home / skills / openclaw / skills / booking
This skill helps you compare real-time hotel pricing across platforms and automatically book accommodations based on your preferences.
npx playbooks add skill openclaw/skills --skill bookingReview the files below or copy the command above to add this skill to your agents.
---
name: Booking
slug: booking
version: 1.0.0
description: Search, compare, and book accommodation across platforms with real pricing, user preferences, and end-to-end execution.
metadata: {"clawdbot":{"emoji":"🏨","requires":{"bins":[]},"os":["linux","darwin","win32"]}}
---
## Quick Reference
| Topic | File |
|-------|------|
| Search, compare, shortlist | `search.md` |
| Platforms, APIs, data sources | `platforms.md` |
| Total cost calculation | `pricing.md` |
## User Preferences
Store preferences in `~/booking/memory.md`. Load on activation.
```
~/booking/
├── memory.md # Traveler type, budget, preferences
├── history.md # Past bookings, liked properties
└── alerts.md # Active price tracking
```
## Critical Rules — Never Skip
1. **Calculate TOTAL cost always** — base price + cleaning fee + service fee + tourist tax + any extras. Never quote per-night without fees
2. **Compare 3+ platforms** before recommending — Booking.com, Airbnb, direct hotel, local platforms (Hostelworld, HousingAnywhere, etc.)
3. **Verify real-time data** — don't recommend from training data. Check live availability and current prices
4. **Ask about purpose** — tourist, business, family, remote work, budget. Needs differ completely
5. **Surface deal-breakers early** — non-refundable, no A/C, far from center, negative review patterns, wifi issues for workers
6. **Shortlist, don't overwhelm** — 3-5 curated options with trade-offs, not 20 links to review
7. **Execute when asked** — "book this" means book, not "here's how to book"
8. **Check cancellation policy** — state deadline clearly before any booking
## Traveler-Specific Traps
| Type | Common Model Failure |
|------|---------------------|
| Casual | Ignoring stated budget, recommending based on popularity not fit |
| Business | Missing corporate rates, not understanding loyalty program math |
| Family | Treating "2 bedrooms" as sufficient without checking bed config, missing safety issues |
| Backpacker | Recommending mid-range, not calculating fees, missing hostel direct pricing |
| Nomad | Multiplying nightly×30 instead of real monthly rate, trusting "wifi included" |
## Before Recommending Any Property
- [ ] Total price calculated with ALL fees
- [ ] Cancellation policy stated
- [ ] Location context (walking time to center/meeting/beach)
- [ ] Review patterns checked (cleanliness, noise, wifi for workers, family-friendliness)
- [ ] Deal-breakers surfaced if any
This skill helps you search, compare, shortlist, and book accommodation across multiple platforms using real-time pricing and user preferences. It always computes the total trip cost including fees, taxes, and extras, and surfaces deal-breakers early. The skill can execute bookings end-to-end when you confirm.
On activation it loads stored traveler preferences and history, then queries three or more platforms (e.g., Booking.com, Airbnb, direct hotel and local sites) for live availability and fares. It calculates total cost for each option, checks cancellation rules and review patterns, and returns a curated shortlist of 3–5 properties with clear trade-offs. When you instruct “book this,” it performs the booking and updates memory and history.
How does the skill ensure prices are current?
It queries live platform APIs and checks availability and pricing in real time rather than relying on training data.
Will you ever recommend more than five options?
No—recommendations are limited to 3–5 curated choices to avoid overwhelming users; additional options are available on request.