Folder Organization Assistant
Feature Description
Help users sort out messy folders, classify by ownership, unify naming, clean up redundancies, and make the directory structure clear at a glance.
- → Organize the current working directory
- → Organize the specified directory
Workflow
Step 1: Scan the Full Picture
- to view all files and folders in the root directory (including hidden files)
- Expand subdirectories one level to understand the content
- Record the total number of files, total number of directories, and number of scattered files
Focus Points:
- Files scattered in the root directory (not placed in any subdirectory)
- Directories with inconsistent naming styles (e.g., some with prefixes, some without)
- Hidden directories/files (determine if they are tool products or user files)
- Suspected duplicate files (compare with md5 for similar file names)
Step 2: Analyze Ownership
Classify all files and directories by owner. Common ownership dimensions:
- By Owner: Client's / Internal / Personal
- By Type: Documents / Code / Design / Data / Media
- By Status: Active / Archived / Deletable
Classification Principles:
- Prioritize classification by owner; place items of the same owner together
- Do not modify directory structures that are already systematic (e.g., subdirectories with clear organization)
- Temporary files/caches/logs generated by tools are classified as "cleanable"
Criteria for "Cleanable":
- Hidden directories containing only .DS_Store or log files
- Cache/temporary directories generated by tool operations (e.g., .playwright-mcp, node_modules, etc.)
- Intermediate products from evaluation/debugging that have no subsequent use value
- Older copies of duplicate files (only confirmed as duplicates after md5 comparison)
Step 3: Develop a Plan
Output the organization plan, including:
- Target Structure: Show the organized directory structure with a tree diagram
- Action List:
- Which directories to create
- Which files/directories to move where
- Which directories/files to rename
- Which can be deleted
- Unchanged Parts: Clearly state which parts remain unchanged and why
Plan Format:
Organized Structure:
Target Directory/
├── Category A/
│ ├── ...
├── Category B/
│ ├── ...
└── Retained/
Action List:
- [Create] Category A/
- [Move] xxx → Category A/xxx
- [Rename] yyy → zzz (Unify naming style)
- [Delete] .cache/ (Tool cache, no retention value)
- [Keep] Retained/ (Existing structure, no adjustment needed)
Step 4: Execute After Confirmation
Must wait for user confirmation before execution. Users may:
- Agree to all → Execute directly
- Adjust partially → Execute according to the adjusted plan
- Only clean up without classification → Only execute the deletion part
Execution Order:
- Create directories first
- Move files next (move independent files in parallel)
- Rename afterwards
- Delete last
- Run to verify results after execution
Step 5: Display Results
Output the organized directory tree, marking changes.
Core Principles
1. Classify by Ownership, Not by Format
"Client A's Proposal.pptx" should be placed under
instead of
. Ownership is more important than format.
2. Confirm Before Acting, Do Not Act Arbitrarily
The organization plan must be reviewed and confirmed by the user before execution. Especially for deletion operations, it's better to ask one more question.
3. Unify Naming Styles
Naming styles for directories at the same level must be consistent:
- Either all with prefixes or all without
- Either all in Chinese or all in English
- Unified date format
4. Do Not Modify Existing Structures
If a subdirectory is already well-organized internally, do not break it up and reorganize it. The goal of organization is to make the root directory clear, not to pursue perfect symmetry.
5. Verify Suspected Duplicates First
Similar file names do not mean identical content. Must confirm with md5 comparison before judging as duplicates.
6. Handle Hidden Files Carefully
Directories starting with
may be tool configurations (e.g., .claude, .git), do not move or delete them randomly. Only clean up those clearly identified as caches/logs.