agentsclimarketplace

Run2 budget validation

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/travel-planning/run2_budget-validation

[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 run2_budget-validation

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

Validate travel budget calculations including accommodation nights, meal costs, and constraint compliance.

SKILL.md

1.1 KB, 285 tokens by cl100k_base, as published. Nobody here has run it

Budget Validation

Accommodation Costs

For each city stay:

  • Verify minimum_nights <= planned stay
  • Verify maximum_occupancy >= 2 (for couple)
  • Verify no "No pets" in house_rules
  • Cost = price_per_night × number_of_nights

Meal Costs

  • Average Cost in database is per person
  • For 2 travelers: meal_cost = avg_cost × 2
  • Count all non-"-" meals

Validation Checklist

  1. Total accommodation + meals <= $5,100
  2. All 7 days accounted for (March 17-23, 2022)
  3. No flights used
  4. Pet-friendly accommodations only
  5. All 4 cuisine types represented (American, Mediterranean, Chinese, Italian)
  6. All entities exist in the database with correct city
  7. Attractions end with semicolon
  8. Last day accommodation can be "-" (returning home)

Sample Budget for Cleveland-Dayton-Cincinnati Route

  • Cleveland 2 nights: ~$400-600/night
  • Dayton 2 nights: ~$400-500/night
  • Cincinnati 2 nights: ~$250-300/night
  • 15-17 meals × $30-80 avg × 2 people = ~$900-2,700
  • Target: keep total under $5,100

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.