agentleFS
apifyapify/awesome-skills/skills/apify-plan-travel/SKILL.md

apify-plan-travel

Skill293 starsChanged 7 days agoApache-2.0View on GitHub

This skill should be used when the user asks to "find flights", "compare flights", "analyze flight search results", "plan a flight itinerary", "plan a complete trip", "plan an event trip", or create an itinerary and budget that combines flights with lodging. It turns supplied or live Apify travel results into a defensible recommendation while preserving unresolved fare scope. Do not use it for hotel-only or lodging-only requests. It prices and advises but never books.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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
  1. Distinctive:

    Flights only: read references/flights.md.

    line 20
  2. Distinctive:

    Whole trip: when the requested output combines flights with lodging, an event plan, overnight bases, or a full trip budget, read …

    line 21
  3. Distinctive:

    Hotel or lodging only: do not use this skill. Use the selected Actor's current documentation or a dedicated lodging skill.

    line 22
  4. Distinctive:

    Use only prices whose currency, itinerary or stay coverage, and price basis are known.

    line 33
  5. Distinctive:

    Do not turn missing data into zero or infer a favorable interpretation from plausibility.

    line 34
  6. Distinctive:

    Keep ground transport, fuel, parking, meals, taxes, fees, and tickets outside the sourced subtotal unless a cited source priced them for …

    line 36
  7. Distinctive:

    Do not infer award availability, points prices, program benefits, or alliance and brand membership from cash results.

    line 37
  8. Distinctive:

    Never book or imply that an option is held.

    line 38

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan flights or a complete trip with Apify

Turn travel data into a decision rather than a list of results. Preserve the requested scope, distinguish sourced prices from estimates, and keep unresolved price or itinerary coverage explicit.

Disclosure: The skill author also maintains the two paid Apify Actors used here.

Route the request

  • Flights only: read references/flights.md. This includes flight-only round-trip, multi-city, and open-jaw requests. Do not load the hotel or whole-trip references merely because the flight has several segments.
  • Whole trip: when the requested output combines flights with lodging, an event plan, overnight bases, or a full trip budget, read references/whole-trip.md, then references/flights.md and references/hotels.md.
  • Hotel or lodging only: do not use this skill. Use the selected Actor's current documentation or a dedicated lodging skill.
  • Supplied results: analyze usable supplied Actor output without rerunning the Actor unless fresher data is requested or required.

Data sources and prerequisites

For live flight searches, use Google Flights Data Scraper. For lodging within a whole-trip plan, use Google Hotels Search Scraper. Access them through Apify MCP or another available Apify interface.

Before a live call, inspect the Actor's current README, input schema, pricing, and returned payload. Estimate the intended run before starting paid work. Keep optional billable features off unless the user needs them. Treat the Actor documentation as the source for current inputs and operation; use this skill for the judgment that the documentation does not provide.

Shared decision rules

  1. Use only prices whose currency, itinerary or stay coverage, and price basis are known. Keep incompatible or ambiguous amounts separate.
  2. Do not turn missing data into zero or infer a favorable interpretation from plausibility.
  3. Rank against the user's priorities. When priorities are unstated, expose the main trade-offs instead of inventing a universal score.
  4. Keep ground transport, fuel, parking, meals, taxes, fees, and tickets outside the sourced subtotal unless a cited source priced them for this plan.
  5. Do not infer award availability, points prices, program benefits, or alliance and brand membership from cash results. Verify current membership from a primary source when it affects the recommendation.
  6. Never book or imply that an option is held. Warn that prices, schedules, and availability must be verified before booking.

Deliverable

Lead with the recommended flight or trip shape and the evidence behind it. Follow with compact alternatives, meaningful trade-offs, evidence locators or returned booking URLs, price-basis caveats, and a verify-before-booking warning. For a whole trip, include a day-by-day outline, a sourced flight-and-lodging subtotal, and separately labelled estimates or unknowns.

Example requests

Supported:

  • "Compare these supplied flight-search results for Prague to Tokyo and explain the cheapest and best-convenience options."
  • "Plan an event trip from Boston to Austin with flights, overnight bases, a day-by-day itinerary, and a clearly sourced budget."

Boundary:

  • "Find me a hotel in Vienna for Friday night." This is lodging-only, so do not activate this skill.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.