Design Judge Skills
A set of skills for design-award submissions: winner research, criteria-based evaluation, award matching, entry writing and pre-submission checks
- 709 ★ on the repository
- Last commit
- Apache-2.0
Minimal access
Why this level
- The skills consist of instructions and reference data
- They require verifying official award pages at run time
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/design-judge-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skills consist of instructions and reference data
- They require verifying official award pages at run time
This is third-party code. Review the repository files before installing.
What it does
A set of several skills splits a design-award submission into separate tasks with clear boundaries. The modules research comparable winners from official pages, evaluate the design and its presentation against criteria while separating facts from inferences, match an award, track and category, prepare entry text with sources, and check a package for submission readiness. A coordinator skill picks the smallest sufficient route and keeps a handoff record between stages. It ships aggregated winner observations as descriptive background, not as a probability of winning.
Who it is for. For designers and product managers preparing a project for a design-award submission.
Good fit when
- You need to match an award and category to a project
- You need a design evaluation by transparent criteria with weak spots
- You need to prepare entry text and check the package before submitting
Not a fit when
- You are not preparing a design-award submission
- You expect a guaranteed win probability, which the skill does not provide
Example request
Compare which design awards fit this student concept best and explain whyLimitations
The skill verifies official award pages at run time because deadlines, fees and rules change. Scores and matches support a decision; they do not predict a win. The built-in winner observations are descriptive background.
How to disable. Remove the design-judge skill folders from the agent's skills directory or uninstall via the manager you used.
FAQ
Can I install a single module?
Yes, each skills folder is a separate unit. For modules that rely on shared data, install design-judge-shared alongside them.
Does it estimate a win probability?
No. Scores and matches support a decision and are not a probability of winning.
Discussion
No questions or reviews yet.
Related
SkillsNine Zhangyi skills: a game design sparring partner that drafts, passes a verdict and keeps a decision archive
Nine skills guide a product designer through seven layers, from observed behaviour to interface decisions.
18 skills and 6 agents for UX strategy: from research and flows to accessibility, ethics and engineering handoff
A skill that walks a student team through a math modeling contest in ten stages, from choosing a problem to submission
A skill that turns a vague interest, a literature gap or a proposal draft into a testable research question with a first-step plan
A plugin of 17 skills for product teams: customer research, prioritisation, experiments and design from idea to prototype
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Design Judge Skills (this card) | no | 709 | |
| awesome-gamedev-agent-skills | no | 8,686 | a skill router |
| Journalism agent skills | no | 452 | plugins for journalists and source checking |
| Wildberries jewelry card skills pack | no | 1 | seven Codex skills for jewelry listings on Wildberries |
README in short
The README presents a set of skills for the full design-award submission cycle: winner research, evaluation, award matching, entry preparation and pre-submission checks. It states principles: prefer primary sources, separate facts from inferences, keep scoring transparent and give each module a single role. Install runs via npx skills for Codex, Claude Code and other agents, each skills folder is a separate unit, and design-judge-shared is the shared package. Major awards are covered, and rules are verified on official pages at run time. Apache-2.0 licensed.
README badge
Original SKILL.md
--- name: design-award-pipeline description: "Route and coordinate an end-to-end design-award workflow across winner research, evidence-based evaluation, award matching, entry-text preparation, and final submission checking. Use when a user asks for a complete award plan, does not know which Design Judge skill to use, wants multiple stages coordinated, or needs a resumable workflow with explicit handoffs. Do not replace the specialist skills, invent project facts, treat scores as winning probabilities, or bypass current official-rule verification." --- # Design Award Pipeline Coordinate the specialist Design Judge skills without duplicating their rules. ## Route the request Choose the smallest sufficient route: | User goal | Route | |---|---| | Find comparable winners | `design-award-search` | | Diagnose or score the design | `design-evaluation` | | Select an award, route, or category | `design-award-match` | | Prepare entry fields and copy | `design-information-prep` | | Audit a concrete submission package | `design-submission-check` | | Complete journey | evaluation or match → information prep → submission check; add search only when precedents are needed | If the user has not provided enough information to select a route, ask at most one short question. Otherwise proceed with explicit assumptions. ## Maintain the handoff Create or update a compact handoff record using [references/handoff-schema.json](references/handoff-schema.json). Keep these concepts separate: - user-supplied facts; - evidence-backed findings; - model inferences; - missing facts and live-rule checks; - decisions already approved by the user; - the next recommended specialist skill. Do not copy long specialist outputs into the handoff. Store identifiers, decisions, blockers, source links, and artifact paths. When a handoff is written to JSON, run `python scripts/validate_handoff.py <handoff.json>` before treating it as resumable. Use [examples/handoff.example.json](examples/handoff.example.json) as a minimal valid shape, not as project evidence. ## Coordinate stages 1. State the selected route and why it is sufficient. 2. Invoke or follow the relevant specialist Skill exactly. 3. Preserve its uncertainty labels, evidence confidence, and blockers. 4. Stop for user approval when the target award, maturity track, or another consequential choice changes downstream work.