using centralized resolver."""
+    print_header("Checking API Key Configuration")
+
+    # Try to use centralized resolver
+    claude_root = Path(__file__).parent.parent.parent.parent
+    sys.path.insert(0, str(claude_root / 'scripts'))
+    try:
+        from resolve_env import resolve_env
+
+        print_info("Using centralized resolver...")
+        api_key = resolve_env('GEMINI_API_KEY', skill='ai-multimodal')
+
+        if api_key:
+            print_success("API key found via centralized resolver")
+            print_info(f"Key preview: {api_key[:20]}...{api_key[-4:]}")
+
+            # Show hierarchy
+            print_info("\nTo see where the key was found, run:")
+            print_info("python ~/.claude/scripts/resolve_env.py GEMINI_API_KEY --skill ai-multimodal --verbose")
+
+            return api_key
+        else:
+            print_error("API key not found in any location")
+            return None
+
+    except ImportError:
+        print_warning("Centralized resolver not available, using fallback")
+
+        # Fallback: check environment
+        api_key = os.getenv('GEMINI_API_KEY')
+        if api_key:
+            print_success("API key found in process.env")
+            print_info(f"Key preview: {api_key[:20]}...{api_key[-4:]}")
+            return api_key
+        else:
+            print_error("API key not found")
+            return None
+
+
+def validate_api_key_format(api_key):
+    """Basic validation of API key format."""
+    if not api_key:
+        return False
+
+    # Google AI Studio keys typically start with 'AIza'
+    if api_key.startswith('AIza'):
+        print_success("API key format looks valid (Google AI Studio)")
+        return True
+    elif len(api_key) > 20:
+        print_warning("API key format not recognized (may be Vertex AI or custom)")
+        return True
+    else:
+        print_error("API key format looks invalid (too short)")
+        return False
+
+
+def test_api_connection(api_key):
+    """Test API connection with a simple request."""
+    print_header("Testing API Connection")
+
+    try:
+        from google import genai
+
+        print_info("Initializing Gemini client...")
+        client = genai.Client(api_key=api_key)
+
+        print_info("Fetching available models...")
+        # List models to verify API key works
+        models = list(client.models.list())
+
+        print_success(f"API connection successful! Found {len(models)} available models")
+
+        # Show some available models
+        print_info("\nSample available models:")
+        for model in models[:5]:
+            print(f"  - {model.name}")
+
+        return True
+
+    except ImportError:
+        print_error("google-genai package not installed")
+        return False
+    except Exception as e:
+        print_error(f"API connection failed: {str(e)}")
+        return False
+
+
+def check_directory_structure():
+    """Verify skill directory structure."""
+    print_header("Checking Directory Structure")
+
+    script_dir = Path(__file__).parent
+    skill_dir = script_dir.parent
+
+    required_files = [
+        ('SKILL.md', skill_dir / 'SKILL.md'),
+        ('.env.example', skill_dir / '.env.example'),
+        ('gemini_batch_process.py', script_dir / 'gemini_batch_process.py'),
+    ]
+
+    all_exist = True
+
+    for name, path in required_files:
+        if path.exists():
+            print_success(f"{name} exists")
+        else:
+            print_error(f"{name} NOT found at {path}")
+            all_exist = False
+
+    return all_exist
+
+
+def provide_setup_instructions():
+    """Provide setup instructions if configuration is incomplete."""
+    print_header("Setup Instructions")
+
+    print_info("To configure the ai-multimodal skill:")
+    print("\n1. Get a Gemini API key:")
+    print("   → Visit: https://aistudio.google.com/apikey")
+
+    print("\n2. Configure the API key (choose one method):")
+
+    print(f"\n   Option A: User global config (recommended)")
+    print(f"   $ echo 'GEMINI_API_KEY=your-api-key-here' >> ~/.claude/.env")
+
+    script_dir = Path(__file__).parent
+    skill_dir = script_dir.parent
+
+    print(f"\n   Option B: Skill-specific config")
+    print(f"   $ cd {skill_dir}")
+    print(f"   $ cp .env.example .env")
+    print(f"   $ # Edit .env and add your API key")
+
+    print(f"\n   Option C: Runtime environment (temporary)")
+    print(f"   $ export GEMINI_API_KEY='your-api-key-here'")
+
+    print("\n3. Verify setup:")
+    print(f"   $ python {Path(__file__)}")
+
+    print("\n4. Debug if needed:")
+    print(f"   $ python ~/.claude/scripts/resolve_env.py --show-hierarchy --skill ai-multimodal")
+    print(f"   $ python ~/.claude/scripts/resolve_env.py GEMINI_API_KEY --skill ai-multimodal --verbose")
+
+
+def main():
+    """Run all setup checks."""
