agentsclimarketplace
Sign in

Run2 itinerary content requirements

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/travel-planning/run2_itinerary-content-requirements

Guidelines for selecting database-compliant restaurants, accommodations, and attractions based on specific user constraints like budget, pets, and cuisine.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_itinerary-content-requirements

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, 243 tokens by cl100k_base, as published. Nobody here has run it

  1. Data Sourcing: Only use real-world data from the provided database files (e.g., restaurants/clean_restaurant_2022.csv, accommodations/clean_accommodations_2022.csv). Do not use internal knowledge or hallucinations.
  2. Pet-Friendly Accommodations: Filter the accommodations database specifically for entries labeled as pet-friendly. The selected lodging must explicitly support pets for every night of the trip.
  3. Cuisine Alignment: Match the breakfast, lunch, and dinner fields with the user's preferred cuisines: American, Mediterranean, Chinese, and Italian. If a specific cuisine is unavailable in a city, default to a high-rated American option from the database.
  4. Attraction Format: List attractions as a string, separated by semicolons, and ensure the string ends with a semicolon (e.g., "Attraction A;Attraction B;").
  5. Daily Engagement: Ensure a minimum of one attraction is listed for every single day (Day 1 through Day 7). Use city-specific data to ensure the attraction is relevant to the current_city or route.

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.