agentsclimarketplace

Itinerary planner

Skill cxcscmu/SkillLearnBench/skills/b4-skill-creator-gemini-3-flash-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.

SKILL.md

1.2 KB, 290 tokens by cl100k_base, as published. Nobody here has run it

name: itinerary-planner description: How to construct a 7-day travel itinerary with constraints. Use this skill when organizing days, managing budget, and ensuring all user requirements (pet-friendly, cuisine, no flights) are met.

Planning Workflow

1. Route Optimization

  • Start from the origin (Minneapolis).
  • Sequence cities to minimize backtracking and excessive driving on a single day (except for the long hauls from/to Minneapolis).
  • Use distance.csv to validate the route.

2. Constraint Checklist

  • 7 Days: Ensure exactly 7 day objects in the final JSON.
  • Three Cities: Cover the requested number of target cities.
  • Pet-Friendly: Every accommodation MUST have a rule allowing pets.
  • Cuisines: Incorporate preferred cuisines (American, Mediterranean, Chinese, Italian) across the meals.
  • Budget: Keep total cost (Accommodations + Meals + Estimated Fuel) under the limit ($5,100).
    • Fuel Estimate: $0.15 per km (roughly).
    • Meal Estimate: Use Average Cost from restaurant data.

3. Output Format

  • Strictly follow the JSON structure provided in the task description.
  • Ensure current_city accurately reflects the location or the movement (e.g., "from A to B").
  • attraction field must end with ;.

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.