find-stays
Skill1 starsChanged 4 months agoMITView on GitHub
This skill should be used whenever the user wants somewhere to stay — phrases like "find a hotel", "where should we stay", "accommodation in", "book a room", "hotel prices in", "best area to stay", or when a trip plan reaches the accommodation stage. Also use it for comparisons ("this hotel or that one"), hotel questions ("does it have a pool?") and price checks for a specific property.
In this repository15 other files it gives its agents.
- expense-reportSkill
- export-itinerarySkill
- find-activitiesSkill
- find-diningSkill
- find-flightsSkill
- fun-factsSkill
- manage-itinerarySkill
- monitor-faresSkill
- on-trip-conciergeSkill
- plan-tripSkill
- sync-calendarSkill
- traveller-profileSkill
- trip-budgetSkill
- trip-checklistsSkill
- trip-weatherSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Search live accommodation across the stay connectors and recommend where to stay.
- Distinctive: line 43
When several sources list the same property, show each price with its source.
- Distinctive: line 44
If no stay connector is available, ask the user to enable one, then fall back to web search with an "indicative prices" caveat.
- Distinctive: line 67
Follow with one clear recommendation and why, plus one budget-saver and one splurge alternative when the spread allows.
- Distinctive: line 89
Use the connectors' ratings and facts.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Find Stays
Search live accommodation across the stay connectors and recommend where to stay.
Connector strategy
Primary search — run 2–3 of these in parallel and deduplicate by property:
- Booking.com — widest inventory, filters, and property Q&A (use its property-questions tool for "does it have parking/a pool?" follow-ups).
- Expedia — second broad search with strong filters.
- Super.com — price benchmark: city-wide rates and lowest price for shortlisted hotels; often surfaces discounted rates.
- lastminute.com — check when departure is close (within ~2 weeks) or the traveller wants a deal.
Price-check and enrich the shortlist:
- DirectBooker — resolve shortlisted hotels and compare the direct-booking rate; direct rates sometimes beat aggregators.
- Tripadvisor — reviews, rankings and hotel comparisons for the shortlist; use it when the traveller asks "which is actually nicer?"
- Wyndham Hotels and Resorts — brand-direct search and details when the traveller favours Wyndham brands or has their loyalty programme.
- Otto Travel — a further live-inventory search source with the traveller's stored preferences and hotel loyalty numbers. Search only: never place a booking through it.
When several sources list the same property, show each price with its source. If no stay connector is available, ask the user to enable one, then fall back to web search with an "indicative prices" caveat.
Inputs
Pull destination, firm dates (after flights), party composition, budget
remaining and style from trip-brief.md. Derive a sensible nightly budget
from the overall ceiling minus committed costs — say what range is being
searched.
Neighbourhood first
For cities, briefly recommend 2–3 areas matched to the trip's emphasis (sights / nightlife / quiet / family) before listing properties, one line each. Search within the chosen area.
Presenting results
Comparison table of 3–6 options:
| Property | Area | Rating | Room type | Cancellation | Per night | Total | Source |
Follow with one clear recommendation and why, plus one budget-saver and one
splurge alternative when the spread allows. For business trips, rank by
distance to the meeting venue first, then workspace, Wi-Fi and breakfast;
respect the policy cap from trip-brief.md and favour chains where the
traveller holds loyalty status (e.g. Wyndham brand-direct, or programmes
stored in Otto Travel). Flag non-refundable rates, city
taxes not included, and locations far from the planned activities.
After the choice
- Save the comparison table to
options/stays-<date>.mdfor the savings summary (expense-reportskill). - Record the chosen stay (property, dates, rate, cancellation terms, link) in
trip-brief.md; log the cost inbudget.md. - Note check-in/check-out times for the itinerary's first and last days.
- Link out for the actual booking — Travel Concierge is search-only by
design and never books or takes payment in-chat. Record the details in
trip-brief.mdonce the traveller confirms they have booked.
Care points
- State totals including nights count; make clear if taxes/fees are excluded.
- Use the connectors' ratings and facts; do not invent amenities — verify via Booking.com property Q&A when the traveller asks details.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.