file-organization

ljchg12-hue's avatarfrom ljchg12-hue

Automated file and folder organization with categorization and duplicate detection

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 6, 2026
[Files and Documents]

When & Why to Use This Skill

This Claude skill automates file and folder organization through intelligent categorization, duplicate detection, and batch renaming. It streamlines digital workspaces by sorting files based on content, metadata, and custom rules, ensuring a clutter-free and efficient directory structure optimized for productivity and searchability.

Use Cases

  • Automated Directory Cleanup: Instantly organize cluttered folders like 'Downloads' or 'Desktop' into structured subdirectories based on file types, dates, or project names.
  • Storage Optimization via Duplicate Detection: Identify and remove redundant files using hash-based matching (MD5/SHA256) to reclaim disk space and prevent data fragmentation.
  • Standardized Batch Renaming: Apply consistent naming conventions across large sets of files using regex or date-based patterns to improve version control and professional documentation.
  • Project-Based Archiving: Automatically sort documents, media, and code into domain-specific templates (e.g., dev, design, docs) to maintain a clean and logical workflow for complex projects.
namefile-organization
descriptionAutomated file and folder organization with categorization and duplicate detection

File Organization Skill

Intelligent file organization based on content, metadata, and best practices.

When to Use

  • File/folder organization requests
  • Directory cleanup, duplicate detection
  • Batch renaming, categorization
  • Keywords: "organize files", "cleanup", "sort files"

Core Capabilities

1. Auto-Categorization

  • Content/type-based classification
  • Date-based (year/month/project)
  • Size-based sorting

2. Duplicate Detection

  • Hash-based (MD5, SHA256)
  • Similar file/image detection
  • Version detection (v1, v2, final)

3. Smart Folder Structures

  • Project-based organization
  • Domain templates (dev, design, docs, media)

4. Batch Renaming

  • Pattern-based (regex)
  • Sequential numbering
  • Date prefix, case normalization

Quick Reference

Commands

# Find by type
find /path -type f -name "*.pdf"

# Find large files (>100MB)
find /path -type f -size +100M

# Find duplicates
fdupes -r /path

# Batch rename
rename 's/\.txt$/.md/' *.txt

Recommended Structures

/Documents/{PDFs,Word,Excel}
/Media/{Images,Videos,Audio}
/Code/{Projects,Scripts}
/Archives/{Compressed,Backups}

Naming Convention

YYYYMMDD_description_version.ext
2025-01-15_project-report_v2.pdf

Workflow

  1. Analysis: Scan, count types, detect duplicates
  2. Planning: Define structure, create rules
  3. Execution: Create dirs, move files, rename (dry-run first)
  4. Maintenance: Automate, document, monitor

Best Practices

  • ✅ Backup before bulk operations
  • ✅ Use dry-run mode first
  • ✅ Keep folder depth ≤4 levels
  • ❌ Don't organize system folders
  • ❌ Don't delete duplicates without verification

Integration

  • digital-forensics: Evidence preservation
  • metadata-extraction: File metadata analysis