SkillHub

daolv-hotel-booking

v0.1.3

Hotel discovery, shortlist comparison, and booking handoff using the ai-go-hotel MCP server (getHotelSearchTags, searchHotels, getHotelDetail). Use when users ask to find hotels, compare options by budget/location/amenities, plan city stays, family or business lodging, or complete hotel booking deci...

Sourced from ClawHub, Authored by KaiChan

Installation

Please help me install the skill `daolv-hotel-booking` from SkillHub official store. npx skills add cnChenKai/daolv-hotel-booking

Daolv Hotel Booking

Provide reliable hotel planning and booking support with structured MCP calls and decision-ready outputs.

Workflow

  1. Capture booking intent before calling tools
  2. Extract: destination, check-in date, nights, adults/children, room count, budget, purpose (business/family/leisure), required amenities, preferred/avoided brands.

  3. If key constraints are missing, ask only the minimum follow-up questions.

  4. Prime tags once per task

  5. Call ai-go-hotel.getHotelSearchTags once.
  6. Cache returned tags for the rest of the conversation.

  7. Use those tags to build hotelTags.requiredTags, preferredTags, excludedTags, and optional budget constraints.

  8. Search hotels with normalized parameters

  9. Call ai-go-hotel.searchHotels with:
  10. place
  11. placeType
  12. originQuery
  13. optional checkInDate, stayNights, adultCount, size, starRatings, hotelTags, countryCode, distanceInMeter, withHotelAmenities, language
  14. Prefer size=8-12 for first pass; narrow to top 3-5 in final output.
  15. Respect live schema behavior:
  16. checkInDate invalid/past/empty may fallback to tomorrow
  17. price is an object (use price.lowestPrice + price.currency)
  18. some fields can be null or missing
  19. placeType can be normalized from user language:
  20. 城市/city → 城市
  21. 机场/airport → 机场
  22. 景点/attraction → 景点
  23. 火车站/railway station → 火车站
  24. 地铁站/metro → 地铁站

  25. 酒店/hotel → 酒店

  26. Enrich finalists with room-level details

  27. For each shortlisted option, call ai-go-hotel.getHotelDetail (prefer hotelId when available).
  28. Pass dates with checkInDate / checkOutDate format YYYY-MM-DD.
  29. Handle fallback and edge behavior:
  30. invalid/empty dates may auto-correct
  31. failures may return plain text (not structured JSON)
  32. roomRatePlans can be very large; render only top rows by relevance/price

  33. Extract actionable room/price data, cancellation policy, breakfast inclusion, and important constraints.

  34. Return decision-ready output

  35. Always provide:
  36. Recommended option (best fit)
  37. Two alternatives
  38. Why each matches constraints
  39. Trade-offs (price vs distance vs amenities)
  40. Booking handoff steps (what user should confirm next)

Output Template

Use concise bullet format:

  • 行程信息: 目的地 / 日期 / 人数 / 预算 / 关键偏好
  • 推荐酒店（首选）
  • 酒店名
  • 预估价格（每晚 & 总价）
  • 位置与交通
  • 房型亮点
  • 取消与早餐政策
  • 推荐理由
  • 备选 1 / 备选 2（同结构）
  • 决策建议: 适合人群与风险提示
  • 下一步确认: 仅列 2-4 个必要确认项

Quality Bar

  • Prefer concrete numbers over vague wording.
  • Do not invent unavailable policies/prices.
  • If data is missing or stale, say so explicitly and suggest a refresh query.
  • Keep choices constrained: no long dump lists.
  • Avoid credential exposure or config leakage.

MCP Preset Config

  • Embedded MCP preset is included at:
  • references/mcp-client-config.json
  • It targets https://mcp.aigohotel.com/mcp using streamable_http and prefilled Authorization header.

Platform Distribution

When user asks to publish/distribute this skill, follow the checklist in: - references/distribution.md - references/promo-copy.md