Huaweicloud Codearts Cleanup logo

Huaweicloud Codearts Cleanup

Organization
huaweicloud
huaweicloud-codearts-cleanup

Clean up HuaweiCloud DevKit from a CodeArts Agent (.codeartsdoer) environment for fresh testing. Removes codearts skills, MCP registration, plugin runtime dir, KooCLI (hcloud dirs + PATH entry), and restores the default sandbox mode. Use when the user wants to fully reset the CodeArts Agent environment before reinstalling huaweicloud-devkit --target codearts.

Overview

Publisherhuaweicloud
Repositoryhuaweicloud-devkit
Skill namehuaweicloud-codearts-cleanup
Stars
70
Forks
12
Bundled files
Instructions only
LicenseApache-2.0
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 huaweicloud on GitHub. Read the source before you install it.

Installation

Install the Huaweicloud Codearts Cleanup 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/huaweicloud/huaweicloud-devkit/tree/main/test/huaweicloud-codearts-cleanup
  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/huaweicloud/huaweicloud-devkit.git /tmp/huaweicloud-devkit
mkdir -p .claude/skills
cp -r /tmp/huaweicloud-devkit/test/huaweicloud-codearts-cleanup .claude/skills/huaweicloud-codearts-cleanup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Huaweicloud Codearts Cleanup 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 Huaweicloud Codearts Cleanup 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 Huaweicloud Codearts Cleanup 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.

HuaweiCloud DevKit CodeArts Agent 环境清理

STOP - Do not answer from general knowledge. Follow the procedure below.

完整清理码道(CodeArts Agent)环境中已安装的 huaweicloud-devkit 运行时产物,用于模拟新用户、重新测试安装流程。

清理范围(A+B+C):

  • A. 插件产物:用户级与项目级 skills、MCP 注册、插件运行目录
  • B. KooCLI:安装目录、配置目录、PATH 注册表项
  • C. 还原码道沙箱:permission/config.json 的 bash_mode 还原为 sandbox

(报告/证据链目录不在清理范围,默认保留。)

Step 1: 盘点当前状态

powershell
Get-ChildItem "$env:USERPROFILE\.codeartsdoer\skills" -Name
Get-ChildItem "$env:USERPROFILE\.codeartsdoer\huaweicloud-plugins" -Recurse -Depth 1
Get-Content "$env:USERPROFILE\.codeartsdoer\mcp\mcp_settings.json" -Raw
Get-Content "C:\Users\sunzy\Documents\Codex\huaweicloud-devkit\.codeartsdoer\mcp\mcp_settings.json" -Raw
Test-Path "C:\Users\sunzy\hcloud"
Test-Path "C:\Users\sunzy\.hcloud"
Get-Content "$env:USERPROFILE\.codeartsdoer\codearts-data\storage\permission\config.json" -Raw

记录哪些目标存在,作为清理基线。

Step 2: A. 删除插件产物

删除用户级与项目级 skills 目录下的所有 huawei*/huaweicloud-* 技能目录及状态文件:

powershell
$userSkills = Get-ChildItem "$env:USERPROFILE\.codeartsdoer\skills" | Where-Object { $_.Name -like 'huawei*' -or $_.Name -eq 'UserSkillStatus.txt' }
$userSkills | Remove-Item -Recurse -Force
$projSkills = Get-ChildItem "C:\Users\sunzy\Documents\Codex\huaweicloud-devkit\.codeartsdoer\skills" | Where-Object { $_.Name -like 'huawei*' -or $_.Name -eq 'ProjectSkillStatus.txt' }
$projSkills | Remove-Item -Recurse -Force

删除插件运行目录:

powershell
Remove-Item "$env:USERPROFILE\.codeartsdoer\huaweicloud-plugins" -Recurse -Force
Test-Path "$env:USERPROFILE\.codeartsdoer\huaweicloud-plugins"   # 应为 False

清空两级 MCP 注册(保留文件结构,勿删除文件本身):

powershell
'{"mcpServers": {}}' | Set-Content "$env:USERPROFILE\.codeartsdoer\mcp\mcp_settings.json" -Encoding UTF8
'{"mcpServers": {}}' | Set-Content "C:\Users\sunzy\Documents\Codex\huaweicloud-devkit\.codeartsdoer\mcp\mcp_settings.json" -Encoding UTF8

