agentsclimarketplace

Route planning

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/travel-planning/route-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 route-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

Algorithmic planning of itineraries avoiding specific transport modes and allocating time based on budget constraints.

SKILL.md

1.4 KB, 296 tokens by cl100k_base, as published. Nobody here has run it

Route Planning and Itinerary Construction

This skill focuses on sequentially constructing travel plans by selecting daily activities and accommodations, avoiding certain travel modes (e.g., no flights), and managing budget constraints.

Key Concepts

  • Distance/Travel time estimation without flights (driving or ground transportation only).
  • Day-by-day scheduling of activities (Meals, Attractions).
  • Maintaining budget variables iteratively across multiple days.

Implementation Details

  • Identify starting point and sequential destinations.
  • Use a driving distance matrix to calculate time/costs.
  • Iteratively assign activities and ensure costs are kept under constraints.
  • Output final structured format (e.g., JSON).
import json

itinerary = {
    'plan': [],
    'data_sources': ['data/distance.csv', 'data/attractions.csv']
}

# Example daily assignment
day_plan = {
    'day': 1,
    'current_city': 'Minneapolis',
    'transportation': 'Self-driving: from Minneapolis to Cleveland',
    'breakfast': 'Local Cafe',
    'lunch': 'Bistro',
    'dinner': 'Fine Dining',
    'attraction': 'City Park;Museum;',
    'accommodation': 'Pet-Friendly Inn'
}

itinerary['plan'].append(day_plan)

with open('output/itinerary.json', 'w') as f:
    json.dump(itinerary, f, indent=2)

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.