← Back to Skills Marketplace
longcreat

hotel-recommendation

by zlon · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
318
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install hotel-recommendation
Description
使用 RollingGo CLI 查询酒店信息、筛选结果、读取酒店标签和获取房型价格。当用户需要按目的地 / 日期 / 星级 / 预算 / 标签 / 距离搜索酒店、查看酒店详情与房型报价,或读取酒店标签库时触发本技能。触发短语——"搜索酒店"、"查酒店"、"酒店详情"、"房型价格"、"酒店标签"、"附近酒店"、"...
README (SKILL.md)

\r \r

RollingGo 酒店 CLI\r

\r

适用范围\r

\r ✅ 在以下情况使用本技能:\r

  • 查找候选酒店: 用户需要按城市、地标、机场或具体地址搜索附近酒店(例如:“查找东京迪士尼附近的酒店”)。\r
  • 多条件精准筛选: 用户需要在搜索时结合自然语言意图,并严格限制入离日期、入住人数、预算上限、星级区间或距离范围。\r
  • 基于标签与品牌匹配: 用户想寻找包含特定设施或属于特定品牌的酒店(如“亲子友好”、“包含早餐”、“万豪”等),技能可先查询标签库以进行精准筛选。\r
  • 查询房型与实时报价: 用户想深入了解某家具体酒店(通过 hotelId)的可用房型、实时价格、退款政策或具体配置。\r
  • 酒店对比与评估: 用户需要基于真实的结构化数据和当前报价,在多个候选酒店中进行对比分析。\r
  • 酒店预订: 用户选定酒店想要完成预订时。可提取并提供结果中的预订 URL 或酒店主页链接,引导用户直接点击完成购买。\r \r ❌ 以下情况不适用:\r
  • 用户询问非酒店类的旅游预订业务(如机票、火车票、接送机、租车等)。\r \r

API Key\r

\r 解析顺序:--api-key 参数 → AIGOHOTEL_API_KEY 环境变量。\r \r 还没有 Key?前往申请:https://mcp.agentichotel.cn/apply\r \r

运行环境\r

\r 根据用户环境选择,加载对应的参考文件,并在整个会话中保持一致。\r \r

  • npmnpx、Node 或无明确偏好: 加载 references/rollinggo-npx.md\r
  • uvuvx、PyPI 或 Python: 加载 references/rollinggo-uv.md\r
  • 一致性检查或对比: 同时加载两个参考文件\r \r 未明确指定时默认使用 npm/npx(跨环境兼容性更好)。\r \r

主要工作流\r

\r 除非用户已经把问题限定在某个具体步骤,否则按顺序执行:\r \r

  1. 明确需求:目的地、日期、晚数、入住人数、预算、星级、标签、距离\r
  2. 如果需要标签筛选 → 先执行 hotel-tags 获取有效标签字符串\r
  3. 执行 search-hotels → 解析 JSON → 提取 hotelId\r
  4. 执行 hotel-detail --hotel-id \x3Cid> 查询房型和价格\r
  5. 如果结果不理想 → 放宽筛选条件后重新搜索\r \r

