shape
Skill41 starsChanged 7 months agoMITView on GitHub
Plan the UX and UI for a feature before writing code. Run a structured discovery interview, then produce a design brief (.design-context.md) that guides implementation. Establishes design direction, constraints, and strategy before any code is written. Triggers on plan the design, design brief, shape the UX, before we build, design discovery.
We split this skill into the rules it gives an agent
14 rules. 0 are common, 12 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 30 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read ~/.claude/skills/minoan-frontend-design/SKILL.md for aesthetic principles and anti-pattern guidance.
- Very specific: line 15
Check for existing design context: .design-context.md in the project root, or a ## Design Context section in CLAUDE.md.
- Distinctive: line 19
Do NOT make any design decisions during this phase.
- Distinctive: line 23
Ask 2-3 questions per round, then wait for answers.
- Distinctive: line 25
Assert-then-confirm, not menu-with-escape: When the user's prompt and existing context make one option obvious, name it and ask the user to …
- Distinctive: line 27
Ask these questions conversationally — adapt based on answers, don't dump them all at once:
- Distinctive: line 45
Theme via scene sentence: Write one sentence of physical context for this surface: who uses it, where, under what ambient light, in what …
- Distinctive: line 52
Always ask. Sketch quality and shipped quality are different outputs — don't guess between them.
- Distinctive: line 71
After the interview, generate 2-4 visual direction probes before writing the final brief when all of these are true:
- Distinctive: line 76
When those conditions are met, this step is mandatory.
- Distinctive: line 82
After the interview (and any probes), synthesize into a structured design brief.
- Distinctive: line 85
Compact form (3-5 bullets): when discovery was crisp and existing context already pins scope, content, and direction.
- Distinctive: line 86
Full structured form: when the task is genuinely ambiguous, multi-screen, or the user asked for shape as a standalone step.
- Distinctive: line 88
Don't pad a clear brief into a long one to look thorough.
“Common” is measured: kept by at least 6 in 10 of the 30 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shape the UX and UI for a feature before any code is written. This skill produces a design brief — a structured artifact that guides implementation through discovery, not guesswork.
Scope: Design planning only. This skill produces design briefs, not code.
Preparation
Read ~/.claude/skills/minoan-frontend-design/SKILL.md for aesthetic principles and anti-pattern guidance. These inform the design direction but should not constrain the discovery interview.
Check for existing design context: .design-context.md in the project root, or a ## Design Context section in CLAUDE.md. If either exists, use it as a starting point — don't re-ask questions it already answers.
Phase 1: Discovery Interview
Do NOT make any design decisions during this phase. Understand the feature deeply enough to make excellent decisions later.
Interview cadence
Ask 2-3 questions per round, then wait for answers. One round is the default. Add a second only if the first answers leave material gaps — don't run a second round just to feel thorough.
Assert-then-confirm, not menu-with-escape. When the user's prompt and existing context make one option obvious, name it and ask the user to confirm or override. "This reads as Restrained, confirm?" beats a four-option menu when the answer is already clear.
Ask these questions conversationally — adapt based on answers, don't dump them all at once:
Purpose & Context
- What is this feature for? What problem does it solve?
- Who specifically will use it? (Role, context, frequency — not just "users")
- What does success look like? How will you know this feature is working?
- What's the user's state of mind when they reach this? (Rushed? Exploring? Anxious?)
Content & Data
- What content or data does this feature display or collect?
- What are the realistic ranges? (Minimum, typical, maximum — e.g., 0 items, 5 items, 500 items)
- What are the edge cases? (Empty state, error state, first-time use, power user)
Design Direction
Force a visual decision on three fronts. Skip anything existing context already answers; ask only what's missing.
- Color strategy for this surface. Pick one: Restrained / Committed / Full palette / Drenched. Can override the project default if the surface earns it (e.g. a drenched hero inside an otherwise Restrained product).
- Theme via scene sentence. Write one sentence of physical context for this surface: who uses it, where, under what ambient light, in what mood. The sentence forces dark vs light. If it doesn't, add detail until it does.
- Two or three named anchor references. Specific products, brands, objects. Not adjectives like "modern" or "clean."
- What's the single most important thing a user should do or understand here?
- Are there existing patterns in the product this should be consistent with?
Scope
Always ask. Sketch quality and shipped quality are different outputs — don't guess between them.
- Fidelity. Sketch / mid-fi / high-fi / production-ready?
- Breadth. One screen / a flow / a whole surface?
- Interactivity. Static visual / interactive prototype / shipped-quality component?
- Time intent. Quick exploration, or polish until it ships?
Constraints
- Technical constraints? (Framework, performance budget, browser support)
- Content constraints? (Localization, dynamic text length, user-generated content)
- Mobile/responsive requirements?
- Accessibility requirements beyond WCAG AA?
Anti-Goals
- What should this NOT be? What would be a wrong direction?
- What's the biggest risk of getting this wrong?
Phase 1.5: Visual Direction Probe (Capability-Gated)
After the interview, generate 2-4 visual direction probes before writing the final brief when all of these are true:
- The work is net-new or directionally ambiguous enough that visual exploration will clarify the brief.
- The requested fidelity is mid-fi, high-fi, or production-ready.
- The current harness gives you native image generation (e.g.
image_gen, an MCP tool, or similar).
When those conditions are met, this step is mandatory. If image generation isn't natively available, state in one line that the step is skipped and proceed.
