Skip to content
中文

Leaderboard / Coding

compare-tasks

compare-tasks (aaif-goose/goose): Compare how two harbor benchmark runs performed on a single shared task

Stars
55k
Votes
—
Score
47.4369

Source: aaif-goose/goose · evals/harbor/.agents/skills/compare-tasks/SKILL.md

Open ↗
npx skills add aaif-goose/goose --skill compare-tasks

Rate this skill

Related skills

01 brainstormingobra/superpowers Coding 301k
5479.1
↗
02 karpathy-guidelinesmultica-ai/andrej-karpathy-skills Coding 218k
5337.5
↗
03 app-e2e-testsanomalyco/opencode Coding 216k
5334.6
↗
04 component-testsanomalyco/opencode Coding 216k
5334.6
↗
05 ponytailDietrichGebert/ponytail Coding 167k
5222.2
↗