agentsclimarketplace

Run1 multi city road trip planning

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/travel-planning/run1_multi-city-road-trip-planning

[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 run1_multi-city-road-trip-planning

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

Plan a multi-day road trip across multiple cities without flights, considering driving distances, travel time between destinations, and logical routing to minimize backtracking. Use this when building itineraries that require ground transportation between cities.

SKILL.md

1.3 KB, 187 tokens by cl100k_base, as published. Nobody here has run it

Overview

Road trip planning requires understanding:

  • Geographic layout of destination cities
  • Driving distances and estimated travel times between cities
  • Optimal routing order to minimize total driving time
  • Reasonable daily driving distances for leisure travel
  • Buffer time for travel days vs. activity days

Key Considerations

  • Route Optimization: Visit cities in a logical geographic sequence to avoid excessive backtracking
  • Driving Time: Typical leisure travelers prefer 3-5 hour driving days; plan travel days separately from activity days
  • Starting Point: Account for distance from origin city (Minneapolis) to first destination
  • Multi-City Sequences: For 3 Ohio cities, research their relative positions (e.g., Cleveland, Columbus, Cincinnati form a triangle)

Data Requirements

  • Distance/routing data (distance matrix or geographic coordinates)
  • City locations within Ohio
  • Approximate travel times for road segments

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.