find-dining
Skill1 starsChanged 4 months agoMITView on GitHub
This skill should be used whenever food is the question — phrases like "where should we eat", "book a table", "restaurant near", "best food in", "we're hungry", "order food to the hotel", "dinner reservation", "is this restaurant good", whether while planning the trip or in the middle of it.
In this repository15 other files it gives its agents.
- expense-reportSkill
- export-itinerarySkill
- find-activitiesSkill
- find-flightsSkill
- find-staysSkill
- fun-factsSkill
- manage-itinerarySkill
- monitor-faresSkill
- on-trip-conciergeSkill
- plan-tripSkill
- sync-calendarSkill
- traveller-profileSkill
- trip-budgetSkill
- trip-checklistsSkill
- trip-weatherSkill
The file
Files
Find Dining
Handle everything food: recommendations, table reservations and delivery to the door — tuned to the trip's tastes, location and budget.
Connector strategy
- Resy — restaurant discovery and table reservations. First stop for "book a table" and for finding notable restaurants with real availability for the party size, date and time.
- Tripadvisor — reviews and rankings to sense-check or discover restaurants, and to answer "is it any good?"
- Uber Eats — delivery: search restaurants, cuisines and menu items deliverable to the stay. The answer for tired-after-a-long-day evenings, room picnics and "we just landed and everything nearby is shut".
- Complement with web search for local institutions, markets and street food that no platform lists.
Inputs
Pull dietary needs from the traveller profile (treat these as hard
constraints, never suggestions), cuisine loves/avoids and budget style from
trip-brief.md, and location plus timing from today's itinerary.md entry —
recommend near where the traveller will actually be at meal time, not near
the hotel by default.
Presenting options
Two or three options, each one line: name — cuisine and signature dish — distance from where they'll be — price band — why this one. For reservations, state real availability from Resy before recommending a time.
Handing off
Travel Concierge is search-only by design — it checks availability and menus, then hands the traveller to the provider to complete things:
- Reserve: confirm party size, date and time, verify real availability
via Resy, then link the traveller to Resy to place the reservation. Once
they confirm it is booked, mark it in
itinerary.mdwith 🎟 booked. - Deliver: find what is deliverable to the stay via Uber Eats (dishes, prices, timings), then link to Uber Eats to place the order.
- Log notable meal spends against the food estimate in
budget.md.
Care points
- Dietary requirements are non-negotiable filters — verify the venue can cater to them rather than assuming.
- Mention dress codes or long waits when the source flags them.
- Client or team dinners: private-dining or quieter venues suited to conversation, near the venue or the client's side of town; confirm the business occasion so Resy notes it, and log the spend itemised for expenses.
- For planning-stage requests, pencil suggestions into the itinerary as 💡 rather than booking weeks of dinners nobody asked for.
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.

