Folder Organizer: Read-First File Cleanup

    1

    Your agent reads each file before it sorts, dedupes by content, and never hard-deletes anything.

    Free

    2 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Folder Organizer: Read-First File Cleanup

    Example session with this skill installed

    My Downloads folder is a disaster — tons of duplicates and files like report.xlsx / report-v2.xlsx / report-final.xlsx. Can you clean it up safely? Don't delete anything without asking me.

    • Read your context and instructions
    • Compiled the folder organizer
    • Generated the document

    Summary

    Profiled ~/Downloads (1,204 files · 8.3 GB), found

    1.2 GB of exact duplicates by content hash, and spotted 3 files whose names don't match what's inside. Nothing has been moved yet — here's what I propose.

    1 · Profile

    Files1,204 (23 hidden)
    Size8.3 GB
    Biggest subtreescreen-recordings/ — 4.1 GB
    Date span2023-04-11 → 2025-08-22

    2 · Duplicates (by content, not name)

    A · Exact duplicates — safe to stage (reclaims 1.2 GB)

    KeepStageSize
    screen-recordings/demo-v3-FINAL.movdemo-v3-FINAL 2.mov612 MB
    design-exports/hero.pnghero (1).png4.2 MB
    … 12 more

    B · Version residue — your call, I won't delete these

    • reports/ · report.xlsx · report-v2.xlsx · report-final.xlsx (different contents)

    3 · What files actually are

    FileName suggestsContent says
    invoice.htmlan invoicetitle: Sign in · h1: Welcome back → a login page
    Q3-copy.xlsxa backupsheets Raw · Pivot · Summary — same as Q3-numbers.xlsx
    scan_0012.pdfa scan⚠️ a passport page — recommend moving to a private folder

    Next steps

    Approve the 14 exact duplicates above → I'll move them to Downloads/_待删_20261006/ (a staging folder — nothing is hard-deleted; you empty it yourself).
    2. Pick an organizing axis: by project · by date · by file type?
    3. I'll then show a file-by-file mapping (old versions grouped into an old-versions subfolder, latest copy kept on top) before moving anything.

    hero.png

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Messy folders are hard to clean up because filenames lie. A file named final is often a draft, an invoice.html can be a login page, and three copies of report_v2.xlsx may contain three different things. Tools that sort by name put files in the wrong place and can delete the wrong one. Folder Organizer has your agent open each file first and work out what it is before deciding where it goes.

    The skill runs in five phases. It profiles the folder (size hotspots, file types, biggest files, date span) and finds duplicates by content hash, not by name. It separates true byte-for-byte duplicates from version chains like draft → v2 → final. Then it pulls a content signature from every file: HTML titles, Office sheet and slide names, a PDF's first page, photo EXIF data, audio and video duration. If a file can't be read, it falls back to basic metadata instead of failing.

    There's no built-in set of categories. The skill asks how you want things grouped (by project, client, date, type or topic), then proposes a structure and a file-by-file mapping for you to approve. Renaming is optional and works the same way. You lock the naming rules first, review an old → new table, and only then is anything renamed. The new names say what's actually inside each file.

    It's built to be safe. Nothing is ever hard-deleted. Removals are moved to a dated staging folder that you empty yourself, and every destructive step pauses for your approval with the exact list of files. It never decides which version is "final" for you, and it flags sensitive files (IDs, contracts, bank details) that are sitting loose in a work folder.

    It works on Desktop, Downloads, project drives, photo and asset libraries, and mixed folders. The bundled scripts use only the Python standard library, run on macOS, Linux and Windows, and handle filenames with spaces or CJK characters. Three tools are optional and add deeper reading: pdftotext, exiftool and ffprobe.

    Not for code repository refactoring or file format conversion. Requires local Python environment. Deletions are moved to a staging folder rather than erased.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike basic tools that look at filenames, this agent opens and reads every file to understand its true content, ensuring an "invoice.html" that is actually a login page doesn't end up in your tax folder. It identifies duplicates by content hash rather than name and flags sensitive documents like IDs or contracts for special handling.

    The skill works on Windows, macOS, and Linux, and is compatible with any AI agent capable of executing Python scripts. It is designed to handle complex file systems, including those with CJK characters or spaces in filenames.

    The agent never performs "hard deletes"; instead, it moves duplicates or unwanted files to a dated staging folder for you to review and empty manually. Furthermore, it generates a full mapping table of every proposed move or rename, requiring your explicit approval before a single file is touched.

    You receive the core Python-based automation scripts, the agentic reasoning prompts for content classification, and a setup guide. While it works out of the box using the Python standard library, it also includes instructions for integrating optional tools like `exiftool` or `pdftotext` for deeper file analysis.

    No, the agent is flexible. It analyzes your folder and asks how you prefer to group items—such as by project, client, or topic—then proposes a custom structure based on your specific workflow for you to approve or adjust.

    New in Workflow Automation