A comprehensive tool for evaluating code submissions in hackathons, coding competitions, and educational assessments.

• Multi-language Support: Evaluates code in Python, JavaScript/TypeScript, Java, C/C++, Go, Rust, and more
• Comprehensive Analysis:
  • Code quality and structure
  • Documentation completeness
  • Functionality implementation
  • Innovation and creativity
• Configurable Scoring: Customizable weights and thresholds
• Detailed Reports: JSON output with actionable feedback
• CLI Interface: Easy to integrate into automated workflows

1. Basic Evaluation:

   python main.py /path/to/submission

2. With Custom Config:

   python main.py /path/to/submission --config config.json

3. Save Results:

   python main.py /path/to/submission --output results.json --verbose

• File structure and organization
• Code complexity and readability
• Naming conventions
• Comments and inline documentation
• Error handling

• README completeness
• Setup/installation instructions
• Additional documentation files
• Inline code documentation

• Code executability
• Test coverage
• Configuration management
• Dependency management

• Creative problem-solving approaches
• Additional features beyond requirements
• Use of advanced technologies/patterns

• Excellent: 90-100%
• Good: 75-89%
• Satisfactory: 60-74%
• Needs Improvement: Below 60%

Customize evaluation criteria in config.json:

{
  "weights": {
    "code_quality": 0.3,
    "documentation": 0.25,
    "functionality": 0.3,
    "innovation": 0.15
  },
  "thresholds": {
    "excellent": 90,
    "good": 75,
    "satisfactory": 60,
    "needs_improvement": 40
  }
}

usage: main.py [-h] [--config CONFIG] [--output OUTPUT] 
               [--problem-statement PROBLEM_STATEMENT] [--verbose]
               submission_path

positional arguments:
  submission_path       Path to the submission directory to evaluate

options:
  -h, --help            show this help message and exit
  --config CONFIG, -c CONFIG
                        Path to configuration file (JSON format)
  --output OUTPUT, -o OUTPUT
                        Output file for evaluation results (JSON format)
  --problem-statement PROBLEM_STATEMENT, -p PROBLEM_STATEMENT
                        Path to problem statement or PRD file
  --verbose, -v         Enable verbose output

============================================================
AI JURY EVALUATION REPORT
============================================================
Submission: /path/to/submission
Timestamp: 2024-01-15T10:30:45.123456

OVERALL SCORE: 78.5/100.0 (78.5%)

DETAILED SCORES:
  Code Quality:    82.0/100
  Documentation:   75.0/100
  Functionality:   80.0/100
  Innovation:      70.0/100

- name: Evaluate Submission
  run: |
    python ai-jury/main.py ./submission --output evaluation.json

#!/bin/bash
for submission in submissions/*/; do
    python main.py "$submission" --output "results/$(basename $submission).json"
done

• Python: .py
• JavaScript/TypeScript: .js, .ts
• Java: .java
• C/C++: .c, .cpp
• Go: .go
• Rust: .rs
• Ruby: .rb
• PHP: .php
• C#: .cs
• Kotlin: .kt
• Swift: .swift

• 0: Excellent submission (≥70%)
• 1: Good submission (50-69%)
• 2: Needs improvement (<50%)
• 3: Evaluation error

MIT License - see LICENSE file for details.

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

For issues and feature requests, please open an issue on the project repository.