SA

safe-project-organizer

Analyzes and refactors project structures with dry-run previews and safety checks.

Install

mkdir -p .claude/skills/safe-project-organizer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7487" && unzip -o skill.zip -d .claude/skills/safe-project-organizer && rm skill.zip

Installs to .claude/skills/safe-project-organizer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Safely analyze and reorganize project structure with multi-stage validation, dry-run previews, and explicit user confirmation. Use when projects need cleanup, standardization, or better organization.
199 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Maps file structure for read-only analysis
  • Simulates file moves and deletions via dry-run
  • Generates impact reports on file system state
  • Executes atomic file system modifications

How it works

Runs a multi-stage validation pipeline that snapshots the file system before generating and simulating transformation scripts.

Inputs & outputs

You give it
Desired organizational change request
You get back
Validated list of pending file path changes and safety impact metrics

When to use safe-project-organizer

  • Clean up a messy root directory
  • Move source code into a src folder
  • Remove empty or unused directories safely

About this skill

Safe Project Organizer

Overview

This skill enables Claude Code to analyze project structure and suggest safe organizational improvements like moving files, removing unused directories, and restructuring folders. It prioritizes safety through multi-stage validation, dry-run previews, and explicit user confirmation.

Core Safety Principles

1. Read-Only Analysis Phase

  • All analysis operations are read-only
  • No modifications occur during scanning
  • Complete project snapshot before any changes

2. Dry-Run Validation

  • All operations preview changes before execution
  • Show exact file paths being affected
  • Calculate impact metrics (files moved, deleted, created)

3. Explicit User Confirmation

  • Require confirmation for each operation category
  • Display detailed change summary
  • Allow selective approval of suggestions

4. Atomic Operations with Rollback

  • Each operation is reversible
  • Create backup references before modifications
  • Maintain operation log for audit trail

5. Protected File Patterns

Never modify files matching these patterns:

  • .git/, .svn/, .hg/ (version control)
  • node_modules/, vendor/, venv/, .venv/ (dependencies)
  • .env*, secrets.*, credentials.* (sensitive data)
  • package-lock.json, yarn.lock, pnpm-lock.yaml (lock files)
  • dist/, build/, .next/, .nuxt/ (build artifacts)

When to Use This Skill

Use this skill when you encounter any of these scenarios:

Project Cleanup:

  • "My project root is messy with too many files"
  • "I have empty directories that should be cleaned up"
  • "Documentation files are scattered everywhere"

Standardization:

  • "This project doesn't follow standard directory structure"
  • "Source files are mixed with config files in root"
  • "I need to organize files by type for better maintainability"

Migration Preparation:

  • "I'm about to hand off this project and need to clean it up"
  • "This codebase needs better organization before adding new features"
  • "I want to standardize the project structure"

Safety Concerns:

  • "I'm nervous about accidentally breaking something"
  • "I need to see exactly what will change before making changes"
  • "I want a safe way to reorganize without losing data"

Safe Usage Workflow

Step 1: Initial Scan (Read-Only)

Execute the project organizer script with --scan flag:

python3 scripts/project_organizer.py /path/to/project --scan

What it does:

  • Scans entire project structure
  • Identifies file types, counts, sizes
  • Detects empty directories
  • Lists protected files
  • No modifications made

Example Output:

🔍 Scanning project: /path/to/project
📋 This is a READ-ONLY scan. No changes will be made.

✅ Scan complete!
   📁 Directories: 24
   📄 Files: 156
   🔒 Protected items: 42
   📂 Empty directories: 3

Step 2: Generate Suggestions (Still Read-Only)

Use --analyze flag to generate organizational suggestions:

python3 scripts/project_organizer.py /path/to/project --analyze

What it does:

  • Performs full analysis
  • Generates organizational suggestions
  • Displays suggestion count
  • Still no modifications

Step 3: Preview Changes (Detailed Review)

Use --preview flag to see exactly what will change:

python3 scripts/project_organizer.py /path/to/project --preview

What it does:

  • Shows detailed preview of ALL suggestions
  • Groups by action type (move, delete, create)
  • Displays risk levels (🟢 low, 🟡 medium, 🔴 high)
  • Shows safety checks for each operation
  • Lists exact file paths affected
  • Zero modifications

Example Preview Output:

📋 PREVIEW MODE - No changes will be made
============================================================