+    print(f"\n{BOLD}AI Multimodal Skill - Setup Checker{RESET}")
+
+    all_passed = True
+
+    # Check directory structure
+    if not check_directory_structure():
+        all_passed = False
+
+    # Check centralized resolver
+    check_centralized_resolver()
+
+    # Check dependencies
+    if not check_dependencies():
+        all_passed = False
+        provide_setup_instructions()
+        sys.exit(1)
+
+    # Check API key
+    api_key = find_api_key()
+
+    if not api_key:
+        print_error("\n❌ GEMINI_API_KEY not found in any location")
+        all_passed = False
+        provide_setup_instructions()
+        sys.exit(1)
+
+    # Validate API key format
+    if not validate_api_key_format(api_key):
+        all_passed = False
+
+    # Test API connection
+    if not test_api_connection(api_key):
+        all_passed = False
+
+    # Final summary
+    print_header("Setup Summary")
+
+    if all_passed:
+        print_success("✅ All checks passed! The ai-multimodal skill is ready to use.")
+        print_info("\nNext steps:")
+        print("  • Read SKILL.md for usage examples")
+        print("  • Try: python scripts/gemini_batch_process.py --help")
+        print("\nImage generation models:")
+        print("  • gemini-2.5-flash-image    - Nano Banana Flash (DEFAULT - fast)")
+        print("  • imagen-4.0-generate-001   - Imagen 4 (alternative - production)")
+        print("  • gemini-3-pro-image-preview - Nano Banana Pro (4K text, reasoning)")
+        print("\nExample (uses default model):")
+        print("  python scripts/gemini_batch_process.py --task generate \\")
+        print("    --prompt 'A sunset over mountains' --aspect-ratio 16:9 --size 2K")
+    else:
+        print_error("❌ Some checks failed. Please fix the issues above.")
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

package/skills/ai/ai-multimodal/scripts/document_converter.py

@@ -0,0 +1,395 @@
+#!/usr/bin/env python3
+"""
+Convert documents to Markdown using Gemini API.
+
+Supports all document types:
+- PDF documents (native vision processing)
+- Images (JPEG, PNG, WEBP, HEIC)
+- Office documents (DOCX, XLSX, PPTX)
+- HTML, TXT, and other text formats
+
+Features:
+- Converts to clean markdown format
+- Preserves structure, tables, and formatting
+- Extracts text from images and scanned documents
+- Batch conversion support
+- Saves to docs/assets/document-extraction.md by default
+"""
+
+import argparse
+import os
+import sys
+import time
+from pathlib import Path
+from typing import Optional, List, Dict, Any
+
+try:
+    from google import genai
+    from google.genai import types
+except ImportError:
+    print("Error: google-genai package not installed")
+    print("Install with: pip install google-genai")
+    sys.exit(1)
+
+try:
+    from dotenv import load_dotenv
+except ImportError:
+    load_dotenv = None
+
+
+def find_api_key() -> Optional[str]:
+    """Find Gemini API key using correct priority order.
+
+    Priority order (highest to lowest):
+    1. process.env (runtime environment variables)
+    2. .claude/skills/ai-multimodal/.env (skill-specific config)
+    3. .claude/skills/.env (shared skills config)
+    4. .claude/.env (Claude global config)
+    """
+    # Priority 1: Already in process.env (highest)
+    api_key = os.getenv('GEMINI_API_KEY')
+    if api_key:
+        return api_key
+
+    # Load .env files if dotenv available
+    if load_dotenv:
+        # Determine base paths
+        script_dir = Path(__file__).parent
+        skill_dir = script_dir.parent  # .claude/skills/ai-multimodal
+        skills_dir = skill_dir.parent   # .claude/skills
+        claude_dir = skills_dir.parent  # .claude
+
+        # Priority 2: Skill-specific .env
+        env_file = skill_dir / '.env'
+        if env_file.exists():
+            load_dotenv(env_file)
+            api_key = os.getenv('GEMINI_API_KEY')
+            if api_key:
+                return api_key
+
+        # Priority 3: Shared skills .env
+        env_file = skills_dir / '.env'
+        if env_file.exists():
+            load_dotenv(env_file)
+            api_key = os.getenv('GEMINI_API_KEY')
+            if api_key:
+                return api_key
+
+        # Priority 4: Claude global .env
+        env_file = claude_dir / '.env'
+        if env_file.exists():
+            load_dotenv(env_file)
+            api_key = os.getenv('GEMINI_API_KEY')
+            if api_key:
+                return api_key
+
+    return None
+
+
+def find_project_root() -> Path:
+    """Find project root directory."""
+    script_dir = Path(__file__).parent
+
+    # Look for .git or .claude directory
+    for parent in [script_dir] + list(script_dir.parents):
+        if (parent / '.git').exists() or (parent / '.claude').exists():
+            return parent
+
+    return script_dir
+
+
+def get_mime_type(file_path: str) -> str:
+    """Determine MIME type from file extension."""
