ai-design
$
npx mdskill add arcasilesgroup/ai-engineering/ai-designMaster design skill. Aesthetic direction + design systems + component design + UI/UX and information-architecture guidance. Translates user intent into specific, opinionated design decisions -- never vague suggestions. Every output has a clear conceptual direction executed with precision.
SKILL.md
.github/skills/ai-designView on GitHub ↗
---
name: ai-design
description: "Designs user interfaces and design systems for web, mobile, CLI, and documentation-heavy experiences: aesthetic direction, color palettes, typography, spatial composition, information architecture. Trigger for 'design this page', 'create a design system', 'what style should we use', 'UI for this feature', 'color palette for', 'typography for'. Not for animation; use /ai-animation instead. Not for static visual art (posters, banners); use /ai-visual instead. Not for slide decks; use /ai-slides instead."
effort: high
argument-hint: "[UI or design task description]"
mode: agent
tags: [design, ui, ux, design-system, aesthetics]
model_tier: opus
mirror_family: copilot-skills
generated_by: ai-eng sync
canonical_source: .claude/skills/ai-design/SKILL.md
edit_policy: generated-do-not-edit
---
# Design
## Purpose
Master design skill. Aesthetic direction + design systems + component design + UI/UX and information-architecture guidance. Translates user intent into specific, opinionated design decisions -- never vague suggestions. Every output has a clear conceptual direction executed with precision.
## When to Use
- Designing interfaces (web or mobile)
- Creating or extending a design system
- Choosing aesthetic direction for a project
- Structuring text-heavy or CLI-facing information architecture when hierarchy, framing, and flow are design problems
- Component design and layout decisions
- Responsive design strategy
- Typography and color palette selection
- Spatial composition and visual hierarchy
## Process
### Step 1 -- Load Design Thinking Framework
Read `handlers/aesthetics.md` for the full aesthetic direction philosophy. This establishes the design thinking framework (Purpose, Tone, Constraints, Differentiation) and all frontend aesthetics guidelines.
### Step 2 -- Load UX Rules and Design System Intelligence
Read `handlers/design-system.md` for the priority-ranked UX rule database, covering accessibility, touch targets, performance, style selection, layout, typography, animation, forms, navigation, and data visualization.
### Step 3 -- Analyze the Request
Apply the design thinking framework from `handlers/aesthetics.md` (or directly if the handler is unavailable):
1. **Purpose** -- what problem does this interface solve? Who uses it?
2. **Tone** -- choose an extreme direction with clear character (minimalist, maximalist, organic, luxury, playful, editorial, brutalist, etc.)
3. **Constraints** -- technical requirements (framework, performance budget, accessibility level)
4. **Differentiation** -- "What makes this UNFORGETTABLE? What's the one thing someone will remember?"
### Step 4 -- Apply UX Guidelines by Priority
Use the priority ranking from `handlers/design-system.md`:
| Priority | Category | Gate |
| -------- | ------------------- | ---------------------- |
| 1 | Accessibility | CRITICAL -- never skip |
| 2 | Touch & Interaction | CRITICAL -- never skip |
| 3 | Performance | HIGH |
| 4 | Style Selection | HIGH |
| 5 | Layout & Responsive | HIGH |
| 6 | Typography & Color | MEDIUM |
| 7 | Animation | MEDIUM |
| 8 | Forms & Feedback | MEDIUM |
| 9 | Navigation Patterns | HIGH |
| 10 | Charts & Data | LOW |
Address P1-P2 as hard gates. P3-P9 as design considerations. P10 only when data visualization is involved.
### Step 5 -- Generate Design Direction
Produce specific choices, not vague guidance:
- Name the fonts (display + body pairing)
- Define the color system (primary, secondary, accent, surface, background, text hierarchy, state colors)
- Specify spacing scale (4pt/8dp system)
- Describe spatial composition with layout strategy
- Choose motion approach (duration, easing, what animates)
- Declare the conceptual direction in one sentence
### Step 6 -- Delegate Specialized Work
- If motion/animation design is needed beyond micro-interactions, invoke `/ai-animation`
- If visual artifacts (posters, banners, illustrations) are needed, invoke `/ai-visual`
- If presentation design, invoke `/ai-slides` (which consumes this skill's output)
### Step 7 -- Pre-Delivery Quality Check
Before delivering any design work, run `handlers/checklist.md` and verify all items pass. Do not deliver with unchecked items.
## Integration
- **Called by**: user directly, `/ai-slides`, `/ai-media`, `/ai-build`
- **Calls**: `handlers/aesthetics.md`, `handlers/design-system.md`, `handlers/checklist.md`, `/ai-animation`, `/ai-visual`
- **Consumed by**: `/ai-slides` (presentation aesthetics), `/ai-media` (visual asset direction)
## Common Mistakes
- Using generic AI aesthetics (the "ChatGPT look" -- purple gradients, Inter font, centered hero)
- Defaulting to Inter, Roboto, or Arial instead of choosing distinctive typography
- Choosing predictable layouts (centered hero, 3-column features, testimonials, CTA)
- Giving vague advice ("use a clean design") instead of specific choices ("use Space Grotesk for headings at 700 weight with 16px Instrument Serif body text")
- Skipping the differentiation question -- every design must answer what makes it unforgettable
- Ignoring accessibility as a hard gate (contrast, touch targets, keyboard nav)
- Treating dark mode as an afterthought instead of designing both themes simultaneously
## Examples
### Example 1 — design system from scratch
User: "create a design system for our internal admin tool"
```
/ai-design create design system for internal admin tool
```
Picks aesthetic direction (with rationale), defines color tokens, typography stack, spatial system; runs the pre-delivery checklist before handing off.
### Example 2 — UI for a specific feature
User: "design the empty state for the search results page"
```
/ai-design empty state for search results page
```
Specific opinionated decisions: layout, micro-copy, illustration vs icon, accessibility checks, light + dark mode simultaneously.
$ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.