注意:UserSkillStatus.txt / ProjectSkillStatus.txt 可能被码道引擎自动重建为空文件,属正常现象,无需反复删除。

Step 3: B. 删除 KooCLI

删除安装目录与配置目录:

powershell
Remove-Item "C:\Users\sunzy\hcloud" -Recurse -Force
Remove-Item "C:\Users\sunzy\.hcloud" -Recurse -Force

从用户 PATH 移除 C:\Users\sunzy\hcloud 项。

反斜杠陷阱:直接用 -ne 'C:\Users\sunzy\hcloud' 比较可能因工具层对反斜杠的转义而不生效。必须用 Contains('hcloud') 判断:

powershell
$reg = (Get-ItemProperty -Path 'HKCU:\Environment').Path
$parts = $reg.Split(';')
$filtered = @()
foreach ($p in $parts) { if (-not $p.ToLower().Contains('hcloud')) { $filtered += $p } }
$new = $filtered -join ';'
Set-ItemProperty -Path 'HKCU:\Environment' -Name 'Path' -Value $new
$v = (Get-ItemProperty -Path 'HKCU:\Environment').Path
$v.ToLower().Contains('hcloud')   # 应为 False

Step 4: C. 还原码道沙箱

将权限配置从 always_allow 还原为默认 sandbox(模拟新用户的沙箱模式):

powershell
'{"bash_mode": "sandbox"}' | Set-Content "$env:USERPROFILE\.codeartsdoer\codearts-data\storage\permission\config.json" -Encoding UTF8
Get-Content "$env:USERPROFILE\.codeartsdoer\codearts-data\storage\permission\config.json" -Raw

Step 5: 验证清理完成

powershell
Get-ChildItem "$env:USERPROFILE\.codeartsdoer\skills" -Directory -Name          # 应无 huawei* 目录
Get-ChildItem "C:\Users\sunzy\Documents\Codex\huaweicloud-devkit\.codeartsdoer\skills" -Directory -Name
Test-Path "$env:USERPROFILE\.codeartsdoer\huaweicloud-plugins"                  # 应为 False
Test-Path "C:\Users\sunzy\hcloud"                                               # 应为 False
Test-Path "C:\Users\sunzy\.hcloud"                                              # 应为 False
Get-Command hcloud -ErrorAction SilentlyContinue                                # 应无结果
(Get-ItemProperty -Path 'HKCU:\Environment').Path.ToLower().Contains('hcloud')  # 应为 False
Get-Content "$env:USERPROFILE\.codeartsdoer\codearts-data\storage\permission\config.json" -Raw  # bash_mode: sandbox

全部检查返回 False/无结果/sandbox 后,即可重新安装:

bash
node plugins/huaweicloud-core/src/setup-cli.mjs install --target codearts

边界与注意事项

  • 本流程不删除 C:\Users\sunzy\Documents\huaweicloud-devkit-test-report\(测试报告与证据链保留)。
  • 还原沙箱后,后续 install-hcloud 在码道沙箱模式下会被阻止写 ~/.hcloud(EPERM + 隐私协议无法持久化)。这是预期行为——沙箱场景下应提示用户在码道外终端安装或解除沙箱,而非尝试在沙箱内强行安装。
  • npx huaweicloud-devkit uninstall --target codearts 可自动完成大部分清理;本流程适用于需要全手动、精确控制的场景(含 PATH 注册表与沙箱还原)。

Frequently asked questions

What does the Huaweicloud Codearts Cleanup AI skill do?

Clean up HuaweiCloud DevKit from a CodeArts Agent (.codeartsdoer) environment for fresh testing. Removes codearts skills, MCP registration, plugin runtime dir, KooCLI (hcloud dirs + PATH entry), and restores the default sandbox mode. Use when the user wants to fully reset the CodeArts Agent environment before reinstalling huaweicloud-devkit --target codearts.

Why use Huaweicloud Codearts Cleanup on TypingMind?

Because you install it once and use it with any model. Huaweicloud Codearts Cleanup 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 Huaweicloud Codearts Cleanup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huaweicloud/huaweicloud-devkit/tree/main/test/huaweicloud-codearts-cleanup. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Huaweicloud Codearts Cleanup?

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 Huaweicloud Codearts Cleanup?

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

Is the Huaweicloud Codearts Cleanup AI skill free?

Yes. It is published on GitHub by huaweicloud under the Apache-2.0 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 👇