+    ext = Path(file_path).suffix.lower()
+
+    mime_types = {
+        # Documents
+        '.pdf': 'application/pdf',
+        '.txt': 'text/plain',
+        '.html': 'text/html',
+        '.htm': 'text/html',
+        '.md': 'text/markdown',
+        '.csv': 'text/csv',
+        # Images
+        '.jpg': 'image/jpeg',
+        '.jpeg': 'image/jpeg',
+        '.png': 'image/png',
+        '.webp': 'image/webp',
+        '.heic': 'image/heic',
+        '.heif': 'image/heif',
+        # Office (need to be uploaded as binary)
+        '.docx': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+        '.xlsx': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
+        '.pptx': 'application/vnd.openxmlformats-officedocument.presentationml.presentation',
+    }
+
+    return mime_types.get(ext, 'application/octet-stream')
+
+
+def upload_file(client: genai.Client, file_path: str, verbose: bool = False) -> Any:
+    """Upload file to Gemini File API."""
+    if verbose:
+        print(f"Uploading {file_path}...")
+
+    myfile = client.files.upload(file=file_path)
+
+    # Wait for processing if needed
+    max_wait = 300  # 5 minutes
+    elapsed = 0
+    while myfile.state.name == 'PROCESSING' and elapsed < max_wait:
+        time.sleep(2)
+        myfile = client.files.get(name=myfile.name)
+        elapsed += 2
+        if verbose and elapsed % 10 == 0:
+            print(f"  Processing... {elapsed}s")
+
+    if myfile.state.name == 'FAILED':
+        raise ValueError(f"File processing failed: {file_path}")
+
+    if myfile.state.name == 'PROCESSING':
+        raise TimeoutError(f"Processing timeout after {max_wait}s: {file_path}")
+
+    if verbose:
+        print(f"  Uploaded: {myfile.name}")
+
+    return myfile
+
+
+def convert_to_markdown(
+    client: genai.Client,
+    file_path: str,
+    model: str = 'gemini-2.5-flash',
+    custom_prompt: Optional[str] = None,
+    verbose: bool = False,
+    max_retries: int = 3
+) -> Dict[str, Any]:
+    """Convert a document to markdown using Gemini."""
+
+    for attempt in range(max_retries):
+        try:
+            file_path_obj = Path(file_path)
+            file_size = file_path_obj.stat().st_size
+            use_file_api = file_size > 20 * 1024 * 1024  # >20MB
+
+            # Default prompt for markdown conversion
+            if custom_prompt:
+                prompt = custom_prompt
+            else:
+                prompt = """Convert this document to clean, well-formatted Markdown.
+
+Requirements:
+- Preserve all content, structure, and formatting
+- Convert tables to markdown table format
+- Maintain heading hierarchy (# ## ### etc)
+- Preserve lists, code blocks, and quotes
+- Extract text from images if present
+- Keep formatting consistent and readable
+
+Output only the markdown content without any preamble or explanation."""
+
+            # Upload or inline the file
+            if use_file_api:
+                myfile = upload_file(client, str(file_path), verbose)
+                content = [prompt, myfile]
+            else:
+                with open(file_path, 'rb') as f:
+                    file_bytes = f.read()
+
+                mime_type = get_mime_type(str(file_path))
+                content = [
+                    prompt,
+                    types.Part.from_bytes(data=file_bytes, mime_type=mime_type)
+                ]
+
+            # Generate markdown
+            response = client.models.generate_content(
+                model=model,
+                contents=content
+            )
+
+            markdown_content = response.text if hasattr(response, 'text') else ''
+
+            return {
+                'file': str(file_path),
+                'status': 'success',
+                'markdown': markdown_content
+            }
+
+        except Exception as e:
+            if attempt == max_retries - 1:
+                return {
+                    'file': str(file_path),
+                    'status': 'error',
+                    'error': str(e),
+                    'markdown': None
+                }
+
+            wait_time = 2 ** attempt
+            if verbose:
+                print(f"  Retry {attempt + 1} after {wait_time}s: {e}")
+            time.sleep(wait_time)
+
+
+def batch_convert(
+    files: List[str],
+    output_file: Optional[str] = None,
+    auto_name: bool = False,
+    model: str = 'gemini-2.5-flash',
+    custom_prompt: Optional[str] = None,
+    verbose: bool = False
+) -> List[Dict[str, Any]]:
+    """Batch convert multiple files to markdown."""
