Token导航 LogoToken导航

Agent Skill · 前端设计

taiwan-md-knowledge-base(台湾医学博士知识库)

用于搭建或维护带检索增强的 RAG 工作流,适合让 Agent 处理知识库问答、向量检索、来源引用和事实核查。它可以辅助整理数据接入、Embedding、向量库、召回参数和回答生成流程。使用时需要确认数据来源、更新频率、召回阈值和引用展示方式,避免把未命中的资料或过期内容包装成确定事实。

taiwan-md-knowledge-base 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在前端设计类的 10,216 个 Skill 里排第 433。

总安装 24,646周安装 997GitHub Stars 39下载 7,737核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:taiwan-md-knowledge-base(台湾医学博士知识库)
来源仓库:https://github.com/aradotso/trending-skills
仓库路径:skills/taiwan-md-knowledge-base
安装命令:
npx skills add https://github.com/aradotso/trending-skills --skill taiwan-md-knowledge-base
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/aradotso/trending-skills --skill taiwan-md-knowledge-base

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

构建面向台湾医学博士群体的知识库问答系统。集成向量检索与来源引用机制增强回答可信度。支持专业术语解析与临床指南查询。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。应定期更新医学文献数据库以确保准确性。

taiwan-md-knowledge-base 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/taiwan-md-knowledge-base

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/aradotso/trending-skills --skill taiwan-md-kno…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

taiwan-md-knowledge-base 怎么安装?

在终端执行 npx skills add https://github.com/aradotso/trending-skills --skill taiwan-md-knowledge-bas…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

taiwan-md-knowledge-base 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

taiwan-md-knowledge-base 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

taiwan-md-knowledge-base 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

taiwan-md-knowledge-base 用的人多吗?

公开数据是累计安装 24,646 次,近一周安装 997 次,下载 7,737 次,GitHub 39 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

taiwan-md-knowledge-base 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
taiwan-md-knowledge-base

台湾医学博士知识库 · 本页

24,64639需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Taiwan.md Knowledge Base

Skill by ara.so — Daily 2026 Skills collection.

Taiwan.md is an open-source, AI-native knowledge base about Taiwan built with Astro v5. It uses a Single Source of Truth (SSOT) architecture where all content lives in the knowledge/ directory as Markdown files, and the website is a build-time projection. Features include bilingual support (Traditional Chinese as default + English), an interactive D3.js knowledge graph, and 96+ curated articles across 12 categories.


Installation & Setup

Prerequisites

  • Node.js 18+
  • npm or pnpm

Clone and Install

git clone https://github.com/frank890417/taiwan-md.git
cd taiwan-md
npm install

Development Server

npm run dev
# Site available at http://localhost:4321

Build & Preview

npm run build
npm run preview

Sync Knowledge to Content

bash scripts/sync.sh
# Copies knowledge/ → src/content/ for Astro build

Project Architecture

taiwan-md/
├── knowledge/               ← SSOT: ALL content lives here
│   ├── History/             ← Chinese articles + _Hub.md
│   ├── Geography/
│   ├── Culture/
│   ├── Food/
│   ├── Art/
│   ├── Music/
│   ├── Technology/
│   ├── Nature/
│   ├── People/
│   ├── Society/
│   ├── Economy/
│   ├── Lifestyle/
│   ├── About/               ← Meta content
│   └── en/                  ← English translations (mirrors zh-TW)
│       ├── History/
│       ├── Geography/
│       └── ...
├── scripts/
│   └── sync.sh              ← Syncs knowledge/ → src/content/
├── src/
│   ├── pages/               ← Astro pages
│   ├── layouts/             ← Shared layouts
│   └── content/             ← Build-time projection (DO NOT EDIT)
├── public/
│   └── images/wiki/         ← Cached Wikimedia Commons images
└── docs/                    ← Architecture & roadmap docs

Critical rule: Never edit files in src/content/ directly. Always edit knowledge/ and run scripts/sync.sh.


Content Structure

The 12 Categories

SlugChineseEnglish
history歷史History
geography地理Geography
culture文化Culture
food美食Food
art藝術Art
music音樂Music
technology科技Technology
nature自然Nature
people人物People
society社會Society
economy經濟Economy
lifestyle生活Lifestyle

Article File Naming

knowledge/
├── Food/
│   ├── _Hub.md              ← Category hub page (literary overview)
│   ├── bubble-tea.md        ← Individual article (zh-TW)
│   └── beef-noodle.md
└── en/
    └── Food/
        ├── _Hub.md          ← English hub page
        ├── bubble-tea.md    ← English translation
        └── beef-noodle.md

Writing Articles

Chinese Article Template (knowledge/[Category]/article-slug.md)

