← 返回 Skills 市场
gaogao605

hotel-best-price

作者 fenbeitong-trip · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
93
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install hotel-best-price
功能描述
酒店比价助手,对比携程、美团、同程、去哪儿、华住会、锦江会、飞猪等OTA平台相同酒店房型价格,给出最优推荐。Invoke when user wants to compare hotel prices across multiple OTA platforms or find the best hotel deal.
使用说明 (SKILL.md)

酒店比价助手 (fb-hotel-comparison-skill)

技能描述

酒店比价助手,实时对比携程、美团、同程、去哪儿、华住会、锦江会、飞猪等OTA平台相同酒店下所有房型产品的报价,通过智能算法给出最优推荐。


⚠️ 【重要约束】

  • 必须调用各OTA平台的API获取真实价格数据
  • 禁止自行编造价格信息
  • 接口返回什么数据就展示什么,不要修改
  • 比价结果需标明数据来源和采集时间

技能概述

基于多平台OTA API开发的酒店比价技能,支持:

  • 多平台酒店价格实时抓取
  • 同酒店同房型跨平台价格对比
  • 智能最优推荐算法(综合考虑价格、取消政策、早餐、积分等)
  • 价格趋势分析和预订建议

技能能力

核心能力

  1. 多平台价格抓取:同时查询携程、美团、同程、去哪儿、华住会、锦江会、飞猪等平台
  2. 智能比价:同酒店同房型跨平台价格对比
  3. 最优推荐:基于价格、政策、权益综合评分推荐最优选择
  4. 价格监控:支持设置价格提醒,降价通知

触发条件

  1. 酒店比价:当用户输入「比价/对比/哪个便宜/最优惠」+ 酒店名称时

    • 调用多平台API获取价格
    • 展示各平台同房型价格对比表格
    • 给出最优推荐
  2. 展示格式示例

    🏨 桔子酒店(北京燕莎三元桥店) - 多平台比价
    📅 入住:3月15日 → 退房:3月16日
    🛏️ 房型:高级大床房
    
    | 平台 | 价格 | 早餐 | 取消政策 | 会员权益 | 推荐指数 |
    |:---:|---:|:---:|:---|:---|:---:|
    | 🥇 携程 | ¥483 | 含早 | 限时取消 | 积分+早餐 | ⭐⭐⭐⭐⭐ |
    | 美团 | ¥526 | 无早 | 不可取消 | 无 | ⭐⭐⭐ |
    | 同程 | ¥498 | 含早 | 限时取消 | 积分 | ⭐⭐⭐⭐ |
    | 飞猪 | ¥510 | 无早 | 限时取消 | 积分 | ⭐⭐⭐⭐ |
    
    💡 最优推荐:携程 ¥483(含早+限时取消+积分)
    🔗 [立即预订-携程](https://...)
    

对接平台

支持OTA平台

平台 标识 特点
携程 ctrip 价格优势明显,会员权益丰富
美团 meituan 本地生活场景多,优惠券多
同程 tongcheng 微信生态,返现活动多
去哪儿 qunar 低价策略,学生优惠
华住会 huazhu 自有会员体系,积分价值高
锦江会 jinjiang 会员折扣力度大
飞猪 fliggy 阿里生态,信用住免押金

核心接口列表

一、查询类接口

接口名称 核心用途 必选参数
search_hotel_prices 多平台酒店价格查询 hotel_name, city, check_in, check_out, platforms
get_price_trend 价格趋势分析 hotel_id, room_type, days
get_best_deal 获取最优推荐 hotel_name, city, check_in, check_out

二、数据类接口

接口名称 核心用途 说明
compare_platforms 多平台对比 返回结构化对比数据
calculate_recommendation 计算推荐分数 基于多维度算法评分

推荐算法

评分维度

维度 权重 说明
价格 40% 基础价格对比
取消政策 20% 限时取消 > 不可取消
早餐权益 15% 含早 > 无早
会员权益 15% 积分、升级等
平台信誉 10% 服务保障、退改政策

推荐指数

  • ⭐⭐⭐⭐⭐ (90-100分):强烈推荐,综合最优
  • ⭐⭐⭐⭐ (75-89分):推荐,某方面突出
  • ⭐⭐⭐ (60-74分):一般,可考虑
  • ⭐⭐ (40-59分):不推荐
  • ⭐ (0-39分):强烈不推荐

