← All skills

mars-cluster-to-expert-matching

100 / 100 · Low risk

Fine to try.

By cxcscmu/SkillLearnBench (GitHub) · other · 93 stars · scanned at commit 726e1f7

Implement greedy nearest-neighbor matching between cluster centroids and expert annotations. Use this skill when you need to match predicted cluster centers to ground-truth expert points for Mars cloud evaluation, always using standard Euclidean distance with a maximum distance threshold of 100 pixels.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'mars-cluster-to-expert-matching' ] || [ -L ~/.agents/skills/'mars-cluster-to-expert-matching' ]; then echo 'A skill folder named mars-cluster-to-expert-matching already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/cxcscmu/SkillLearnBench' "$d" && git -C "$d" checkout --quiet '726e1f79b96b0cb3d729d0e55a1c847e0b5353ae' -- 'skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-cluster-to-expert-matching' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-cluster-to-expert-matching' ~/.agents/skills/'mars-cluster-to-expert-matching' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'mars-cluster-to-expert-matching' ~/.claude/skills/'mars-cluster-to-expert-matching' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for cxcscmu/SkillLearnBench shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/cxcscmu/SkillLearnBench.svg)](https://zalavijaysinh.github.io/skilltrust/repos/cxcscmu/SkillLearnBench/)

Score history