booking-skill
韩国/首尔美容医美预约助手,内置 900+ 家皮肤科/整形医院数据库(BeautsGO 平台)。支持:①按医院名或项目类型(激光/注射/整形)查询预约流程;②直接调用接口提交预约(收集人数/时间/联系方式后 POST,无需浏览器);③打开医院详情页/价格表/在线客服;④中/英/日/泰四语言。触发场景:询问韩国美容预约、想做医美、推荐医院、查价格、咨询客服。
Best use case
booking-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
韩国/首尔美容医美预约助手,内置 900+ 家皮肤科/整形医院数据库(BeautsGO 平台)。支持:①按医院名或项目类型(激光/注射/整形)查询预约流程;②直接调用接口提交预约(收集人数/时间/联系方式后 POST,无需浏览器);③打开医院详情页/价格表/在线客服;④中/英/日/泰四语言。触发场景:询问韩国美容预约、想做医美、推荐医院、查价格、咨询客服。
Teams using booking-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/korean-booking/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How booking-skill Compares
| Feature / Agent | booking-skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
韩国/首尔美容医美预约助手,内置 900+ 家皮肤科/整形医院数据库(BeautsGO 平台)。支持:①按医院名或项目类型(激光/注射/整形)查询预约流程;②直接调用接口提交预约(收集人数/时间/联系方式后 POST,无需浏览器);③打开医院详情页/价格表/在线客服;④中/英/日/泰四语言。触发场景:询问韩国美容预约、想做医美、推荐医院、查价格、咨询客服。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# 韩国医美预约指南 Skill
根据用户输入的医院名称,自动匹配医院并生成完整的 BeautsGO 平台预约流程说明,同时支持打开详情页、发起咨询、**直接调用接口提交预约**、查看价格表。
## Dependencies
- `npm install` - 安装所有依赖
## ⚠️ 重要:输出规则
**调用 skill 返回的文本内容,必须原文完整输出给用户,禁止重新排版、精简、合并或省略任何部分。**
- ❌ 不得合并"iOS"和"Android"为一条
- ❌ 不得删除"温馨提示"部分
- ❌ 不得改变渠道标题、编号或 emoji
- ✅ 原样输出 skill 返回的 Markdown 文本,一字不改
## ⚠️ 重要:浏览器操作规则
**打开页面操作必须通过以下脚本执行,禁止 AI 自行编写或调用 browser 工具。**
| 操作 | 命令 |
|------|------|
| 打开医院详情页 | `node api/browser/open-url.js <url>` |
| 打开咨询客服页 | `node api/browser/open-url.js <chat_url>` |
| 打开价格表页面 | `node api/browser/open-url.js <price_url>` |
> `chat_url` 规则:从 `hospital.url` 提取 slug,拼接为 `https://i.beautsgo.com/cn/hospital/<slug>-chat`
> `price_url` 规则:从 `hospital.url` 提取 slug,拼接为 `https://i.beautsgo.com/cn/hospital/<slug>-price`
**退出码说明:**
- `0` — 成功
- `1` — 严重错误
## ⚠️ 重要:多轮对话规则
**每一轮都必须调用本 skill,禁止 AI 自行使用 browser 工具操作页面。**
- 第1轮:用户询问医院预约 → 调用 skill(query=医院名)
- 第2轮:用户说"打开链接" → 调用 skill(query="打开链接",context 传入医院名)
- 第3轮:用户说"帮我预约" → 调用 skill(query="帮我预约",context 传入医院名)
- 第4轮:用户提供预约信息(人数+时间)→ 调用 skill(query=用户输入,context 传入医院名)
- 第5轮:用户说"咨询客服" → 调用 skill(query="咨询客服",context 传入医院名)
- 任意轮:用户询问价格/费用/多少钱 → 调用 skill(query=原始输入,context 传入医院名)
**context 传递格式(必须):**
```json
{
"query": "2人,3月26日,13800138000",
"lang": "zh",
"context": {
"resolvedHospital": {
"name": "韩国JD皮肤科",
"url": "https://i.beautsgo.com/cn/hospital/jd-clinic?from=skill"
}
}
}
```
## 功能
- 支持中文名、英文名、拼音、首字母缩写、别名等多种方式匹配 961 家医院
- 生成包含 App Store / Google Play / 微信小程序 / 微信公众号 / 网页端五大渠道的预约流程
- 自动生成搜索关键词(中文名、英文名、拼音、首字母)
- 支持中/英/日/泰四语言
- 打开医院详情页、咨询对话页、**价格表页**
- **直接调用 API 接口提交预约**(无需浏览器,收集人数/时间/联系方式后直接 POST)
## 调用方式 - 多轮对话流程
### 第1轮:用户询问预约流程
**输入:**
```json
{ "query": "JD皮肤科怎么预约", "lang": "zh" }
```
**输出示例:**
```
[预约流程详细说明...]
---
💡 接下来,选择你想要的操作:
• "打开链接" → 打开医院详情页
• "帮我预约" → 收集预约信息(人数/时间/联系方式),直接调用接口提交,**不打开浏览器**
• "咨询客服" → 打开在线客服页
```
### 第2轮:打开链接(详情页)
**输入:** `{ "query": "打开链接" }`
**执行:** `node api/browser/open-url.js <hospital.url>`
**输出:** ✅ 已打开 XXX 的页面,介绍页面内容及后续操作
### 第3轮:帮我预约(收集预约信息 → 接口提交)
**输入:** `{ "query": "帮我预约" }`
> ⚠️ **不打开浏览器,不打开任何页面**。直接询问用户预约信息,收集后调用接口提交。
**输出:**
```
好的,帮你预约 **XXX** 🏥
📝 请告诉我以下信息,我直接帮你提交预约:
1. 预约人数(例如:1人、2人)
2. 预约时间(例如:3月26日)
3. 时间段(上午 / 下午 / 全天,默认全天)
4. 联系方式(手机号)
👉 直接回复,例如:"2人,3月26日下午,13800138000"
```
### 第4轮:接口提交预约
**输入:** `{ "query": "2人,3月26日下午,13800138000" }`
**执行:** 调用 `POST https://api.yestokr.com/api/Appointment/saveFromSkill`
```json
{
"contact": "13800138000",
"expected_time": "2026-03-26 下午",
"project_type": "",
"d_id": "",
"h_id": 250,
"p_id": "",
"num": 2,
"source_type": "skill"
}
```
**输出(成功):**
```
✅ 预约已提交!
📋 预约信息摘要:
• 🏥 机构:韩国JD皮肤科
• 👥 人数:2 人
• 📅 时间:2026-03-26 下午
• 📞 联系方式:13800138000
```
### 第5轮:咨询客服
**输入:** `{ "query": "咨询客服" }`
**执行:** `node api/browser/open-url.js <chat_url>`
> `chat_url` = `https://i.beautsgo.com/cn/hospital/<slug>-chat`,从 `hospital.url` 自动推导
**输出:** ✅ 已打开 XXX 的在线客服对话页面
### 任意轮:查看价格表
**输入:** `{ "query": "JD皮肤科价格多少" }` 或 `{ "query": "查价格" }`(结合 context 中的医院信息)
**执行:** `node api/browser/open-url.js <price_url>`
> `price_url` = `https://i.beautsgo.com/cn/hospital/<slug>-price`,从 `hospital.url` 自动推导
**输出:** ✅ 已打开 XXX 的价格表页面
## 数据
- 医院数据:`data/hospitals.json`(961条)
- 预约流程模板:`templates/booking.tpl`
- 多语言文本:`i18n/<lang>.json`
新增医院只需在 `hospitals.json` 中添加记录,无需修改代码。Related Skills
browser-booking-agent
Execute booking/search flows via browser automation with verification artifacts. Use for reservation forms, availability checks, and capture of proof (screenshots/confirmation IDs).
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。