---
title: 珍珠奶茶
description: 台灣最具代表性的飲料文化,從夜市攤車到全球連鎖,珍珠奶茶如何征服世界。
category: food
date: 2024-01-15
tags: [飲食文化, 台灣之光, 夜市]
image: /images/wiki/bubble-tea-abc123.jpg
imageCaption: 台灣珍珠奶茶 | Wikimedia Commons | CC BY-SA 4.0
sources:
  - title: 珍珠奶茶的起源考證
    url: https://example.com/boba-origin
  - title: 台灣飲料市場報告
    url: https://example.com/beverage-report
---

## 30 秒認識

珍珠奶茶(波霸奶茶)誕生於 1980 年代台灣,現已成為全球年產值超過 30 億美元的飲料產業。

## 深度閱讀

### 起源爭議

台南翰林茶館與台中春水堂都聲稱是珍珠奶茶的發明者...

### 全球擴張

2010 年代,珍珠奶茶席捲歐美亞各大城市...

## 為什麼重要

珍珠奶茶不只是一杯飲料,它是台灣軟實力的最佳代言人——在沒有邦交的地方,台灣味道先到了。

## 參考資料

- [珍珠奶茶的起源考證](https://example.com/boba-origin)
- [台灣飲料市場報告](https://example.com/beverage-report)

English Article Template (knowledge/en/[Category]/article-slug.md)

---
title: Bubble Tea
description: Taiwan's most iconic beverage culture — how boba conquered the world from night market stalls to global chains.
category: food
date: 2024-01-15
tags: [food culture, taiwan pride, night market]
image: /images/wiki/bubble-tea-abc123.jpg
imageCaption: Taiwanese Bubble Tea | Wikimedia Commons | CC BY-SA 4.0
sources:
  - title: Origins of Bubble Tea
    url: https://example.com/boba-origin
  - title: Taiwan Beverage Market Report
    url: https://example.com/beverage-report
---

## 30-Second Overview

Bubble tea (boba) was born in 1980s Taiwan and has grown into a global industry worth over $3 billion annually.

## Deep Dive

### The Origin Debate

Both Hanlin Tea Room in Tainan and Chun Shui Tang in Taichung claim to have invented bubble tea...

### Global Expansion

In the 2010s, bubble tea swept across cities in Europe, America, and Asia...

## Why This Matters

Bubble tea isn't just a drink — it's Taiwan's finest soft power ambassador. Where there's no diplomatic recognition, Taiwanese flavor arrived first.

## References

- [Origins of Bubble Tea](https://example.com/boba-origin)
- [Taiwan Beverage Market Report](https://example.com/beverage-report)

Hub Page Template (knowledge/[Category]/_Hub.md)

---
title: 美食
titleEn: Food
description: 台灣的飲食文化是移民歷史、地理環境與創意精神的完美結晶。
category: food
---

## 關於這個分類

台灣是一個以食物說故事的地方...

## 精選文章

這個分類收錄了台灣飲食文化最具代表性的面向...

Frontmatter Reference

Required Fields

---
title: "文章標題"           # Display title
description: "一句話說明"   # Meta description (150 chars max)
category: food             # Must match one of 12 category slugs
date: 2024-01-15           # ISO date format
---

Optional Fields

---
tags: [tag1, tag2]         # Array of tags for knowledge graph
image: /images/wiki/...    # Must be from Wikimedia Commons cache
imageCaption: "..."        # Attribution: Title | Source | License
sources:                   # REQUIRED: clickable URLs, no plain-text refs
  - title: "Source Name"
    url: https://...
---

Adding Images (Wikimedia Commons Policy)

All images must be from Wikimedia Commons with verified CC licenses. Cache them locally:

# Download and cache a Wikimedia image
# Images are stored with MD5-hashed filenames
curl -o public/images/wiki/$(echo "filename.jpg" | md5sum | cut -d' ' -f1).jpg \
  "https://commons.wikimedia.org/wiki/Special:FilePath/Taiwan_landscape.jpg"

Image attribution format in frontmatter:

imageCaption: "Description | Wikimedia Commons | CC BY-SA 4.0"

Knowledge Graph Integration

Articles automatically appear in the D3.js knowledge graph at /graph. Nodes are created from articles; edges are created from shared tags and cross-references.

Linking Articles

Reference other articles within content using relative paths:

台灣的[半導體產業](/technology/tsmc)是台積電...

See also: [Bubble Tea](/food/bubble-tea) for more on Taiwan's soft power.

