agentsclimarketplace

CleanMyMacSkill

Skill peizhou/cleanMyMacSkill

macOS / Windows / Linux read-only storage analysis helper. Scans disk usage, finds large files/directories, divides items into 🟢Safe to Clean / 🟡Needs Review / 🔴Caution, provides execution commands, and builds a gorgeous, interactive HTML report inspired by CleanMyMac. Includes a local server mode for web-based one-click cleanup (move to trash/delete). Triggers on user queries about: "storage analysis", "disk full", "C drive full", "low disk space", "clean disk", "free up space", "what is taking up space", "show storage details", "caches", "cache cleanup". Contact & Support: [email protected].From its SKILL.md

Install
npx -y skills add peizhou/cleanMyMacSkill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 599 tokens by cl100k_base, as published. Nobody here has run it

cleanMyMacSkill

Read-only storage analyzer for macOS, Windows, and Linux. Produces an interactive, Apple-style web-based dashboard with safe one-click cleanup integrations.

Core Directives

  • Read-Only Scanner. The scanning phase only uses safe operations (e.g., df, du, stat, ls). Direct modifications or deletions are strictly prohibited during scanning.
  • Interactive Deletions. In server mode, users can click "Move to Trash" or "Hard Delete" on the web page. The backend validates paths against strict session tokens and home boundaries.
  • Accurate Estimates. Explicitly mark any reclaimable space values as estimates.
  • Retain Command Snippets. Keep absolute paths and terminal command snippets exactly as they are (do not translate paths).

Execution Pipeline

Step 1: Run Storage Scan

Execute the multi-threaded scan script to collect filesystem size metadata:

python3 scripts/scan.py > /tmp/storage_scan.json

The script detects the OS automatically and concurrently queries cache targets, user folders, and developer structures using standard ThreadPoolExecutor. Denied folders are marked as denied.

Step 2: Interpret & Segment

Read /tmp/storage_scan.json. Load references at references/macos.md, references/windows.md, or references/linux.md depending on the OS platform. Perform the following checks:

  1. Identify Top 5 Space Consumers: Mark their types (User files, databases, developer caches, VM files, etc.).
  2. Track App Sandbox Folders: Correlate UUID folders in containers back to their parent bundle-id names.
  3. Partition into Clean Tiers:
    • 🟢 Safe to Clean: Caches, logs, package registers. Offer one-click trashing or direct deletions.
    • 🟡 Needs Review: Personal documents, downloads, active database container folders. Enable opening in the file manager or trashing verified safe subfolders.
    • 🔴 Caution: Software application packages. Guide users to uninstall manually via official settings.

Step 3: Compile and Serve Report

Inject the interpreted classification JSON into the template. Use the server script for interactive dashboard functionality:

python3 scripts/server.py /tmp/storage_analysis.json

Alternatively, compile a static HTML file:

python3 scripts/build_report.py /tmp/storage_analysis.json ~/Desktop/cleanmymac-report.html

Step 4: Dialogue Summary

Once generated, output a concise summary in the chat:

  • Total space scanned and free space remaining.
  • Estimated reclaimable capacity.
  • Top 2-3 cleanup priorities and potential risks.

Platform Prerequisites

  • Runs on Python 3 Standard Library (no pip dependencies).
  • Compatible with macOS, Linux (Freedesktop compliant trashing), and Windows.

What ships with it: 11 files

89.4 KB alongside SKILL.md, 3 of them executable

assets/

references/

scripts/

Keep looking

Skills are one crate of 326,696. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.