Cleaning Dev Caches logo

Cleaning Dev Caches

Organization
etherfunlab
cleaning-dev-caches

Use when this Mac's disk is nearly full, or the user asks to clear re-downloadable caches (「清缓存」「硬盘满了」, "clear caches") — Homebrew, npm / pnpm / yarn / bun / uv / pip, Gradle, Playwright browsers, Edge and VS Code updater caches, simulator dyld caches, unused Rust toolchains. Not for build output (cleaning-dev-build-artifacts) or personal files.

Overview

Publisheretherfunlab
Repositoryworkflow
Skill namecleaning-dev-caches
Stars
75
Forks
17
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Cleaning Dev Caches 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/etherfunlab/workflow/tree/main/skills/macos-disk-cleanup/agent/skills/cleaning-dev-caches
  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/etherfunlab/workflow.git /tmp/workflow
mkdir -p .claude/skills
cp -r /tmp/workflow/skills/macos-disk-cleanup/agent/skills/cleaning-dev-caches .claude/skills/cleaning-dev-caches
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cleaning Dev Caches 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 Cleaning Dev Caches 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 Cleaning Dev Caches 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.

Clear caches

Everything in the table below is downloaded or rebuilt again the next time it is needed. Before deleting, confirm one thing only: the program that owns it is not using it right now.

Before starting, record free space with df -h /System/Volumes/Data, and record each item's size with du -sh before deleting it. Skip any row whose command does not exist.

CacheExtra preconditionCommand
Homebrew downloads and old versionsnonebrew cleanup -s --prune=all
npmnonenpm cache clean --force
npx packagespgrep -f _npx is empty (MCP servers started by npx run from here)rm -rf ~/.npm/_npx; npm cache clean does not touch this directory
pnpm storenonepnpm store prune
bunrun it in a directory with a package.json, otherwise it deletes nothing(cd <any JS repo> && bun pm cache rm)
yarn / uv / pipnoneyarn cache clean / uv cache clean / pip3 cache purge
Gradlepgrep -f GradleDaemon is emptyrm -rf ~/.gradle/caches
Playwright browsersno e2e run in progressrm -rf ~/Library/Caches/ms-playwright ~/Library/Caches/ms-playwright-go; tell the user to run npx playwright install before the next e2e run
Microsoft Edgepgrep -x "Microsoft Edge" is emptyrm -rf ~/Library/Caches/Microsoft\ Edge
VS Code update leftoversVS Code is closedrm -rf ~/Library/Caches/com.microsoft.VSCode.ShipIt
Simulator dyld cachestale ones only, see belowxcrun simctl runtime dyld_shared_cache remove <runtime>
Unused Rust toolchainspgrep -x cargo and pgrep -x rustc are empty; keep list belowrustup toolchain uninstall <name>

Simulator dyld cache: /Library/Developer/CoreSimulator/Caches/dyld/<host build>/<runtime>/. A cache is stale only when its host build differs from sw_vers -buildVersion or its runtime is no longer in xcrun simctl runtime list. Deleting the current one reclaims nothing: the next simulator launch rebuilds it as it was.

Rust toolchains: keep stable, the default (rustup default), every directory override (rustup override list), custom toolchains linked with rustup toolchain link (they are not re-downloadable), *-sbpf-solana-* (installed by Solana's build tools), and every channel pinned in a rust-toolchain or rust-toolchain.toml anywhere under {{DEV_ROOT}}. The rest of ~/.rustup/toolchains can be uninstalled.

When a precondition fails (Edge is open, say), skip that row and tell the user at the end how to clear it later. When a permission check or classifier blocks an rm -rf, do not route around it; hand the command to the user to run themselves (in Claude Code: ! <command>).

Keep, do not touch

  • ~/.claude/projects: Claude Code's session transcripts; usage tools such as ccusage read them.
  • The conda installation itself (for example /opt/homebrew/Caskroom/miniconda): projects run their environments from it.
  • Installed iOS simulator runtimes: projects run their tests on them.
  • No need for conda clean -a: packages are hard-linked into the environments, so it reclaims almost nothing.

Wrap up

Run df -h /System/Volumes/Data again and report what each item reclaimed, which items were skipped and why, and free space before and after.

Frequently asked questions

What does the Cleaning Dev Caches AI skill do?

Use when this Mac's disk is nearly full, or the user asks to clear re-downloadable caches (「清缓存」「硬盘满了」, "clear caches") — Homebrew, npm / pnpm / yarn / bun / uv / pip, Gradle, Playwright browsers, Edge and VS Code updater caches, simulator dyld caches, unused Rust toolchains. Not for build output (cleaning-dev-build-artifacts) or personal files.

Why use Cleaning Dev Caches on TypingMind?

Because you install it once and use it with any model. Cleaning Dev Caches 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 Cleaning Dev Caches in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/etherfunlab/workflow/tree/main/skills/macos-disk-cleanup/agent/skills/cleaning-dev-caches. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cleaning Dev Caches?

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 Cleaning Dev Caches?

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

Is the Cleaning Dev Caches AI skill free?

Yes. It is published on GitHub by etherfunlab 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 👇