常用命令速查\r

\r

# 获取标签库\r
rollinggo hotel-tags\r
\r
# 搜索酒店(最少必填参数)\r
rollinggo search-hotels \\r
  --origin-query "\x3C用户的自然语言描述>" \\r
  --place "\x3C目的地>" \\r
  --place-type "\x3C查看 --help 获取合法值>"\r
\r
# 查询酒店详情与价格\r
rollinggo hotel-detail \\r
  --hotel-id \x3Cid> \\r
  --check-in-date YYYY-MM-DD \\r
  --check-out-date YYYY-MM-DD \\r
  --adult-count 2 --room-count 1\r
\r
# 查看所有可用参数\r
rollinggo search-hotels --help\r
rollinggo hotel-detail --help\r
```\r
\r
## 关键规则\r
\r
- `--place-type` 必须使用 `rollinggo search-hotels --help` 里显示的精确值\r
- `--star-ratings` 格式:`最小值,最大值`,如 `4.0,5.0`\r
- `--format table` **只允许**用于 `search-hotels`;`hotel-detail` 和 `hotel-tags` 会拒绝该参数\r
- `--child-count` 的数量必须与 `--child-age` 参数的个数一致\r
- `--check-out-date` 必须晚于 `--check-in-date`\r
- 有 `hotelId` 时优先使用 `--hotel-id`,不要依赖 `--name`\r
\r
## 输出说明\r
\r
- stdout → 结果数据(默认 JSON)\r
- stderr → 仅错误信息\r
- 退出码 `0` 成功 · `1` HTTP/网络失败 · `2` CLI 参数校验失败\r
- 结果中包含预订 URL 与酒店详情页链接,可供下游直接使用\r
\r
## 无结果时的放宽策略\r
\r
按顺序尝试:移除 `--star-ratings` → 增大 `--size` → 增大 `--distance-in-meter` → 移除标签筛选 → 放宽日期或预算\r
Usage Guidance
This skill appears coherent: it needs the RollingGo CLI and one API key to perform hotel searches. Before installing or providing your API key: 1) verify the rollinggo package source (npm or uv) and the provider (mcp.agentichotel.cn) so you trust the code you install; prefer using npx/uvx for one-off runs to avoid global installs if unsure; 2) only supply an API key scoped to this service and consider using a dedicated key with limited privileges; 3) be aware the CLI returns booking URLs—validate links before clicking and do not paste your API key into third-party places; 4) if you need higher assurance, inspect the rollinggo package source code yourself or contact the provider for provenance. Installing the package from a registry carries typical package-install risk but is expected for this skill's purpose.
Capability Analysis
Type: OpenClaw Skill Name: hotel-recommendation Version: 1.0.0 The skill bundle provides a legitimate interface for the 'rollinggo' hotel search CLI, supporting both Node.js (npm/npx) and Python (uv/uvx) environments. It facilitates hotel searches, detail retrieval, and tag management via the 'agentichotel.cn' service. The instructions are well-structured, providing clear guidance for the AI agent on parameter usage and error handling, and the required permissions (environment variables and binary execution) are strictly aligned with the stated purpose. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description (hotel search, filters, tags, room prices) align with required artifacts: a RollingGo CLI binary (or npm/uv installers) and a single API key (AIGOHOTEL_API_KEY). Requesting the CLI and API key is expected for this functionality.
Instruction Scope
SKILL.md only instructs running the rollinggo CLI commands (search-hotels, hotel-detail, hotel-tags), parsing JSON output, and using an API key via flag or env var. It does not ask to read arbitrary system files, unrelated environment variables, or to transmit data to unknown endpoints beyond the service implied by the CLI. It does note that results include booking URLs which users may follow.
Install Mechanism
Installers are npm (rollinggo) and uv/uvx packaging for the same rollinggo tool. npm/uv installs are a reasonable delivery method for a CLI but increase trust requirements: the package source (npm registry or uv package index) should be verified before install. No direct downloads from unknown URLs are present.
Credentials
Only one environment variable is required (AIGOHOTEL_API_KEY) and it is the declared primary credential. That is proportional to a CLI that authenticates to a hotel search API.
Persistence & Privilege
Skill is not always-enabled and does not request system config paths or elevated persistence. It uses the normal autonomous-invocation default but does not demand permanent presence or modify other skills.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install hotel-recommendation
  3. After installation, invoke the skill by name or use /hotel-recommendation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the hotel-recommendation skill. - Enables hotel search, filtering, and detail retrieval via RollingGo CLI, including room prices and hotel tags. - Supports complex queries: search by destination, date, star rating, budget, tag, or distance. - Provides hotel details and booking links; supports comparison and structured data analysis. - Handles environment compatibility, API key configuration, and reference file selection automatically. - Includes clear usage scope, command guide, and fallback strategies for no-result scenarios.
Metadata
Slug hotel-recommendation
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is hotel-recommendation?

使用 RollingGo CLI 查询酒店信息、筛选结果、读取酒店标签和获取房型价格。当用户需要按目的地 / 日期 / 星级 / 预算 / 标签 / 距离搜索酒店、查看酒店详情与房型报价,或读取酒店标签库时触发本技能。触发短语——"搜索酒店"、"查酒店"、"酒店详情"、"房型价格"、"酒店标签"、"附近酒店"、"... It is an AI Agent Skill for Claude Code / OpenClaw, with 318 downloads so far.

How do I install hotel-recommendation?

Run "/install hotel-recommendation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is hotel-recommendation free?

Yes, hotel-recommendation is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does hotel-recommendation support?

hotel-recommendation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created hotel-recommendation?

It is built and maintained by zlon (@longcreat); the current version is v1.0.0.

💬 Comments