Cleaning Dev Build Artifacts logo

Cleaning Dev Build Artifacts

Organization
etherfunlab
cleaning-dev-build-artifacts

Use when this Mac's disk is nearly full, or the user asks to clean build output — Rust target/ dirs or Claude Code worktrees (.claude/worktrees) under {{DEV_ROOT}} (「清编译产物」「清 target」「清 worktree」「硬盘满了」, "clean build artifacts"). Not for package-manager or app caches (cleaning-dev-caches) or personal files.

Overview

Publisheretherfunlab
Repositoryworkflow
Skill namecleaning-dev-build-artifacts
Stars
75
Forks
17
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Cleaning Dev Build Artifacts 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-build-artifacts
  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-build-artifacts .claude/skills/cleaning-dev-build-artifacts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cleaning Dev Build Artifacts 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 Build Artifacts 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 Build Artifacts 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.

Clean build output

Most of the space you can reclaim in one piece under {{DEV_ROOT}} sits in two places: Rust target/ dirs, and the worktrees Claude Code opens (each Rust worktree carries a full target/ of its own, each web worktree its own node_modules). Both can be rebuilt; the only cost is a slower next build.

1. Scan (read-only)

bash
bash <this skill's directory>/scan.sh {{DEV_ROOT}}

Output: one line per worktree, REMOVE or KEEP(<reason>), with the path of its main repository; one line per target/ with its size and the cargo of the toolchain pinned in that repository or a parent directory, marked BUSY when cargo or rustc is running inside it. When lsof lists no process at all, the scan exits with an error instead of guessing.

2. Worktrees: remove only those marked REMOVE

The scan says REMOVE when git status succeeds and shows no uncommitted changes, untracked files included whatever status.showUntrackedFiles says (untracked dirs whose CACHEDIR.TAG carries the Cache Directory Tagging signature are tool caches and do not count), no process has its cwd inside it, and one of these holds:

  • On a branch: the branch's PR is MERGED, and the worktree HEAD equals the PR's head commit (no local commits after the merge).
  • Detached HEAD: HEAD is on some remote branch.
bash
git -C <main> worktree remove --force <worktree path>
git -C <main> worktree prune

--force is there only to take the gitignored target/ and node_modules along; uncommitted changes were already ruled out. Leave everything marked KEEP and list the reasons for the user.

When a permission check or classifier blocks a deletion, do not retry it in another form. Finish the other items first, then hand the full command to the user to run themselves (in Claude Code: ! <command>).

3. target/: cargo clean with the pinned toolchain

bash
<cargo path from the scan> clean --manifest-path <repo>/Cargo.toml
  • Call ~/.rustup/toolchains/<channel>-<arch>/bin/cargo directly; do not depend on a cargo on PATH.
  • Not rm -rf target: classifiers block it, and do not route around them with another way of deleting.
  • Skip anything marked BUSY and tell the user to clean it after the build finishes.

4. Wrap up

Run df -h /System/Volumes/Data again and report free space before and after, plus what each item reclaimed.

Out of scope

  • node_modules and .next in main repositories: in daily use.
  • Package-manager, browser and updater caches, unused Rust toolchains: use cleaning-dev-caches.
  • Cloud-sync folders, Downloads, Desktop, chat histories, photo / TV / music libraries: personal data. List them, never delete.

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 Cleaning Dev Build Artifacts AI skill do?

Use when this Mac's disk is nearly full, or the user asks to clean build output — Rust target/ dirs or Claude Code worktrees (.claude/worktrees) under {{DEV_ROOT}} (「清编译产物」「清 target」「清 worktree」「硬盘满了」, "clean build artifacts"). Not for package-manager or app caches (cleaning-dev-caches) or personal files.

Why use Cleaning Dev Build Artifacts on TypingMind?

Because you install it once and use it with any model. Cleaning Dev Build Artifacts 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 Build Artifacts 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-build-artifacts. 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 Cleaning Dev Build Artifacts?

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 Build Artifacts?

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

Is the Cleaning Dev Build Artifacts 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 👇