agentsclimarketplace

Run2 itinerary planning

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/travel-planning/run2_itinerary-planning

Plan multi-city driving itineraries with proper day allocation, cuisine variety, and format compliance.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_itinerary-planning

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

SKILL.md

1.5 KB, 343 tokens by cl100k_base, as published. Nobody here has run it

Itinerary Planning (Improved)

Route Selection for Ohio Trip from Minneapolis

Best 3-city combinations considering drive times:

  • Cleveland + Dayton + Cincinnati: Good loop, varied distances
  • Cleveland + Columbus + Cincinnati: Major cities, good attractions
  • Route: Minneapolis → City1 → City2 → City3 → Minneapolis

Day Allocation Strategy

  • Day 1: Long drive to first Ohio city (skip breakfast/lunch or eat before departure)
  • Days 2-6: Explore cities, with short travel days between cities
  • Day 7: Long drive back to Minneapolis (breakfast only, skip lunch/dinner)
  • Allocate 2 days per city (1 travel + 1 full day, or 2 full days)

Output Format Requirements

  • current_city: exact city name OR "from CityA to CityB"
  • transportation: "Self-driving: from CityA to CityB, duration" or "-"
  • Meals: "Restaurant Name, City" format; use "-" for skipped meals
  • attraction: semicolon-separated, MUST end with semicolon; use "-" if none
  • accommodation: "Accommodation Name, City" or "-" on last day

Cuisine Distribution

Ensure all 4 requested cuisines appear:

  • American: at least 2-3 meals
  • Mediterranean: at least 2-3 meals
  • Chinese: at least 2-3 meals
  • Italian: at least 2-3 meals

Budget Calculation

Total = Σ(accommodation price × nights) + Σ(restaurant avg cost × 2 people) Must stay under $5,100.

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.