A browser built for AI agents and you to share: agents run tasks in isolated Spaces while your own tabs and logins stay untouched.
SeanJ1ang/design-judge-skills
A set of modular Agent Skills that guide design award work, from finding winning cases and evaluating designs to matching awards and checking submissions.
- Stars
- 712
- Forks
- 102
- Open issues
- 0
- Last commit
- 2 months ago
What is it?
Design Judge Skills is a collection of Agent Skills for working through design award entries. It splits the process into separate skills: searching and verifying same-category winning works from official sources, scoring a design and its presentation with an evidence-based rubric, matching a project to suitable awards and entry categories, preparing entry text from the user's own materials, and checking a submission package against the current official rules.
The skills are meant to be installed into coding and general agents such as Claude Code, Codex, OpenClaw, OpenCode and Hermes Agent, and can be used independently or as a full pipeline. Supported awards include iF, Red Dot, IDEA, DIA, K-Design, GOOD DESIGN Japan, Core77, James Dyson and EPDA. Deadlines, fees and eligibility are rechecked against official pages at runtime rather than stored as fixed facts.
The evaluation module ships with aggregated observations from roughly 22,000 winning or shortlisted works, used only as descriptive background and not to estimate award probability. Scores are presented as decision support, not predictions.
Key features
- 01Searches and verifies same-category winning works against official sources.
- 02Evaluates design and presentation with an evidence-based rubric and reports confidence and critical risks.
- 03Matches projects to awards, project paths and categories, and checks structural eligibility.
- 04Extracts facts from user materials to draft entry fields with source constraints.
- 05Checks submission packages for completeness, consistency and readiness with a go / conditional go / no-go verdict.
- 06Works as standalone skills or as a full pipeline across Claude Code, Codex, OpenClaw and other agents.
Use cases
- Finding comparable award-winning projects in your product category before writing an entry.
- Getting an evidence-based critique of a student concept or design portfolio before submitting.
- Deciding which design award or category fits a project best.
- Checking a submission package against current official rules before the deadline.
Quick start
- 1
List the available skills in the repository
npx skills add SeanJ1ang/design-judge-skills --list - 2
Install all skills globally for Codex
npx skills add SeanJ1ang/design-judge-skills --global --agent codex --skill '*' --yes --copy - 3
Open a new Codex session and ask the agent to use a skill, such as design-award-pipeline
Things to know
- Award rules, deadlines, fees and submission specs must be re-verified against official pages at runtime.
- The bundled award-observation data is descriptive only and cannot estimate winning chances.
- Most skills are in Beta and may still have edge-case boundary issues.
Topics
FAQ
- What is design-judge-skills?
- A set of modular Agent Skills that guide design award work, from finding winning cases and evaluating designs to matching awards and checking submissions. Design Judge Skills is a collection of Agent Skills for working through design award entries. It splits the process into separate skills: searching and verifying same-category winning works from official sources, scoring a design and its presentation with an evidence-based rubric, matching a project to suitable awards and entry categories, preparing entry text from the user's own materials, and checking a submission package against the current official rules.
- Is design-judge-skills free to use? What license does it have?
- design-judge-skills is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is design-judge-skills still maintained?
- Updated within 6 months. The last commit to design-judge-skills was on Aug 24, 2026.
- What can I use design-judge-skills for?
- Finding comparable award-winning projects in your product category before writing an entry. Getting an evidence-based critique of a student concept or design portfolio before submitting. Deciding which design award or category fits a project best. Checking a submission package against current official rules before the deadline.
- How do I install design-judge-skills?
- List the available skills in the repository: npx skills add SeanJ1ang/design-judge-skills --list Install all skills globally for Codex: npx skills add SeanJ1ang/design-judge-skills --global --agent codex --skill '*' --yes --copy Open a new Codex session and ask the agent to use a skill, such as design-award-pipeline
- Where can I get design-judge-skills?
- The source code and installation instructions are on GitHub: https://github.com/SeanJ1ang/design-judge-skills
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Agent skills that give AI agents access to YouTube transcripts, video search, channel browsing and playlist extraction via the TranscriptAPI service.
A terminal app (CLI/TUI) for running and managing multiple AI coding agents like Claude Code, Codex, and Aider in separate git workspaces.
Remote control for Claude Code, Codex, Grok, and Cursor on your Mac or PC, driven from a phone or a voice wearable.
A Chinese-language tutorial collection teaching Claude Code, OpenClaw, Codex and WorkBuddy for AI coding, personal agents and office work, with practice materials.
Agent Skills that make coding agents design distinctive frontends, using art direction, real photos and a browser self-check instead of generic AI landing pages.