design-judge-skills

Why we included this project

Preparing a design-award submission is mostly repetitive legwork: finding comparable past winners, judging your own work against criteria that are often vague, and drafting entry text that fits each program's rules. This project turns that workflow into a set of agent skills that run inside Claude Code, Codex, OpenClaw, OpenCode, or Hermes. The skills are separate modules you can trigger on their own, covering winner search and verification, evidence-based design scoring, award and category matching, sourced entry copy, and a final check against the current official rules. The evaluation module draws on more than 22,000 observed award records from iF, Red Dot, IDEA, and others, but treats them as descriptive context rather than a way to predict your odds. Coverage includes iF, Red Dot, IDEA, DIA, K-Design, Good Design Japan, Core77, James Dyson, and EPDA, and the skills re-check official pages at runtime for deadlines, fees, and eligibility. For teams that submit to these programs regularly, it is a practical assistant that keeps the process evidence-driven.