File Organizer logo

File Organizer

Community
smithjoshua
file-organizer

Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files". Creates numbered PARA folders, renames poorly-named files, and maintains rollback logs. Works via bash commands in Claude Code terminal.

Overview

Publishersmithjoshua
Repositoryclaude-code-cowork-skills-file-organizer
Skill namefile-organizer
Stars
58
Forks
6
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by smithjoshua on GitHub. Read the source before you install it.

Installation

Install the File Organizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/smithjoshua/claude-code-cowork-skills-file-organizer/tree/master/claude-code-skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/smithjoshua/claude-code-cowork-skills-file-organizer.git /tmp/claude-code-cowork-skills-file-organizer
mkdir -p .claude/skills
cp -r /tmp/claude-code-cowork-skills-file-organizer/claude-code-skill .claude/skills/file-organizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable File Organizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads File Organizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so File Organizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

File Organizer (Claude Code - PARA Method)

Organizes files using the PARA methodology with bash commands. Intelligent categorization and audit trails.

What is PARA?

#CategoryContainsLifespan
0InboxNew files awaiting processingTemporary
1ProjectsActive work with deadlinesShort-term
2AreasOngoing responsibilitiesLong-term
3ResourcesReference materials by topicEvergreen
4ArchiveInactive/completed itemsPreserved

Workflow

Phase 1: Discovery     → ls, find, file commands to scan and assess
Phase 2: Analysis      → Read file contents for poor names (use Read tool for PDFs)
Phase 3: Triage        → Create categorization table, flag sensitive/scam files
Phase 4: Preparation   → mkdir -p to create PARA structure, get approval
Phase 5: Execution     → mv commands with logging
Phase 6: Cleanup       → Remove empty folders, delete temp files
Phase 7: Completion    → Generate summary, verify PARA folder roots are clean

0-Review Staging Workflow

For large batches of poorly-named files, use a staging folder:

bash
# Create staging folder for files needing content analysis
mkdir -p ~/Downloads/0-Review

# Move cryptic/poorly-named files to review
mv ~/Downloads/U0BPA6*.pdf ~/Downloads/0-Review/
mv ~/Downloads/[0-9][0-9][0-9][0-9][0-9].pdf ~/Downloads/0-Review/

# Analyze each file, then move to proper PARA location
# Remove staging folder when empty
rmdir ~/Downloads/0-Review

Quick Start

bash
# 1. Create PARA folder structure
mkdir -p ~/Downloads/{0-Inbox/_REVIEW,1-Projects/{Work,Personal},2-Areas/{Finance,Health,Legal,Career},3-Resources/{Media/{Images,Videos,Audio,Screenshots},Tools/{Installers,Utilities},Learning/{Articles,Books,Courses}},4-Archive/{Completed-Projects,Past-Years},_ORG}

# 2. Scan target directory
find ~/Downloads -maxdepth 1 -type f | wc -l
ls -la ~/Downloads | head -50

# 3. Move files (log each operation)
mv "~/Downloads/file.pdf" "~/Downloads/2-Areas/Finance/"

PARA Folder Structure

bash
# One-liner to create full PARA structure
mkdir -p ~/Downloads/{0-Inbox/_REVIEW,1-Projects/{Work,Personal},2-Areas/{Finance,Health,Legal,Career,Home},3-Resources/{Media/{Images,Videos,Audio,Screenshots},Tools/{Installers,Utilities},Learning/{Articles,Books,Courses},Templates},4-Archive/{Completed-Projects,Past-Areas,Old-Resources},_ORG}

Visual structure:

Target-Directory/
├── 0-Inbox/                    # New files land here first
│   └── _REVIEW/
├── 1-Projects/                 # Active work with deadlines
│   ├── Work/
│   └── Personal/
├── 2-Areas/                    # Ongoing responsibilities
│   ├── Finance/
│   ├── Health/
│   ├── Legal/
│   └── Career/
├── 3-Resources/                # Reference materials
│   ├── Media/
│   ├── Tools/
│   └── Learning/
├── 4-Archive/                  # Inactive items
│   └── Completed-Projects/
└── _ORG/                       # Tracking files

Inbox Review Workflow

Daily Review (5 min)

bash
# List inbox contents
ls -la ~/Downloads/0-Inbox/

# For each file, determine PARA destination:
# Actionable with deadline? → 1-Projects
# Ongoing responsibility?   → 2-Areas
# Reference material?       → 3-Resources
# Completed/inactive?       → 4-Archive

