plagiarism-checker-pre-screener（抄袭检查器预筛选器）

Plagiarism Checker Pre-Screener

Pre-screens text for potential plagiarism by detecting similarity patterns and providing paraphrasing suggestions for high-duplicate sections.

Technical Difficulty: High ⚠️

AI自主验收状态: 需人工检查 This skill uses advanced NLP techniques. Results should be manually reviewed before submission.

Features

1. Text Similarity Detection: Identifies potentially plagiarized or highly similar text segments
2. Originality Scoring: Provides overall originality percentage (0-100%)
3. Paraphrasing Suggestions: Offers AI-powered rewriting for flagged sections
4. Segment Analysis: Breaks text into sentences/paragraphs for granular checking

Usage

Basic Check

python scripts/main.py --input "Your text here" --threshold 0.75

File Analysis

python scripts/main.py --file document.txt --output report.json

With Paraphrasing

python scripts/main.py --input "text" --paraphrase --style academic

Parameters

Output Format

{
  "originality_score": 85.5,
  "total_segments": 12,
  "flagged_segments": 2,
  "segments": [
    {
      "index": 1,
      "text": "Original sentence text...",
      "similarity_score": 0.92,
      "flagged": true,
      "paraphrase_suggestion": "Rewritten version..."
    }
  ],
  "summary": "Text shows high originality with minor flagged sections"
}

Implementation Notes

• Uses TF-IDF + Cosine Similarity for local similarity detection
• Employs semantic embeddings for meaning-based comparison
• Paraphrasing uses transformer-based models
• No external API calls required; runs locally

References

• references/algorithm.md - Technical algorithm details
• references/paraphrasing_guide.md - Paraphrasing methodology

Limitations

1. Cannot access external databases (internet search required for comprehensive checking)
2. Local similarity only - won't catch plagiarism from external sources
3. Paraphrasing quality depends on input text complexity
4. Processing time increases with document length

Safety & Privacy

• All processing is local - no text sent to external APIs
• Suitable for sensitive/confidential documents
• No data retention after analysis completes

Risk Assessment

Security Checklist

• [ ] No hardcoded credentials or API keys
• [ ] No unauthorized file system access (../)
• [ ] Output does not expose sensitive information
• [ ] Prompt injection protections in place
• [ ] Input file paths validated (no ../ traversal)
• [ ] Output directory restricted to workspace
• [ ] Script execution in sandboxed environment
• [ ] Error messages sanitized (no stack traces exposed)
• [ ] Dependencies audited

Prerequisites

# Python dependencies
pip install -r requirements.txt

Evaluation Criteria

Success Metrics

• [ ] Successfully executes main functionality
• [ ] Output meets quality standards
• [ ] Handles edge cases gracefully
• [ ] Performance is acceptable

Test Cases

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status

• Current Stage: Draft
• Next Review Date: 2026-03-06
• Known Issues: None
• Planned Improvements:

- Performance optimization - Additional feature support