响应规则

成功响应

{
  "code": 0,
  "msg": "success",
  "data": {
    "hotel_name": "桔子酒店(北京燕莎三元桥店)",
    "check_in": "2026-03-15",
    "check_out": "2026-03-16",
    "room_type": "高级大床房",
    "platforms": [
      {
        "platform": "携程",
        "price": 483,
        "breakfast": "含早",
        "cancel_policy": "限时取消",
        "benefits": ["积分", "早餐"],
        "score": 95,
        "recommendation": "⭐⭐⭐⭐⭐"
      }
    ],
    "best_deal": {
      "platform": "携程",
      "price": 483,
      "savings": 43,
      "reason": "价格最低且含早餐"
    }
  }
}

失败响应

{
  "code": 500,
  "msg": "错误信息",
  "data": null
}
安全使用建议
This skill's description promises live multi-OTA price comparisons, but the included Python code contains TODOs and placeholder fetch methods that return no data and the package requests no API credentials. Before installing or running: (1) confirm how OTA APIs are authenticated and where API keys/tokens should be configured (the skill currently declares none); (2) inspect and complete the platform-specific _fetch_* implementations or obtain a vetted implementation from the author; (3) ensure required Python dependencies (requests, etc.) are installed from trusted sources; (4) run in a safe/test environment first to observe network calls and verify no unexpected external endpoints are contacted; (5) ask the publisher for a clear integration/credential handling document and for the expected behavior when APIs are unavailable. If you need the advertised functionality but cannot trust or complete the missing integrations, do not rely on this skill for production use.
功能分析
Type: OpenClaw Skill Name: hotel-best-price Version: 1.0.0 The skill bundle is a legitimate template for a hotel price comparison tool across various Chinese OTA platforms. The code in `scripts/hotel_comparison_api.py` and `scripts/openai_adapter.py` implements scoring logic and OpenAI function-calling wrappers, though the actual data-fetching methods are currently placeholders (TODOs). No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The skill's name/description promise real-time price comparisons across multiple OTAs and the SKILL.md states '必须调用各OTA平台的API' (must call OTA APIs). However, the implementation has placeholder fetch methods (each _fetch_* returns [] with TODO comments) and the package does not declare any API keys/credentials or guidance for authenticating to OTA APIs. This is a functional mismatch: to do what it claims it would normally need platform credentials and concrete API implementations.
Instruction Scope
SKILL.md instructs the agent to call OTA APIs, not fabricate prices, and show data sources/timestamps — that scope is appropriately narrow. But the instructions do not explain how to obtain or supply OTA credentials, nor do they contain fallback behavior. The runtime Python adapter expects to call local functions (hotel_comparison_api) but those fetch functions are unimplemented; this creates ambiguity about what the skill will actually do at runtime and may lead to silent failures or unexpected behavior.
Install Mechanism
There is no install spec (instruction-only), which is low risk. However, the skill includes Python scripts that rely on third-party packages (requests) but the skill does not declare dependency installation steps. The absence of declared dependencies may cause runtime failures or prompt ad-hoc installs by users/agents. No external download URLs or unusual installers are present.
Credentials
The registry metadata and SKILL.md declare no required environment variables or credentials. That contradicts the stated requirement to call multiple OTA APIs: those integrations commonly require API keys, tokens, or other credentials. Asking for no credentials while promising live API access is disproportionate and suggests incomplete implementation or missing secret-handling design.
Persistence & Privilege
Skill does not request persistent presence (always=false), does not declare config paths, and does not attempt to modify other skills or system settings. Autonomous invocation is allowed (platform default), which is expected for skills.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install hotel-best-price
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /hotel-best-price 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the 酒店比价助手 (hotel best price comparison skill). - Supports real-time hotel price comparison across Ctrip, Meituan, Tongcheng, Qunar, Huazhu, Jinjiang, and Fliggy platforms. - Provides intelligent recommendations based on price, cancellation policy, breakfast, member benefits, and platform reputation. - Displays platform sources, collection time, and detailed comparison tables. - Includes price monitoring, trend analysis, and best deal suggestions.
元数据
Slug hotel-best-price
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

hotel-best-price 是什么?

酒店比价助手,对比携程、美团、同程、去哪儿、华住会、锦江会、飞猪等OTA平台相同酒店房型价格,给出最优推荐。Invoke when user wants to compare hotel prices across multiple OTA platforms or find the best hotel deal. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 93 次。

如何安装 hotel-best-price?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install hotel-best-price」即可一键安装,无需额外配置。

hotel-best-price 是免费的吗?

是的,hotel-best-price 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

hotel-best-price 支持哪些平台?

hotel-best-price 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 hotel-best-price?

由 fenbeitong-trip(@gaogao605)开发并维护,当前版本 v1.0.0。

💬 留言讨论