Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

docs-pro专业文档

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

367

周安装

15

GitHub Stars

9

下载量

119
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:docs-pro(专业文档)
来源仓库:https://github.com/yuniorglez/gemini-elite-core
仓库路径:skills/docs-pro
安装命令:
npx skills add https://github.com/yuniorglez/gemini-elite-core --skill docs-pro
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/yuniorglez/gemini-elite-core --skill docs-pro

简介

用于辅助技术文档的全生命周期管理,实现从代码到用户文档的无缝衔接。

  • 适用于 README、API 说明、配置指南等 Markdown 文档的结构梳理与内容优化。
  • 可自动提取代码特征、补齐章节、统一术语并检查链接有效性。
  • 需基于项目实际路径和命令保留事实,避免虚构未验证信息。
  • 对外文案应保持客观语气,防止过度承诺或夸大功能边界。

SKILL.md

📚 Skill: docs-pro (v1.1.0)

Executive Summary

docs-pro is a comprehensive skill for managing the lifecycle of technical documentation. It bridges the gap between raw implementation and user-facing clarity. In 2026, we treat Documentation as Code (DaC), using AI to ensure that every new feature, configuration, and API change is accurately reflected in our docs within minutes of a commit.


📋 Table of Contents

  1. Core Capabilities
  2. The "Do Not" List (Anti-Patterns)
  3. Quick Start: The Sync Audit
  4. Standard Production Patterns
  5. Documentation Quality Standards
  6. AI-Driven Documentation Workflow
  7. Reference Library

🚀 Core Capabilities

  • Automated Sync Audit: Scanning codebases for undocumented exports, settings, and flags.
  • Style Enforcement: Ensuring all documentation follows the 2026 Squaads AI Style Guide.
  • Modular Content Architecture: Managing reusable snippets and modular pages for scalability.
  • Multimodal Documentation: Integrating diagrams (Mermaid), code examples, and interactive elements.

🚫 The "Do Not" List (Anti-Patterns)

Anti-PatternWhy it fails in 2026Modern Alternative
"Click Here" LinksBad for accessibility and AI context.Use Descriptive Anchor Text.
Outdated DefaultsLeads to user frustration and support tickets.Use Docs Sync Audit to verify defaults.
Manual Reference DocsImpossible to maintain at scale.Generate API refs from Code Docstrings.
Wall of TextLow information retention.Use Bullet Points, Tables, and Diagrams.
Mixing LanguagesMakes maintenance and translation hard.Keep English as the Source of Truth in docs/.

⚡ Quick Start: The Sync Audit

Perform a basic check to see what's missing in your documentation:

# 1. Analyze changes in current branch vs main
git diff main...HEAD -- src/

# 2. Search for common undocumented patterns
rg "export (const|function|class)" src/ --type ts

# 3. Compare findings with docs/ structure
ls -R docs/

🛠 Standard Production Patterns

Pattern A: The Feature Release Doc

When implementing a new feature, follow this checklist:

  1. Overview: What does it do?
  2. Configuration: List all environment variables and settings.
  3. Examples: Provide "Quick Start" and "Advanced" code blocks.
  4. Troubleshooting: Common errors and their fixes.

Pattern B: The API Reference Update

Instead of editing docs/ref/*.md directly:

  1. Update the JSDoc/TSDoc comments in the source code.
  2. Run the doc generator (e.g., make build-docs).
  3. Verify the output matches the Markdown Standard.

📏 Documentation Quality Standards

We adhere to strict standards to ensure high utility for both humans and AI agents.

  • Clarity: Active voice, present tense, and direct address.
  • Accuracy: Code examples must be tested and valid.
  • Discoverability: Every page must be listed in mkdocs.yml with a descriptive title.

*See References: Style Guide for more.*


🤖 AI-Driven Documentation Workflow

  1. Inventory: AI scans the codebase to build a feature list.
  2. Gap Analysis: AI compares the inventory to existing .md files.
  3. Drafting: AI proposes new content based on implementation logic.
  4. Review: Human-in-the-loop verification of tone and accuracy.

*See References: AI Collaboration for more.*


📖 Reference Library

Detailed deep-dives into documentation excellence:


*Updated: January 22, 2026 - 17:05*

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

32.51%
按下载量换算39

Claude

31.13%
按下载量换算37

Cursor

18.75%
按下载量换算22

Gemini CLI

10.08%
按下载量换算12

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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