agentsclimarketplace

Itinerary builder

Skill cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-opus-4-6/travel-planning/itinerary-builder

Build multi-day travel itineraries in JSON format from database lookups. Use this skill when constructing day-by-day travel plans with transportation, meals, attractions, and accommodations.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill itinerary-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.9 KB, 425 tokens by cl100k_base, as published. Nobody here has run it

Itinerary Builder

Output Format

Write to /app/output/itinerary.json with this structure:

{
  "plan": [
    {
      "day": 1,
      "current_city": "CityA" or "from CityA to CityB",
      "transportation": "Self-driving: from CityA to CityB" or "-",
      "breakfast": "Restaurant Name, City" or "-",
      "lunch": "Restaurant Name, City" or "-",
      "dinner": "Restaurant Name, City" or "-",
      "attraction": "Attraction1;Attraction2;",
      "accommodation": "Accommodation Name"
    }
  ],
  "data_sources": ["file1.csv", "file2.csv"]
}

Planning Strategy

  1. Route optimization: Minimize backtracking. For a round-trip, choose a logical geographic loop.
  2. Travel days: On long driving days (8+ hours), plan fewer attractions. Breakfast in departure city, dinner in arrival city.
  3. Budget tracking: Sum accommodations (per night), meals (per meal for 2), and transport costs. Stay under budget.
  4. Cuisine variety: Spread requested cuisine types across days. Match restaurant cuisines from the Cuisines column.
  5. Constraints: No flights means self-driving only. Pet-friendly means exclude "No pets" accommodations. Check minimum nights and max occupancy.
  6. Attractions: Pick 2-3 per full day in a city, 1 on travel days. End attraction list with semicolon.
  7. Accommodation: Use same accommodation for consecutive nights in the same city.

Data Sources to List

Always include all dataset files actually consulted:

  • background/citySet_with_states.txt
  • accommodations/clean_accommodations_2022.csv
  • restaurants/clean_restaurant_2022.csv
  • attractions/attractions.csv
  • googleDistanceMatrix/distance.csv

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.