Token导航 LogoToken导航TokenDH.com
前端设计敏感数据github未标认证来源可访问许可证需确认审计通过

cmd-idiot-proof-docscmd 白痴证明文档

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

756

周安装

17

GitHub Stars

7

下载量

140
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:cmd-idiot-proof-docs(cmd 白痴证明文档)
来源仓库:https://github.com/olshansk/agent-skills
仓库路径:skills/cmd-idiot-proof-docs
安装命令:
npx skills add https://github.com/olshansk/agent-skills --skill cmd-idiot-proof-docs
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/olshansk/agent-skills --skill cmd-idiot-proof-docs

简介

简化文档结构,提升可读性与执行效率。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

  • 优先展示快速上手路径,保留原始事实内容。
  • 支持配置表与备选方案,复杂细节放入折叠区块。
  • 编辑前需经用户批准,避免擅自更改关键路径。
  • cmd-idiot-proof-docs 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Simple Docs for Humans and Agents

Use this command to write or rewrite documentation so it is simple, fast to scan, and easy to execute.

Primary Goal

  • Bias toward simple docs.
  • Start with the shortest successful path.
  • Preserve original meaning and factual content while reordering for clarity.

Required Output Order

  1. Quickstart (always first)
  2. Main workflow
  3. Configuration/reference tables (when relevant)
  4. Alternative paths (only when they are true user/code path alternatives)
  5. Extra details at the end inside <details><summary>...</summary>...</details>

Approval Gate (Required)

  • Before editing any file, show a change preview for approval.
  • Use this exact preview structure for each file:

- Additions - Removals - Changes

  • Show the concrete text to be added, removed, or changed.
  • Wait for explicit user approval before applying edits.
  • Apply only the approved edits.
  • If approval is not granted, do not modify files.

Core Rules

  • Optimize for both human readers and agent readers.
  • Maximize copy-paste command snippets.
  • Prefer short sections and concise language.
  • Use Markdown tables when information is structured.
  • Use Mermaid diagrams when they improve understanding of flow or architecture.
  • Avoid unnecessary sections.
  • Avoid "Optional" sections unless they represent an actual alternate path.
  • Put superfluous/background material at the end.
  • Add "Code Structure" only when repository layout helps task completion.

Command Block Rules (Strict)

  • Do not place comments inside bash code blocks.
  • Put labels outside code blocks.

Correct pattern:

Start the server:

make start_server

Run a command:

make run_command

Incorrect pattern (separate steps combined in one unlabeled block):

make start_server
make run_command

Section Defaults

Use only sections that add value for the specific document. Default section set:

  • Quickstart
  • Main Workflow
  • Configuration
  • Code Structure (only if useful)
  • Troubleshooting (only for real recurring issues)

Configuration Table Format

If environment variables or configuration values are required, use this format:

NamePurposeDefault
APP_ENVRuntime environmentdevelopment
API_URLBase URL for API callshttp://localhost:8000

Details Block Rule

Move long explanations, implementation notes, and low-priority reference material into details blocks:

<details>
<summary>Deep dive: request lifecycle</summary>

Detailed explanation here.

</details>

Deliverable

  • Return the final output as Markdown (.md).
  • Keep all important content, but simplify, reorder, and prioritize for quick execution.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.55%
按下载量换算48

Claude

30.37%
按下载量换算43

Cursor

19.86%
按下载量换算28

Gemini CLI

10.59%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills