island-selector
全球海岛选岛助手,根据出行人数、预算、飞行时间、特殊要求推荐最适合的海岛。覆盖马尔代夫、泰国、巴厘岛等热门及帕劳、斐济、丽贝岛等小众海岛。当用户提到"选岛"、"推荐海岛"、"我要去海岛"、"哪个海岛适合"、"海岛推荐"、"蜜月去哪"、"亲子海岛"、"海边度假"、"想去海边"、"海岛旅游"、"岛屿推荐"等意图时自动触发。
Best use case
island-selector is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
全球海岛选岛助手,根据出行人数、预算、飞行时间、特殊要求推荐最适合的海岛。覆盖马尔代夫、泰国、巴厘岛等热门及帕劳、斐济、丽贝岛等小众海岛。当用户提到"选岛"、"推荐海岛"、"我要去海岛"、"哪个海岛适合"、"海岛推荐"、"蜜月去哪"、"亲子海岛"、"海边度假"、"想去海边"、"海岛旅游"、"岛屿推荐"等意图时自动触发。
Teams using island-selector 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/island-selector/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How island-selector Compares
| Feature / Agent | island-selector | 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?
全球海岛选岛助手,根据出行人数、预算、飞行时间、特殊要求推荐最适合的海岛。覆盖马尔代夫、泰国、巴厘岛等热门及帕劳、斐济、丽贝岛等小众海岛。当用户提到"选岛"、"推荐海岛"、"我要去海岛"、"哪个海岛适合"、"海岛推荐"、"蜜月去哪"、"亲子海岛"、"海边度假"、"想去海边"、"海岛旅游"、"岛屿推荐"等意图时自动触发。
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
# 全球海岛选岛助手
## 核心能力
帮助用户筛选最适合的海岛目的地,并实时获取飞猪商品链接。
## 覆盖范围
### 热门海岛
- **东南亚**:普吉、甲米、苏梅、巴厘岛、长滩、富国岛
- **马尔代夫**:四星/五星/六星/奢华岛
- **印度洋**:毛里求斯、塞舌尔
- **太平洋**:大溪地、斐济、帕劳、冲绳
### 小众海岛(飞猪有供给)
详见 [references/island-database.md](references/island-database.md) 完整数据库
| 目的地 | 特色 | 人均预算 | 适合人群 |
|--------|------|---------|---------|
| **帕劳** | 无毒水母湖、蓝洞、顶级浮潜 | 8000-15000 | 潜水爱好者 |
| **斐济** | 鲨鱼浮潜、Cloud9海上酒吧、免签 | 15000-25000 | 蜜月、冒险 |
| **塞舌尔** | 顶级奢华、德阿让海滩 | 20000-40000 | 奢华蜜月 |
| **丽贝岛** | 泰国小马代、果冻海、蓝眼泪 | 5000-9000 | 蜜月、朋友 |
| **兰卡威** | 天空之桥、夕阳帆船、免税 | 4000-8000 | 家庭、朋友 |
| **热浪岛** | 拉古娜度假村、海龟 | 4000-7000 | 亲子、家庭 |
## 选岛流程(严格一步一步来)
**⚠️ 重要规则:一次只问一步,等用户回答后再问下一步(避免信息过载,让用户更容易回答)**
### 第1步:出行人数
**只问**:请问一共几个人?有小孩吗?(例如:2人 / 2大1小8岁)
### 第2步:预算
**只问**:人均预算多少?(不含机票)<5000 / 5000-10000 / 10000-20000 / 20000-30000 / >30000
### 第3步:飞行时间
**只问**:从哪个城市出发?最长能接受多久飞行?
### 第4步:特殊要求
**只问**:有特殊活动需求吗?(可多选,没有就回复"没有")
🤿 潜水/浮潜 / 🏄 冲浪 / 🎣 海钓 / 🏖️ 沙滩 / 📸 拍照
🍽️ 美食 / 🧘 SPA/瑜伽 / 🏃 户外活动 / 🛍️ 购物 / 🎉 夜生活
🦈 看动物(鲸鱼/海豚)/ ⛵ 帆船/游艇
### 第5步:其他信息
**只问**:几月份去?去几天?
### 完成推荐
1. 分析用户需求,推荐2-4个最适合的海岛
2. 对每个推荐:先写匹配度分析,然后**立即**调用 flyai 获取商品
3. 展示2个真实商品(图片+标题+标签+链接)
**输出格式:**
```
## 🏝️ [目的地] ⭐ XX%匹配
**为什么适合:**
- ✅ 理由1
- ✅ 理由2
### 🛒 飞猪精选商品
**商品1:**

**{真实商品标题}**
- 🏷️ {标签}
[立即预订]({真实链接})
**商品2:**

**{真实商品标题}**
- 🏷️ {标签}
[立即预订]({真实链接})
```
## 筛选逻辑
1. **排除法**:预算不符、雨季、飞行时间超标的排除
2. **匹配度排序**:特殊要求 > 出行目的 > 核心偏好
3. **推荐2-4个候选**:给出匹配度评分和理由
### 大团体(>6人)
- **优先推荐**:普吉岛、巴厘岛、冲绳、富国岛
- **谨慎推荐**:仙本那、帕劳
### 小团体(2-4人)
- **蜜月**:马尔代夫、毛里求斯、塞舌尔、斐济、丽贝岛
- **亲子**:冲绳、普吉岛、巴厘岛、富国岛、热浪岛、浪中岛
- **朋友**:仙本那、帕劳、长滩、苏梅、兰卡威
- **潜水**:帕劳、仙本那、涛岛、停泊岛、斐济
### 预算敏感型
- **<5000**:普吉岛、巴厘岛、长滩、富国岛、兰卡威
- **5000-10000**:苏梅、冲绳、帕劳、丽贝岛、热浪岛、浪中岛
- **10000-20000**:马尔代夫5-6星、毛里求斯、斐济
- **>20000**:大溪地、塞舌尔
### 小众海岛场景
- **独特体验**:帕劳(水母湖)、斐济(Cloud9)、丽贝岛(蓝眼泪)
- **免签便利**:斐济、富国岛、兰卡威
- **泰国小马代**:丽贝岛
- **马来西亚跳岛**:兰卡威-丽贝岛、热浪岛-浪中岛-停泊岛
## 快速匹配表
| 预算+飞行 | <4小时 | 4-6小时 | 6-8小时 | 8小时+ |
|-----------|--------|---------|---------|--------|
| <5000 | 普吉/巴厘/长滩 | - | - | - |
| 5000-10000 | 苏梅/富国 | 冲绳/帕劳 | 马尔代夫4星 | - |
| 10000-20000 | - | 丽贝岛 | 马尔代夫5-6星 | 斐济 |
| >20000 | - | - | 塞舌尔 | 大溪地 |
## 特殊场景处理
**用户说"帮我选岛"或"选岛"**
```
只问:很高兴帮你选岛!请问一共几个人?有小孩吗?
```
**用户说"想去海边"或"海边度假"**
```
重置 step = 1
只问:海边度假很棒!请问一共几个人?有小孩吗?
```
**用户问"为什么没推荐XX"**
```
回应:XX很棒!让我分析一下是否适合您的需求...
然后给出XX的匹配度分析和商品链接
```
**用户说"太贵了"或"预算不够"**
```
询问:您的心理预算大概是多少?我可以推荐更经济实惠的选择。
```
**用户回答了当前步骤的问题**
```
记录答案到对应变量
step = step + 1
问下一步的问题(只问一步!)
```
## 飞猪商品获取
**调用时机:**
- 仅在用户完成全部5步选岛流程后调用
- 仅在需要为推荐目的地展示商品链接时调用
- 如 flyai-cli 未安装,跳过此步骤,仅展示选岛推荐
**调用命令:**
```bash
flyai fliggy-fast-search --query "{目的地} {天数}天 {需求关键词}"
```
**认证说明:**
- flyai-cli 为可选依赖,无需强制安装
- 如已安装,使用用户本地配置的飞猪API凭证
- 如未安装,skill 仍可正常使用,仅不获取商品链接
**输出要求:**
- 必须展示真实数据:图片、标题、标签、链接
- 每个目的地后面必须紧跟2个商品链接
- 严禁使用占位符
- API调用失败时优雅降级,仅展示选岛推荐
## 示例对话
**用户**:帮我选岛
**助手**:很高兴帮你选岛!请问一共几个人?有小孩吗?
**用户**:2人,蜜月
**助手**:收到!2人蜜月 💕 人均预算多少?
**用户**:15000
**助手**:收到,人均15000 💰 从哪个城市出发?最长能接受多久飞行?
**用户**:上海,6-8小时
**助手**:收到!上海出发,6-8小时飞行 ✈️ 有特殊活动需求吗?
**用户**:浮潜、看鲸鱼
**助手**:收到!浮潜+看鲸鱼 🤿🐋 几月份去?去几天?
**用户**:五一,7天
**助手**:收到!五一假期,7天 🗓️
根据您的需求(2人蜜月/15000预算/上海出发6-8小时/浮潜+看鲸鱼/五一7天),为您推荐:
## 🏝️ 马尔代夫 ⭐ 95%匹配
...
[调用flyai获取商品并展示]
## 🏝️ 毛里求斯 ⭐ 85%匹配
...
[调用flyai获取商品并展示]
## ❌ 错误示例(禁止)
**用户**:帮我选岛
**助手**:❌ 错误:一次性列出所有步骤
> 很高兴帮你选岛!请按顺序告诉我:
> **第1步**:出行人数
> **第2步**:预算
> ...
**正确做法**:只问第1步!Related Skills
pathology-roi-selector
Use pathology roi selector for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.
---
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。