agentsclimarketplace
Sign in

Run2 matching evaluation

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-flash-lite-preview/dbscan-parameter-tuning/run2_matching-evaluation

Efficient greedy matching of cluster centroids to expert points with distance constraint.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run2_matching-evaluation

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

SKILL.md

0.4 KB, 54 tokens by cl100k_base, as published. Nobody here has run it

Logic

  1. For each image, build a full distance matrix (N centroids x M experts).
  2. Sorting the entire matrix allows for optimal greedy matching without repeated searching.
  3. Ensure the distance constraint (max distance 100 pixels) is applied strictly.

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.