agentsclimarketplace

Itinerary planner

Skill cxcscmu/SkillLearnBench/skills/b4-skill-creator-gemini-3.1-pro-preview/travel-planning/itinerary-planner

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

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

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

What its author says it does

Copied from the file, not written here

How to plan travel itineraries. Use this skill whenever the user mentions a travel itinerary, a trip, planning a vacation, or generating a schedule from travel constraints, even if they don't explicitly ask for an itinerary planner.

SKILL.md

1.4 KB, 229 tokens by cl100k_base, as published. Nobody here has run it

Travel Itinerary Planning

This skill provides guidelines on creating a detailed and realistic travel itinerary.

Step-by-step Planning

  1. Understand the core constraints: origin, destinations, dates, duration, budget, party size, pet-friendliness, dietary/cuisine preferences, and transportation preferences.
  2. Select destinations based on the criteria (e.g., specific states or cities). Calculate the distance/travel time between cities.
  3. Allocate days to each destination logically to minimize travel time and maximize exploration.
  4. For each day, plan:
    • Transportation: How to get from A to B (or within a city).
    • Accommodation: Select lodging that fits the constraints (e.g., pet-friendly) for the nights spent in a city.
    • Meals: Breakfast, Lunch, and Dinner fitting the cuisine preferences.
    • Attractions: Select points of interest for the day.
  5. Track the budget to ensure the total cost of transportation, accommodation, meals, and attractions stays within the limit.

Output Structure

Follow the specific JSON structure requested by the user, ensuring all keys and values match the expected format exactly.

Keep looking

Skills are one crate of 328,083. 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.