Aerobase Activities

Discover Viator tours, attractions, and activities near airports with ratings, reviews, and booking

Security Scan

The skill's behavior mostly matches its advertised purpose, but the runtime instructions reference an undeclared external scraping proxy (SCRAPLING_URL) and other external browsing/affiliate flows without declaring corresponding credentials or a trustworthy source, which is inconsistent and worth clarifying before installing.

Purpose & Capability

Name/description (discover tours/activities near airports) align with the listed API endpoints and the Aerobase Tours API as the primary data source. Requested primary credential AEROBASE_API_KEY is plausible and proportional for an API-backed discovery skill.

Instruction Scope

SKILL.md instructs the agent to call Aerobase endpoints and to use a browser/scraping fallback (Scrapling) for niche cases. It includes a concrete web_fetch snippet using a {SCRAPLING_URL} placeholder, but SCRAPLING_URL is not declared in requires.env. The instructions authorize web scraping TripAdvisor and performing Google searches for price comparisons — these are reasonable for discovery but expand the runtime network surface and require a configured proxy/credential that is not documented.

Install Mechanism

Instruction-only skill with no install spec or code files. That minimizes filesystem/write risk; nothing will be installed by default.

Credentials

Only AEROBASE_API_KEY is declared (which is appropriate). However, the SKILL.md references SCRAPLING_URL (and implies use of browser/search and possibly third-party services like Scrapling or Google) without declaring required environment variables or credentials for those services. Missing declarations are an incoherence: the runtime needs at least a scrapling proxy URL/credential to perform the provided web_fetch example.

Persistence & Privilege

always is false and the skill does not request persistent system-wide privileges. Model invocation is allowed (default) but that is normal; nothing in the skill requests elevated or permanent presence.

What to consider before installing

This skill largely does what its name says and is low-risk from an install perspective (no code or installers). Before installing, verify the following: (1) Who runs the Aerobase API (no homepage/source is provided) and whether you trust that provider to hold your AEROBASE_API_KEY. (2) The SKILL.md uses a Scrapling proxy placeholder ({SCRAPLING_URL}) but does not declare that environment variable — ask the author how Scrapling is provided and whether credentials or a proxy URL are required. (3) The skill will perform occasional web browsing/scraping (TripAdvisor, Google) for edge cases — confirm you are comfortable with the agent sending queries to those services and potentially transmitting user-supplied trip data to an external scraping proxy. (4) Confirm rate limits and that the skill will not pre-fetch data (the doc says to avoid pre-fetching, which is good). If the author can provide a documented source/homepage for Aerobase, add SCRAPLING_URL (or remove the Scrapling requirement) to the declared env vars, and clarify what data is sent to external services, my confidence would increase and the incoherence would be resolved.

Tours, Attractions & Layover Activities

Match activity intensity to jetlag recovery stage. Days 1-2 jetlagged = low-energy activities near hotel. Day 3+ adapted = major sites.

Search

• GET /api/airports/{code}/attractions — attractions near airport
• GET /api/airports/{code}/tours — curated tours by airport IATA
• GET /api/airports/{code}/activities — activities (adventure, wellness, classes)
• Layover tours: max 240 min, rating >= 4.0

Layover Intelligence

GET /api/v1/layovers/{code} — comprehensive layover data including:

• layoverGuides — time-segmented itineraries (4h, 8h, 24h) with activities
• dayUseHotels — nearby hotels bookable by the hour for layover rest
• airportSpas — spa and wellness services inside the airport
• connection — MCT and average wait times (feasibility check before suggesting off-airport activities)
• delays — historical delay stats (warn if airport has high delay rates)

Use layovers endpoint to check connection time feasibility before suggesting off-airport activities: if layover duration minus MCT minus 90min buffer > activity duration → suggest it.

Viator Is Affiliate

We provide booking URLs, NOT direct booking. Always include: price_from_usd, viator_rating, viator_review_count, duration_minutes, viator_booking_url

When to Suggest

• Layovers > 3 hours: airport-area tours (ensure duration + transit <= connection - 90 min)
• Destination arrival: top-rated local attractions
• Recovery days: walking tours, cafes, parks
• Rain days: museums, food tours

Rate Limits

• Attractions/tours search: max 30/hr (Viator allows 60/min but self-limit).
• Only fetch when user asks or during trip planning — no pre-fetching all cities.

Data Sources — Tours & Activities

Primary: Aerobase Tours API (FREE, always query first)

• Internal tours/activities API with curated experiences
• Query by destination, category, price range, dates, duration
• Returns: activity name, description, price, duration, rating, booking link
• Covers major destinations worldwide

Secondary: Browser (supplementary discovery)

Use browser ONLY when:

• User asks about very niche/local activities not in our database
• User wants to compare prices with Viator, GetYourGuide, etc.
• User needs real-time availability confirmation

Workflow

1. User asks "What can I do in Tokyo for 3 days?"
2. Query Aerobase Tours API with destination=Tokyo
3. Present curated results by category: cultural, food, adventure, nightlife
4. If user wants more options: browse Viator/GetYourGuide via Google search
5. Always prefer our API results — better margins, curated quality

Scrapling — TripAdvisor Activity Discovery

TripAdvisor is in the scrapling tier (no proxy needed). Use for supplementary activity discovery:

Reference: Scrapling Documentation

web_fetch {SCRAPLING_URL}/fetch?url=https://www.tripadvisor.com/Attractions-g294217-Activities-Tokyo_Tokyo_Prefecture_Kanto.html&json=1&extract=css&selector=.listing_title

Returns extracted attraction titles. Replace the geo ID (g294217) and location path for other cities. Always prefer Aerobase Tours API first — use Scrapling TripAdvisor only for discovery of niche activities not in our database.

For UI rendering, see aerobase-ui SKILL for component specs.

When to SKIP browser entirely

• Almost always. Tours API is the primary and usually sufficient source.
• Browser only for edge cases: very niche activities, real-time availability checks
• Price comparison is rarely needed — our API has competitive pricing