Tagging for Graph Connections

Use consistent tags to create knowledge graph bridges:

# Both articles tagged [democratic transition] will be connected
tags: [democratic transition, civil society, 1990s]

Sync Workflow

After editing any file in knowledge/, always sync before building:

# 1. Edit content
vim knowledge/Food/new-article.md
vim knowledge/en/Food/new-article.md

# 2. Sync to src/content/
bash scripts/sync.sh

# 3. Verify build
npm run build

# 4. Preview
npm run preview

Three-Layer Depth Pattern

Every article should follow this structure for AI-readability and varied reading levels:

## 30 秒認識 / 30-Second Overview
[2-3 sentences, the essential fact]

## 深度閱讀 / Deep Dive
### Subsection 1
[Detailed exploration with data]

### Subsection 2
[Historical context or comparison]

## 為什麼重要 / Why This Matters
[Curatorial perspective — answer "why should the world care?"]

## 參考資料 / References
[Clickable URLs only — no plain-text citations]

Contributing via PR

Full PR Workflow

# 1. Fork and clone
git clone https://github.com/YOUR_USERNAME/taiwan-md.git
cd taiwan-md

# 2. Create branch
git checkout -b add/food/scallion-pancake

# 3. Add zh-TW article
cat > knowledge/Food/scallion-pancake.md << 'EOF'
---
title: 蔥抓餅
description: ...
category: food
date: 2024-01-20
sources:
  - title: Source
    url: https://...
---
Content here...
EOF

# 4. Add English translation
mkdir -p knowledge/en/Food
cat > knowledge/en/Food/scallion-pancake.md << 'EOF'
---
title: Scallion Pancake
...
EOF

# 5. Sync and test
bash scripts/sync.sh
npm run build

# 6. Commit and PR
git add knowledge/
git commit -m "feat(food): add scallion pancake article (zh+en)"
git push origin add/food/scallion-pancake

Commit Message Convention

feat(category): add [article name] article (zh+en)
fix(category): correct [article name] factual error
i18n(category): add English translation for [article name]
feat(graph): add knowledge graph connections for [topic]

AI-Native Features

llms.txt

The site exposes /llms.txt for AI consumption. When writing content, use structured headers that AI can parse:

# Title

**Key fact:** One-sentence essential truth.

## Context
...

## Significance
...

Meta AI Summary Tag

Pages include <meta ai-summary> — write descriptions that work as standalone AI context:

description: "台積電(TSMC)生產全球90%最先進晶片,是台灣的「矽盾」——台灣的地緣政治生存策略。"

Astro Page Patterns

Category Page (src/pages/[category].astro)

---
import { getCollection } from 'astro:content';

const category = 'food';
const articles = await getCollection('knowledge', ({ data }) =>
  data.category === category
);
---

<ul>
  {articles.map(article => (
    <li>
      <a href={`/${category}/${article.slug}`}>{article.data.title}</a>
      <p>{article.data.description}</p>
    </li>
  ))}
</ul>

Bilingual Route Pattern

/food/bubble-tea        ← zh-TW (default)
/en/food/bubble-tea     ← English

Content Quality Checklist

Before submitting a PR, verify:

  • Both knowledge/[Category]/article.md (zh-TW) and knowledge/en/[Category]/article.md (en) exist
  • All sources entries have clickable url fields (no plain-text-only references)
  • Article follows three-layer depth: 30-sec → deep dive → why it matters
  • Images sourced from Wikimedia Commons with proper imageCaption attribution
  • category slug matches one of the 12 valid categories exactly
  • bash scripts/sync.sh && npm run build completes without errors
  • Factual claims are verified against cited sources

Troubleshooting

Build fails after adding article

# Check frontmatter syntax
cat knowledge/Food/my-article.md | head -20

# Common issue: missing required fields
# Ensure title, description, category, date are all present

# Re-sync and rebuild
bash scripts/sync.sh
npm run build 2>&1 | grep ERROR

Article not appearing in knowledge graph

# Ensure tags array is populated
# Check category slug matches exactly (case-sensitive)
# Verify sync was run after editing
bash scripts/sync.sh

English article not showing at /en/...

# Verify file exists at correct path
ls knowledge/en/Food/my-article.md

# Check category field matches zh-TW article exactly
grep "category:" knowledge/Food/my-article.md
grep "category:" knowledge/en/Food/my-article.md

Images not loading

# Images must be cached locally in public/images/wiki/
ls public/images/wiki/

# Verify frontmatter path starts with /images/wiki/
grep "image:" knowledge/Food/my-article.md
# Should be: image: /images/wiki/filename-hash.jpg

Sync script permission error

chmod +x scripts/sync.sh
bash scripts/sync.sh

Resources

平台分布

Codex

38.83%
按下载量换算3,004

Claude

29.3%
按下载量换算2,267

Cursor

19.06%
按下载量换算1,475

Gemini CLI

10.18%
按下载量换算788

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills