Bash Style logo

Bash Style

CommunityPopular
doccker
bash-style

当用户操作 .sh、Dockerfile、Makefile、.yml、.yaml 文件,或在 Markdown 中编写 bash 代码块时触发。提供 Bash 编写规范。

Overview

Publisherdoccker
Repositorycc-use-exp
Skill namebash-style
Stars
1.1K
Forks
116
Bundled files
Instructions only
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 doccker on GitHub. Read the source before you install it.

Installation

Install the Bash Style 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/doccker/cc-use-exp/tree/main/.claude/skills/bash-style
  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/doccker/cc-use-exp.git /tmp/cc-use-exp
mkdir -p .claude/skills
cp -r /tmp/cc-use-exp/.claude/skills/bash-style .claude/skills/bash-style
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bash Style 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 Bash Style 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 Bash Style 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.

Bash 编写规范

版本:v1.0 更新:2026-01


1. 注释规范

禁止行尾注释

  • ❌ 禁止行尾注释(如 command # 注释)
  • ✅ 注释应独占一行,放在代码上方

适用范围:

  • Shell 脚本文件(.sh)
  • Markdown 文档中的 bash 代码块
  • Dockerfile、Makefile 中的 shell 命令
bash
# ❌ 错误:行尾注释
curl -X POST https://api.example.com/data # 发送请求
docker run -d nginx # 启动容器
cp -r src/ dist/ # 复制文件

# ✅ 正确:注释独占一行
# 发送请求
curl -X POST https://api.example.com/data

# 启动容器
docker run -d nginx

# 复制文件
cp -r src/ dist/

原因:

  • 复制粘贴时容易带上注释导致命令出错
  • 长命令 + 注释 = 超长行,可读性差
  • Heredoc 块内 # 不是注释而是内容

2. 文件写入方式

推荐方式:tee 命令

bash
# ✅ 推荐:简洁、无嵌套引号
sudo tee /etc/fail2ban/jail.d/docker-nginx.local > /dev/null << 'EOF'
[docker-nginx]
enabled = true
filter = docker-nginx
logpath = /var/log/nginx/access.log
maxretry = 5
EOF

追加内容

bash
# ✅ 追加到文件
sudo tee -a /etc/hosts > /dev/null << 'EOF'
192.168.1.100 myserver
EOF

# ✅ 单行追加
echo '192.168.1.100 myserver' | sudo tee -a /etc/hosts

避免的写法

bash
# ❌ 避免:嵌套引号复杂,易出错
sudo bash -c 'cat > /etc/xxx << EOF
content
EOF'

# ❌ 避免:需要转义内容中的特殊字符
sudo sh -c "echo 'line1\nline2' > /etc/xxx"

方式对比

方式优点缺点推荐场景
sudo tee简洁、无嵌套需 > /dev/null 抑制输出首选
sudo bash -c 'cat >'无需 tee嵌套引号复杂不推荐
临时文件 + mv可先验证步骤多复杂配置

3. Heredoc 引号规则

禁止变量展开(推荐默认)

bash
# ✅ 'EOF' 带引号:内容原样输出,不解析变量
sudo tee /etc/xxx > /dev/null << 'EOF'
$HOME 不会被展开
$(command) 不会被执行
EOF

需要变量展开

bash
# EOF 不带引号:变量会被展开
sudo tee /etc/xxx > /dev/null << EOF
当前用户: $USER
当前目录: $(pwd)
EOF

选择原则

场景用法原因
配置文件<< 'EOF'避免意外展开
模板生成<< EOF需要插入变量
不确定时<< 'EOF'更安全

4. 权限与路径

需要 root 权限

bash
# ✅ 正确:tee 配合 sudo
echo 'content' | sudo tee /etc/xxx

# ❌ 错误:重定向在 sudo 之外,权限不足
sudo echo 'content' > /etc/xxx

路径带空格

bash
# ✅ 正确:双引号包裹路径
sudo tee "/etc/my config/file.conf" > /dev/null << 'EOF'
content
EOF

5. 脚本规范

文件头

bash
#!/usr/bin/env bash
set -euo pipefail

# 脚本说明(一句话)

set 选项说明

选项作用
-e命令失败时退出
-u使用未定义变量时报错
-o pipefail管道中任一命令失败则整体失败

变量使用

bash
# ✅ 推荐:使用 ${} 包裹
echo "Hello, ${name}"

# ✅ 推荐:设置默认值
db_host="${DB_HOST:-localhost}"

# ❌ 避免:裸变量(易与后续字符混淆)
echo "Hello, $name_suffix"

6. 常用模式

检查命令是否存在

bash
if ! command -v docker &> /dev/null; then
    echo "docker 未安装"
    exit 1
fi

检查文件/目录

bash
# 文件存在
[[ -f /path/to/file ]] && echo "文件存在"

# 目录存在
[[ -d /path/to/dir ]] || mkdir -p /path/to/dir

安全删除

bash
# ✅ 使用变量时防止误删
rm -rf "${dir:?}"/*

# ❌ 危险:变量为空时会删除根目录
rm -rf $dir/*

7. 文档中的代码块

在 Markdown 文档中编写 bash 命令时,同样遵循以上规范:

markdown
## 安装配置

创建配置文件:

```bash
sudo tee /etc/myapp/config.yml > /dev/null << 'EOF'
server:
  port: 8080
  host: 0.0.0.0
EOF
```

参考资料

Frequently asked questions

What does the Bash Style AI skill do?

当用户操作 .sh、Dockerfile、Makefile、.yml、.yaml 文件,或在 Markdown 中编写 bash 代码块时触发。提供 Bash 编写规范。

Why use Bash Style on TypingMind?

Because you install it once and use it with any model. Bash Style 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 Bash Style in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/doccker/cc-use-exp/tree/main/.claude/skills/bash-style. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bash Style?

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 Bash Style?

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

Is the Bash Style AI skill free?

It is published on GitHub by doccker. Check the repository for licensing terms. 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 👇