The probes should differ in primary visual direction (hierarchy, topology, density, typographic voice, color strategy), not just palette tweaks. Treat them as direction tests — ask the user which feels closest, what's off, and what should carry forward. If probes reveal a mismatch, revise the brief inputs before finalizing.
Phase 2: Design Brief
After the interview (and any probes), synthesize into a structured design brief. Present it and stop — the user must confirm before considering this skill complete.
Choose the brief shape based on clarity:
- Compact form (3-5 bullets) when discovery was crisp and existing context already pins scope, content, and direction. End with one or two specific questions or "confirm or override?"
- Full structured form when the task is genuinely ambiguous, multi-screen, or the user asked for shape as a standalone step.
Don't pad a clear brief into a long one to look thorough.
1. Feature Summary (2-3 sentences) What this is, who it's for, what it needs to accomplish.
2. Primary User Action The single most important thing a user should do or understand here.
3. Design Direction
Color strategy (Restrained / Committed / Full palette / Drenched) + theme scene sentence + 2-3 named anchor references. Reference the project's design context if available. Set DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY (1-10 each) based on discovery answers. Consult ~/.claude/skills/minoan-frontend-design/references/design-dials.md. If Visual Direction Probes were run, name which direction won and what changed.
4. Layout Strategy High-level spatial approach: what gets emphasis, what's secondary, how information flows. Describe the visual hierarchy and rhythm, not specific CSS.
5. Key States List every state the feature needs: default, empty, loading, error, success, edge cases. For each, note what the user needs to see and feel.
6. Interaction Model How users interact with this feature. What happens on click, hover, scroll? What feedback do they get? What's the flow from entry to completion?
7. Content Requirements What copy, labels, empty state messages, error messages, and microcopy are needed. Note any dynamic content and its realistic ranges.
8. Open Questions Anything unresolved that the implementer should resolve during build.
9. Implementation Skills
Consult references/design-media-catalog.md. Based on discovery answers, recommend which skills the implementer should invoke beyond /minoan-frontend-design. Only list skills that match actual needs discovered — don't enumerate the full catalog.
Get explicit confirmation of the brief before finishing. If the user disagrees with any part, revisit the relevant discovery questions.
Once confirmed, write the brief to .design-context.md in the project root (or update the existing file). The user can then hand it to /minoan-frontend-design or use it to guide any other implementation approach.
Other versions31 projects use a version of this.
Word for word · 0
None found.
Edited · 12
- 10xChengTu/Mux0★ 33746% same
- theexperiencecompany/gaia★ 32446% same
- jagrat7/linux-wallpaper-engine★ 20847% same
- owshq-mec/semana-ai-data-engineer★ 12246% same
- StyleSwift/StyleSwift★ 6146% same
- excatt/superclaude-plusplus★ 1446% same
- The-Utopia-Studio/skills★ 646% same
- tyfarrago-hub/taste★ 346% same
- ReScienceLab/TrySkills★ 246% same
- tamibot/creators-latam-starter★ 246% same
2 more not listed
Wrote their own version · 19
- hoophq/hoop★ 831same name
- educlopez/ui-craft★ 398same name
- saltandsilicon/game-theorist★ 16same name
- Astro-Han/skills★ 12same name
- chrislacey89/skills★ 4same name
- jtsang4/efficient-coding★ 2same name
- kborovik/grok-skills★ 2same name
- moruno21/agents-concerto★ 2same name
- Igloczek/skills★ 1same name
- jamesm-dev/tateru.dev★ 1same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use layout, brief and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
owshq-mecSkilllayout
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
Also in 8 projects that use this
AnthropicSkillbrief
Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
Also in 3 projects that use this
Microsoft AzureSkillbuild
Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 5 projects that use this
OpenAISkillexecuting-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Also in 3 projects that use this
StrayDragonSkillui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Also in 4 projects that use this
In this repository99 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agents-md-managerSkill
- architecture-md-builderSkill
- autoresearchSkill
- claude-agent-sdkSkill
- claude-md-managerSkill
- claude-usageSkill
- dag-typesafeSkill
- fableSkill
- glossarySkill
- openrouter-usageSkill
- react-best-practicesSkill
- skill-optimizerSkill
- stop-slopSkill
- tamarruSkill
- test-harness-auditorSkill
- user-model-builderSkill
- atmosphere-shaderSkill
- component-gallerySkill
- conductor-motionSkill
- design-auditSkill
- design-critiqueSkill
- design-mdSkill
- design-polishSkill
- gemini-claude-resonanceSkill
- gemini-forgeSkill
- gpt-atelierSkill
- grainientSkill
- image-forgeSkill
- image-wellSkill
- meshySkill
- mindnode-uiSkill
- minoan-frontend-designSkill
- nano-banana-proSkill
- overwatch-slidedeckSkill
- paper-designSkill
- particle-swarm-simSkill
- pellicolaSkill
- photo-to-slack-emojiSkill
- pretextSkill
- recordlySkill
- rocaille-shaderSkill
- scroll-cinemaSkill
- shadcnSkill
- smolvlmSkill
- speak-responseSkill
- sprite-forgeSkill
- threejs-particle-canvasSkill
- vellum-editorialSkill
- webgpu-threejs-tslSkill
- agent-browserSkill
- beautiful-mermaidSkill
- classical-887Skill
- claude-peersSkill
- cloudflareSkill
- codex-ctoSkill
- codex-orchestratorSkill
- disc-forgeSkill
- figma-mcpSkill
- linkedin-exportSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

