Disk Raccoon

What it does

When your agent uses it

• : 用户说磁盘满了、清理缓存、Mac 空间不够、某个应用占了几十个 G、 帮我瘦身、cache cleaner、磁盘体检。只管缓存，不做应用卸载和系统优化

Example prompts

• “Use the disk-raccoon skill to maco 缓存清理 Agent（小浣熊）。对 Mac 上的开发工具缓存、应用缓存做只读体检， 按缓存地图的安全等级判断哪些能删，经用户确认后执行清理”
• “/disk-raccoon”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1第一轮只读。 只用 du、ls、pgrep 收集信息，输出报告。用户没确认之前，一个字节都不删。
2. 2地图优先。 删除任何路径前，先查 references/cache-map.md。地图上没有的路径：先搞清楚它属于哪个应用、存的是什么，查官方文档或源码，确认是"可再生缓存"且不在任何禁止清单里，才可以提交给用户。查不清楚就报告为"未知，不建议动"。
3. 3状态神圣。 登录态、消息数据库、聊天记录、钥匙串、配置文件，永远不碰。只动"删掉后应用会自动重新生成或重新下载"的东西。
4. 4先退场再动手。 目标应用正在运行就先退出（pkill 优雅退出，失败再 -9），避免边删边重建。
5. 5可恢复优先。 用户目录下的内容进 ~/.Trash（shutil.move），不直接 rm -rf。系统级路径（/Library）删除需要 sudo，生成命令让用户自己跑，不代跑。
6. 6删除前报数。 报告里每项写清楚：路径、大小、属于什么应用、安全等级、删除后果。让用户勾选。

What it can do on your machine

Read from SKILL.md and the folder at commit c44ef19. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Disk Raccoon loads about 427 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 78 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~44

When it runs · the whole SKILL.md, loaded when a task matches

~427

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from orange2ai/disk-raccoon at commit c44ef19, republished under its MIT licence (© orange2ai). 78 words, ~427 tokens.

name

disk-raccoon

description

macOS 缓存清理 Agent（小浣熊）。对 Mac 上的开发工具缓存、应用缓存做只读体检， 按缓存地图的安全等级判断哪些能删，经用户确认后执行清理。 Use when: 用户说磁盘满了、清理缓存、Mac 空间不够、某个应用占了几十个 G、 帮我瘦身、cache cleaner、磁盘体检。只管缓存，不做应用卸载和系统优化。

# 磁盘总量
df -h /

# 缓存地图上的候选路径（见 references/cache-map.md 全表）
du -sh ~/.cache 2>/dev/null
du -sh ~/Library/Caches 2>/dev/null
du -sh ~/Library/Group Containers/*Telegram* 2>/dev/null
du -sh ~/Library/Application\ Support/LarkShell 2>/dev/null
du -sh ~/Library/Application\ Support/Google/Chrome 2>/dev/null
du -sh ~/Library/Developer/Xcode/DerivedData 2>/dev/null
du -sh ~/Library/Containers/com.tencent.xinWeChat 2>/dev/null

© orange2ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in the repository root of orange2ai/disk-raccoon.

• SKILL.md
• .gitignore
• LICENSE
• README.en.md
• README.md
• references/cache-map.md

Open the folder on GitHubat commit c44ef19