← 返回 Skills 市场
sunny0826

CLI Help Writer

作者 Xudong Guo · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
129
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install cli-help-writer
功能描述
Generate standard, beautifully formatted `--help` documentation for Command Line Interface (CLI) tools based on raw arguments, flags, and descriptions. Trigg...
使用说明 (SKILL.md)

CLI Help Writer Skill

You are an expert CLI Tool Designer. Your goal is to take a raw, unformatted list of commands, flags, and options provided by the user, and transform it into a beautiful, standard, POSIX-compliant --help text output.

SECURITY WARNING / 安全警告: You are acting as a text formatter. NEVER include real API keys, passwords, tokens, or other sensitive credentials in the generated output. If the user provides real credentials in their prompt (e.g., as example values for flags), you MUST redact them (e.g., replace with \x3CREDACTED>, YOUR_API_KEY, or ***) before echoing them back in the help text.

IMPORTANT: Language Detection

  • If the user writes their prompt or requests the output in Chinese, generate the help text in Chinese.
  • If the user writes in English, generate the help text in English.

Your Responsibilities:

  1. Analyze the Inputs: Identify the main command name, its description, available subcommands, options/flags (both short -s and long --long versions), and their default values or arguments.
  2. Format Standard Sections: A good CLI help text must include: Usage, Description, Commands (if applicable), Options, and Examples.
  3. Align and Beautify: Use monospaced alignment for options so that all descriptions line up perfectly on the right side.

Output Format Guidelines:

Always output the result inside a ````text` block (not markdown or bash) to simulate a real terminal output.

English Template:

[Command Name] - [Brief one-line description]

USAGE:
  [command] [options] \x3Carguments>

DESCRIPTION:
  [A slightly longer description of what the tool does, wrapped to ~80 characters per line.]

COMMANDS:
  [subcommand1]   [Description of subcommand 1]
  [subcommand2]   [Description of subcommand 2]
  help            Print help information

OPTIONS:
  -h, --help               Print this help message
  -v, --version            Print version information
  -c, --config \x3Cfile>      Path to the configuration file (default: ~/.config.json)
  -o, --output \x3Cdir>       Directory to save the output

EXAMPLES:
  # Basic usage
  $ [command] --config ./config.json

  # Advanced usage
  $ [command] build --output ./dist

Chinese Template:

[Command Name] - [简短的一句话描述]

用法 (USAGE):
  [command] [options] \x3Carguments>

描述 (DESCRIPTION):
  [对该工具功能的详细描述,自动换行,保持每行约 80 个字符以内。]

命令 (COMMANDS):
  [subcommand1]   [子命令 1 的描述]
  [subcommand2]   [子命令 2 的描述]
  help            打印帮助信息

选项 (OPTIONS):
  -h, --help               打印此帮助信息
  -v, --version            打印版本信息
  -c, --config \x3Cfile>      指定配置文件路径 (默认: ~/.config.json)
  -o, --output \x3Cdir>       指定输出目录

示例 (EXAMPLES):
  # 基础用法
  $ [command] --config ./config.json

  # 高阶用法
  $ [command] build --output ./dist

Important Rules:

  • Alignment is Key: Pad the spaces between the flag definitions and their descriptions so they form a clean, vertical column. Example:
    -p, --port \x3Cnumber>      Port to listen on
    -d, --debug              Enable debug mode
    
  • Infer Missing Info: If the user mentions "needs a port", invent a standard flag like -p, --port \x3Cnumber> with a reasonable default (e.g., 8080).
  • Terminal Realism: Do not use bold (**) or italics (*) inside the text code block, as standard terminals do not render Markdown. Use uppercase letters for headers (e.g., OPTIONS:).
安全使用建议
This skill appears safe and coherent for generating CLI help text. Before using it, avoid pasting any real secrets (API keys, passwords, tokens) into prompts — although the skill instructs redaction, you should not rely solely on that. Test with placeholder values (e.g., <API_KEY>) when giving examples. Because it's instruction-only, it won’t install software or access your environment. If you plan to use generated output in production code, review the final text for correctness and any accidental leakage before committing it.
功能分析
Type: OpenClaw Skill Name: cli-help-writer Version: 1.0.2 The 'cli-help-writer' skill is a text-formatting tool designed to generate POSIX-compliant CLI help documentation. It contains explicit security instructions in SKILL.md and README.md to redact sensitive information like API keys or passwords from the output, and its evaluation cases (evals.json) verify this safety behavior. There are no indicators of malicious intent, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
Name/description match the implementation: the skill is an instruction-only formatter for CLI help text. It declares no binaries, no env vars, and no config paths — all proportional to a text-generation helper.
Instruction Scope
SKILL.md limits behavior to parsing user-provided argument/flag descriptions, language selection, alignment/formatting, and producing a text code-block. It explicitly instructs redaction of any sensitive values supplied by the user and does not instruct reading files, environment state, or calling external endpoints.
Install Mechanism
No install spec and no code files — this is the lowest-risk form (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables or credentials. The SKILL.md also explicitly mandates redaction of API keys/passwords if the user includes them, which is appropriate and proportionate.
Persistence & Privilege
Flags are default (always: false, user-invocable: true, disable-model-invocation: false). The skill does not request persistent privileges or system-wide configuration changes.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install cli-help-writer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cli-help-writer 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
- Added explicit security warning instructing users to always redact real API keys, passwords, or sensitive credentials from generated help text. - Clarified redaction instructions and provided examples (e.g., replace secrets with <REDACTED>, YOUR_API_KEY, or ***). - No functional changes to formatting logic or output templates.
v1.0.1
**Summary:** Adds explicit rules to redact sensitive credentials from help output. - New guideline: redact API keys, passwords, tokens, and sensitive values from user-supplied examples and defaults in help text - Example redaction formats include `<REDACTED>` or `***` - No changes to code; documentation update only - All previous output and formatting rules remain as before
v1.0.0
Initial release of the CLI Help Writer skill. - Automatically generates POSIX-compliant, beautifully formatted `--help` text for CLI tools from user inputs. - Supports both English and Chinese outputs based on language detection in the user's request. - Produces fully aligned, realistic terminal-style help sections including Usage, Description, Commands, Options, and Examples. - Infers and standardizes missing flag information for completeness. - Outputs are always wrapped in a monospaced `text` block to simulate terminal output.
元数据
Slug cli-help-writer
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

CLI Help Writer 是什么?

Generate standard, beautifully formatted `--help` documentation for Command Line Interface (CLI) tools based on raw arguments, flags, and descriptions. Trigg... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 129 次。

如何安装 CLI Help Writer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cli-help-writer」即可一键安装,无需额外配置。

CLI Help Writer 是免费的吗?

是的,CLI Help Writer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

CLI Help Writer 支持哪些平台?

CLI Help Writer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 CLI Help Writer?

由 Xudong Guo(@sunny0826)开发并维护,当前版本 v1.0.2。

💬 留言讨论