Weekly Review (15 min)

bash
# 1. Check for remaining inbox items
ls ~/Downloads/0-Inbox/

# 2. Find completed projects (no recent modifications)
find ~/Downloads/1-Projects -maxdepth 2 -type d -mtime +30

# 3. Archive completed projects
mv ~/Downloads/1-Projects/old-project ~/Downloads/4-Archive/Completed-Projects/

File Naming Convention

Format: [DATE]_[CODE]_[description].[ext]

bash
# Examples
mv "Document.pdf" "2025-01_FIN_tax-statement.pdf"
mv "IMG_1234.jpg" "2025-01_REF_vacation-photo.jpg"
mv "Screenshot 2025-01-13.png" "2025-01-13_PROJ_meeting-notes.png"

PARA Category Codes

CodeCategoryDestination
PROJProjects1-Projects/
FINFinance2-Areas/Finance/
HEALTHHealth2-Areas/Health/
LEGALLegal2-Areas/Legal/
REFReference3-Resources/
LEARNLearning3-Resources/Learning/

Content Analysis (Bash)

For poorly-named files, extract content to determine proper naming:

bash
# PDFs - extract text
pdftotext "Document.pdf" - | head -50

# If pdftotext unavailable, try:
strings "Document.pdf" | head -100

# Images - check EXIF data
file "IMG_1234.jpg"
exiftool "IMG_1234.jpg" 2>/dev/null | grep -E "Date|Title|Description"

# Office docs - unzip and read
unzip -p "document.docx" word/document.xml | head -100

Files to Analyze

Trigger content analysis for:

bash
# Generic names
ls ~/Downloads | grep -iE "^(document|untitled|copy of|new )"

# Camera defaults
ls ~/Downloads | grep -iE "^(IMG_|DSC_|DCIM|scan[0-9])"

# Screenshots
ls ~/Downloads | grep -iE "^(screenshot|screen shot|capture)"

# Numbered duplicates
ls ~/Downloads | grep -E "\([0-9]+\)\."

# Random alphanumeric strings (auto-generated filenames)
ls ~/Downloads | grep -iE "^[A-Z0-9]{16,}\.[a-z]+$"

# Numeric-only filenames (e.g., 65440.pdf)
ls ~/Downloads | grep -E "^[0-9]+\.[a-z]+$"

# Scan prefixes with timestamps
ls ~/Downloads | grep -iE "^scan_.*[0-9]{4}-[0-9]{2}-[0-9]{2}"

# Gmail exports
ls ~/Downloads | grep -iE "^Gmail.*\.pdf$"

Auto-Categorization by Type

bash
# Move images to Resources/Media
find ~/Downloads/0-Inbox -maxdepth 1 \( -name "*.jpg" -o -name "*.png" -o -name "*.gif" \) -exec mv {} ~/Downloads/3-Resources/Media/Images/ \;

# Move installers to Resources/Tools
find ~/Downloads/0-Inbox -maxdepth 1 \( -name "*.dmg" -o -name "*.exe" -o -name "*.pkg" \) -exec mv {} ~/Downloads/3-Resources/Tools/Installers/ \;

# Move PDFs with financial keywords to Areas/Finance
for f in ~/Downloads/0-Inbox/*.pdf; do
  if pdftotext "$f" - 2>/dev/null | grep -qiE "invoice|receipt|statement|tax"; then
    mv "$f" ~/Downloads/2-Areas/Finance/
  fi
done

Logging Template

Create _ORG/_LOG.md:

bash
cat > ~/Downloads/_ORG/_LOG.md << 'EOF'
# Organization Log (PARA Method)
**Started**: $(date '+%Y-%m-%d %H:%M')

## Operations
| Time | Action | File | From | To (PARA) |
|------|--------|------|------|-----------|
EOF

# Log each move
echo "| $(date '+%H:%M') | MOVE | file.pdf | 0-Inbox | 2-Areas/Finance/ |" >> ~/Downloads/_ORG/_LOG.md

Safety Rules

  1. Never delete - only move to 0-Inbox/_REVIEW if uncertain
  2. Log everything - append to _LOG.md before each mv
  3. Approval checkpoints - pause and confirm before bulk moves
  4. Preserve dates - use mv (not cp+rm) to keep timestamps
  5. Sensitive files - flag anything in 2-Areas/{Finance,Health,Legal}

Security & Scam Detection

Flag and quarantine potential scam/phishing files:

bash
# Common scam patterns in PDFs (fake invoices, tech support scams)
# Keywords to search: "Norton", "McAfee", "Microsoft Support",
# "Your account", "Payment required", "Call immediately"

# Check PDF content for scam indicators
for f in ~/Downloads/*.pdf; do
  if pdftotext "$f" - 2>/dev/null | grep -qiE "norton|mcafee|geek squad|call.*1-[0-9]{3}"; then
    echo "⚠️  POTENTIAL SCAM: $f"
    mv "$f" ~/Downloads/0-Inbox/_REVIEW/
  fi
done

Scam indicators:

  • Random alphanumeric filename (e.g., U0BPA6IUWL6FUQRUHYCZ.pdf)
  • Fake invoice from security software companies
  • "Call this number" with toll-free numbers
  • Urgent payment demands

