Sample Skill

---
name: Sample Skill
description: Use as a reference implementation for basic text processing: word counting, character analysis, transformations, batch processing with dual JSON and human-readable output formats.
category: Engineering
version: 1.0.0
tools: []
---

# Sample Text Processor

Reference implementation for text processing with dual output formats (JSON and human-readable).

## Features

**Core Functionality**
- Word count analysis (total, unique, frequency)
- Character statistics (character count, line count, special characters)
- Text transformations (uppercase, lowercase, title case)
- File processing (single files or batch directories)
- Dual output formats (JSON and human-readable)

**Technical Features**
- Command-line interface with argument parsing
- Error handling for file and processing issues
- Progress reporting for batch operations
- Configurable output formatting and verbosity
- Cross-platform compatibility (standard library only)

## Usage

Text analysis:
- Analyze document with statistics output
- Save results to JSON or text

Text transformation:
- Transform text to uppercase, lowercase, or title case
- Save to output file

Batch processing:
- Process directories of text files
- Generate results in JSON or human-readable format

## Output Examples

Text analysis produces:
- File name and path
- Total word count, unique word count
- Character count, line count
- Most frequent word with occurrence count

JSON output structure:
```json
{
  "file": "filename",
  "statistics": {
    "total_words": 150,
    "unique_words": 85,
    "total_characters": 750,
    "lines": 12,
    "most_frequent": {"word": "the", "count": 8}
  }
}
```

## Architecture

Modular design with components:
- **TextProcessor Class**: Core processing and statistics calculation
- **OutputFormatter Class**: Dual format generation (JSON and text)
- **FileManager Class**: File I/O and batch processing
- **CLI Interface**: Argument parsing and user interaction

## Configuration Options

- `--format`: Output format (json, text)
- `--verbose`: Enable verbose output and progress
- `--output`: Specify output file or directory
- `--encoding`: Text file encoding (default: utf-8)

## Error Handling

Comprehensive error handling for:
- File not found or permission errors
- Invalid encoding or corrupted text
- Memory limitations for large files
- Output write permissions
- Invalid arguments

## Performance Considerations

- Efficient memory usage through streaming
- Optimized word counting with dictionary lookups
- Batch processing with progress reporting
- Configurable encoding detection

## Best Practices

1. Follow PEP 8 coding standards
2. Include comprehensive docstrings
3. Add test cases with sample data
4. Update documentation for new features
5. Ensure backward compatibility

## Tier Level

This is a BASIC tier skill demonstrating essential structure and quality standards. Advanced features (sentiment analysis, complex file formats, database integration, parallel processing) are intentionally omitted to keep focus on core functionality.