+
+    api_key = find_api_key()
+    if not api_key:
+        print("Error: GEMINI_API_KEY not found")
+        print("Set via: export GEMINI_API_KEY='your-key'")
+        print("Or create .env file with: GEMINI_API_KEY=your-key")
+        sys.exit(1)
+
+    client = genai.Client(api_key=api_key)
+    results = []
+
+    # Determine output path
+    if not output_file:
+        project_root = find_project_root()
+        output_dir = project_root / 'docs' / 'assets'
+
+        if auto_name and len(files) == 1:
+            # Auto-generate meaningful filename from input
+            input_path = Path(files[0])
+            base_name = input_path.stem
+            output_file = str(output_dir / f"{base_name}-extraction.md")
+        else:
+            output_file = str(output_dir / 'document-extraction.md')
+
+    output_path = Path(output_file)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    # Process each file
+    for i, file_path in enumerate(files, 1):
+        if verbose:
+            print(f"\n[{i}/{len(files)}] Converting: {file_path}")
+
+        result = convert_to_markdown(
+            client=client,
+            file_path=file_path,
+            model=model,
+            custom_prompt=custom_prompt,
+            verbose=verbose
+        )
+
+        results.append(result)
+
+        if verbose:
+            status = result.get('status', 'unknown')
+            print(f"  Status: {status}")
+
+    # Save combined markdown
+    with open(output_path, 'w', encoding='utf-8') as f:
+        f.write("# Document Extraction Results\n\n")
+        f.write(f"Converted {len(files)} document(s) to markdown.\n\n")
+        f.write("---\n\n")
+
+        for result in results:
+            f.write(f"## {Path(result['file']).name}\n\n")
+
+            if result['status'] == 'success' and result.get('markdown'):
+                f.write(result['markdown'])
+                f.write("\n\n")
+            elif result['status'] == 'success':
+                f.write("**Note**: Conversion succeeded but no content was returned.\n\n")
+            else:
+                f.write(f"**Error**: {result.get('error', 'Unknown error')}\n\n")
+
+            f.write("---\n\n")
+
+    if verbose or True:  # Always show output location
+        print(f"\n{'='*50}")
+        print(f"Converted: {len(results)} file(s)")
+        print(f"Success: {sum(1 for r in results if r['status'] == 'success')}")
+        print(f"Failed: {sum(1 for r in results if r['status'] == 'error')}")
+        print(f"Output saved to: {output_path}")
+
+    return results
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Convert documents to Markdown using Gemini API',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Convert single PDF to markdown (default name)
+  %(prog)s --input document.pdf
+
+  # Auto-generate meaningful filename
+  %(prog)s --input testpdf.pdf --auto-name
+  # Output: docs/assets/testpdf-extraction.md
+
+  # Convert multiple files
+  %(prog)s --input doc1.pdf doc2.docx image.png
+
+  # Specify custom output location
+  %(prog)s --input document.pdf --output ./output.md
+
+  # Use custom prompt
+  %(prog)s --input document.pdf --prompt "Extract only the tables as markdown"
+
+  # Batch convert directory
+  %(prog)s --input ./documents/*.pdf --verbose
+
+Supported formats:
+  - PDF documents (up to 1,000 pages)
+  - Images (JPEG, PNG, WEBP, HEIC)
+  - Office documents (DOCX, XLSX, PPTX)
+  - Text formats (TXT, HTML, Markdown, CSV)
+
+Default output: <project-root>/docs/assets/document-extraction.md
+        """
+    )
+
+    parser.add_argument('--input', '-i', nargs='+', required=True,
+                       help='Input file(s) to convert')
+    parser.add_argument('--output', '-o',
+                       help='Output markdown file (default: docs/assets/document-extraction.md)')
+    parser.add_argument('--auto-name', '-a', action='store_true',
+                       help='Auto-generate meaningful output filename from input (e.g., document.pdf -> document-extraction.md)')
+    parser.add_argument('--model', default='gemini-2.5-flash',
+                       help='Gemini model to use (default: gemini-2.5-flash)')
+    parser.add_argument('--prompt', '-p',
+                       help='Custom prompt for conversion')
+    parser.add_argument('--verbose', '-v', action='store_true',
+                       help='Verbose output')
+
+    args = parser.parse_args()
+
+    # Validate input files
+    files = []
+    for file_pattern in args.input:
+        file_path = Path(file_pattern)
+        if file_path.exists() and file_path.is_file():
+            files.append(str(file_path))
+        else:
+            # Try glob pattern
+            import glob
+            matched = glob.glob(file_pattern)
+            files.extend([f for f in matched if Path(f).is_file()])
+
+    if not files:
+        print("Error: No valid input files found")
+        sys.exit(1)
+
+    # Convert files
+    batch_convert(
+        files=files,
+        output_file=args.output,
+        auto_name=args.auto_name,
+        model=args.model,
+        custom_prompt=args.prompt,
+        verbose=args.verbose
+    )
+
+
+if __name__ == '__main__':
+    main()