Action: Move to _REVIEW folder, flag for user, recommend DELETE

Sensitive Document Handling

Flag and secure sensitive documents:

bash
# Tax documents (W-2, 1099, tax returns)
ls ~/Downloads | grep -iE "(w-2|w2|1099|tax.*(return|form))"

# Documents with SSN patterns
grep -l "[0-9]\{3\}-[0-9]\{2\}-[0-9]\{4\}" ~/Downloads/*.pdf 2>/dev/null

# Financial statements
ls ~/Downloads | grep -iE "(statement|account.*summary|routing.*number)"

Sensitive file types:

TypeFlagDestination
W-2, 1099, Tax forms⚠️ SENSITIVE2-Areas/Finance/Tax/
Contracts with signatures⚠️ LEGAL2-Areas/Legal/
Medical records⚠️ HEALTH2-Areas/Health/
Password/credential files⚠️ SECUREEncrypted storage

Action: Flag in categorization table, confirm with user before moving

Duplicate Detection

bash
# Find duplicates by name pattern
ls ~/Downloads/0-Inbox | grep -E "\([0-9]+\)\." | while read f; do
  original="${f/ ([0-9])/}"
  echo "Duplicate: $f -> Original: $original"
done

# Find duplicates by content (md5)
find ~/Downloads -maxdepth 1 -type f -exec md5sum {} \; | sort | uniq -d -w32

Large File Handling

bash
# Find files > 100MB
find ~/Downloads -maxdepth 1 -type f -size +100M -exec ls -lh {} \;

# Large media files typically go to Resources
find ~/Downloads/0-Inbox -maxdepth 1 -size +100M \( -name "*.mp4" -o -name "*.mov" \) -exec mv {} ~/Downloads/3-Resources/Media/Videos/ \;

Session Resume

If interrupted, check last operation:

bash
tail -5 ~/Downloads/_ORG/_LOG.md

Temp File Cleanup

Remove common junk files before organizing:

bash
# Office temp files (~$...)
find ~/Downloads -name "~\$*" -delete

# macOS metadata
find ~/Downloads -name ".DS_Store" -delete
find ~/Downloads -name "._*" -delete

# Empty files
find ~/Downloads -maxdepth 1 -type f -empty -delete

PARA Root-Level Audit

After initial organization, check for loose files at PARA folder roots:

bash
# Files should be in subfolders, not at PARA root level
echo "=== 2-Areas root files (should be in subfolders) ==="
find ~/Downloads/2-Areas -maxdepth 1 -type f ! -name ".DS_Store"

echo "=== 3-Resources root files ==="
find ~/Downloads/3-Resources -maxdepth 1 -type f ! -name ".DS_Store"

echo "=== 4-Archive root files ==="
find ~/Downloads/4-Archive -maxdepth 1 -type f ! -name ".DS_Store"

Empty Folder Cleanup

After processing, remove empty staging folders:

bash
# Remove empty review/staging folders
rmdir ~/Downloads/0-Review 2>/dev/null
rmdir ~/Downloads/0-Inbox/_REVIEW 2>/dev/null

# Find and remove empty subdirectories
find ~/Downloads -type d -empty -delete

Categorization Table Format

Present recommendations in a clear table before executing:

markdown
### 🚫 DELETE (scam/junk)
| File | Reason |
|------|--------|
| `U0BPA6...pdf` | SCAM - Fake Norton invoice |

### ⚠️ SENSITIVE → 2-Areas/Finance
| File | Content |
|------|---------|
| `65440.pdf` | W-2 Tax Form 2024 |

### 📁 4-Archive
| File | Suggested Rename |
|------|------------------|
| `old-project.pdf` | `2023-01_PROJ_project-name.pdf` |

### 📚 3-Resources
| File | Destination |
|------|-------------|
| `manual.pdf` | 3-Resources/Tools/ |

Emoji flags:

  • 🚫 DELETE - Scam, junk, or duplicate
  • ⚠️ SENSITIVE - Tax, legal, medical, credentials
  • 📁 ARCHIVE - Old/completed items
  • 📚 RESOURCES - Reference materials
  • 📂 AREAS - Ongoing responsibilities
  • 📝 PROJECTS - Active work

Reference Files

  • references/config.md: Customize PARA structure and detection keywords
  • references/templates.md: Tracking file templates

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the File Organizer AI skill do?

Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files". Creates numbered PARA folders, renames poorly-named files, and maintains rollback logs. Works via bash commands in Claude Code terminal.

Why use File Organizer on TypingMind?

Because you install it once and use it with any model. File Organizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install File Organizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/smithjoshua/claude-code-cowork-skills-file-organizer/tree/master/claude-code-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use File Organizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with File Organizer?

As many as you like. As long as a model supports skills, you can use File Organizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the File Organizer AI skill free?

Yes. It is published on GitHub by smithjoshua under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