📊 Total Suggestions: 8

🎯 By Action:
   MOVE: 5
   DELETE: 2
   CREATE_DIR: 1

⚠️  By Risk Level:
   🟢 LOW: 6
   🟡 MEDIUM: 2

📝 Detailed Suggestions:

MOVE Operations (5):
1. 🟢 Documentation/config files organized in docs/ directory
   FROM: CONTRIBUTING.md
   TO:   docs/CONTRIBUTING.md
   Safety Checks:
      ✓ File is not a primary config
      ✓ No imports reference this file path
      ✓ Not in protected patterns

DELETE Operations (2):
1. 🟢 Empty directory with no files or subdirectories
   PATH: old_backup/temp
   Safety Checks:
      ✓ Directory is empty
      ✓ Not a protected path
      ✓ No version control markers

Step 4: Dry Run (Simulation Only)

Use --execute flag for dry-run simulation:

python3 scripts/project_organizer.py /path/to/project --execute

What it does:

  • Simulates ALL operations
  • Shows what WOULD happen
  • Validates all safety checks
  • Reports success/failure/skipped
  • No actual changes made

Step 5: Real Execution (Requires Confirmation)

Use --execute-real flag only after thorough review:

python3 scripts/project_organizer.py /path/to/project --execute-real

What it does:

  • Prompts for explicit confirmation
  • Executes approved changes
  • Creates audit log (.project_organizer.log)
  • Shows real-time progress
  • Actually modifies project

Confirmation Prompt:

⚠️  WARNING: This will make REAL changes. Type 'yes' to confirm: yes

Operation Types and Safety

Move Operations

Low Risk (🟢):

  • Moving documentation files to docs/
  • Moving config files to config/
  • Moving scripts to scripts/

Medium Risk (🟡):

  • Grouping source files by type
  • Creating organizational directories

Safety Checks Performed:

  • Source file exists and is accessible
  • Source is not in protected patterns
  • Destination doesn't already exist
  • Parent directories can be created safely

Delete Operations

Low Risk (🟢):

  • Removing truly empty directories
  • Deleting temporary files

Safety Checks Performed:

  • Target exists
  • Directory is completely empty
  • Not a protected path
  • No version control markers

Create Directory Operations

Low Risk (🟢):

  • Creating standard directories (src/, docs/, tests/)
  • Creating organizational structure

Safety Checks Performed:

  • Target doesn't already exist
  • No naming conflicts
  • Standard directory pattern
  • Parent directories can be created

Protected File Patterns

The skill automatically protects these paths from modification:

Version Control

  • .git/, .git/**
  • .svn/, .svn/**
  • .hg/, .hg/**

Dependencies

  • node_modules/, node_modules/**
  • vendor/, vendor/**
  • venv/, venv/**
  • .venv/, .venv/**

Build Artifacts

  • dist/, dist/**
  • build/, build/**
  • .next/, .next/**
  • .nuxt/, .nuxt/**
  • out/, out/**

Sensitive Data

  • .env*
  • secrets.*
  • credentials.*

Lock Files

  • package-lock.json
  • yarn.lock
  • pnpm-lock.yaml
  • Gemfile.lock
  • Pipfile.lock
  • poetry.lock

Cache Files

  • __pycache__/, __pycache__/**

Best Practices

Before Running the Skill

  1. Commit Changes: Ensure all current work is committed to version control
  2. Backup Important Files: Have a recent backup or git stash available
  3. Review Project: Understand what files and directories are important
  4. Test Access: Verify you have necessary permissions

During Execution

  1. Always Start with Scan: Begin with --scan to understand the project
  2. Review Suggestions Carefully: Look through all generated suggestions
  3. Use Preview Mode: Always use --preview before any execution
  4. Test with Dry Run: Use --execute to simulate changes safely

After Execution

  1. Verify Project Works: Test that your project still builds/runs correctly
  2. Review Operation Log: Check .project_organizer.log for what was changed
  3. Commit Separately: Commit organizational changes separately from functional changes
  4. Update Documentation: Update any documentation that references old file paths

Safety Checklist

Before using --execute-real, verify:

  • Project is committed to version control
  • All suggestions reviewed in preview mode
  • Dry run completed successfully
  • No critical files are being moved
  • Build/test processes still work
  • Team members notified if shared project

Error Handling and Troubleshooting

Common Issues

Permission Denied:

  • Ensure you have write permissions
  • Check file ownership
  • May need appropriate privileges

Path Protected:

  • Review protected patterns
  • Confirm the path should be modified
  • Adjust patterns if needed

Changes Not Appearing:

  • Verify you used --execute-real (not just --execute)
  • Check the operation log
  • Confirm "yes" was entered at confirmation prompt

Recovery Options

Git Recovery:

git status                    # See what changed
git checkout -- .            # Restore all changes
git reset --hard HEAD        # Full reset to last commit

Operation Log Review:

cat .project_organizer.log    # Review detailed operation log

Customization

Adding Custom Protected Patterns

Edit the PROTECTED_PATTERNS list in the script:

PROTECTED_PATTERNS = [
    # Existing patterns...
    'my_important_dir/**',    # Custom protection
    '*.critical',             # Protect critical files
]

Custom Organization Rules

Edit MOVABLE_ROOT_FILES dictionary:

MOVABLE_ROOT_FILES = {
    'assets': ['*.png', '*.jpg', '*.svg'],  # Move images to assets/
    'data': ['*.csv', '*.json', '*.xml'],   # Move data files
}

Custom Safety Validators

Extend the SafeProjectOrganizer class:

def _custom_safety_check(self, path: Path) -> bool:
    """Your custom safety logic"""
    # Return True if safe, False if should be protected
    return True

Integration with Claude Code

As a Skill Tool

This skill integrates naturally with Claude Code's workflow:

  1. User Request: "Organize my project structure"
  2. Skill Activation: Safe Project Organizer loads
  3. Sequential Execution: Follows the 5-step workflow automatically
  4. **User Confirma

Content truncated.

When not to use it

  • Complex refactoring of application logic
  • Managing files within dependency directories like node_modules

Limitations

  • Protected patterns strictly block core dependencies
  • Requires explicit manual confirmation for each operation

How it compares

Ensures structural safety through explicit dry-run previews and system snapshots before touching actual files.

Compared to similar skills

safe-project-organizer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
safe-project-organizer (this skill)47moReviewBeginner
resolve-conflicts818moReviewIntermediate
claude-automation-recommender472moReviewBeginner
codex-skill125moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by ananddtyagi

View all by ananddtyagi

math-tools

ananddtyagi

Deterministic mathematical computation using SymPy. Use for ANY math operation requiring exact/verified results - basic arithmetic, algebra (simplify, expand, factor, solve equations), calculus (derivatives, integrals, limits, series), linear algebra (matrices, determinants, eigenvalues), trigonometry, number theory (primes, GCD/LCM, factorization), and statistics. Ensures mathematical accuracy by using symbolic computation rather than LLM estimation.

26134

chief-architect

ananddtyagi

PERSONAL APP ARCHITECT - Strategic development orchestrator for personal productivity applications. Analyzes project context, makes architectural decisions for single-developer projects, delegates to specialized skills, and ensures alignment between user experience goals and technical implementation. Optimized for personal apps targeting 10-100 users.

617

plugin-creator

ananddtyagi

Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills.

538

data-safety-auditor

ananddtyagi

Comprehensive data safety auditor for Vue 3 + Pinia + IndexedDB + PouchDB applications. Detects data loss risks, sync issues, race conditions, and browser-specific vulnerabilities with actionable remediation guidance.

38

document-sync

ananddtyagi

A robust skill that analyzes your app's actual codebase, tech stack, configuration, and architecture to ensure ALL documentation is current and accurate. It never assumes—always verifies and compares the live system with every documentation file to detect code-doc drift and generate actionable updates.

217

api-contract-sync-manager

ananddtyagi

Validate OpenAPI, Swagger, and GraphQL schemas match backend implementation. Detect breaking changes, generate TypeScript clients, and ensure API documentation stays synchronized. Use when working with API spec files (.yaml, .json, .graphql), reviewing API changes, generating frontend types, or validating endpoint implementations.

18

You might also like

resolve-conflicts

antinomyhq

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.

81334

claude-automation-recommender

anthropics

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

47140

codex-skill

feiskyer

Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.

12110

git-advanced-workflows

wshobson

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

1197

subagent-driven-development

davila7

Use when executing implementation plans with independent tasks in the current session

1493

validate-openapi-specs

epieczko

Validates and registers hook manifest files (YAML) in the Hook Registry for versioned hook management.

594

Search skills

Search the agent skills registry