$npx -y skills add Rune-kit/rune --skill designDesign system reasoning. Maps product domain to style, palette, typography, and platform-specific patterns. Generates .rune/design-system.md as the shared design contract for all UI-generating skills.
| 1 | # design |
| 2 | |
| 3 | ## Purpose |
| 4 | |
| 5 | Design system reasoning layer. Converts a product description into a concrete design system — style, color direction, typography pairing, platform conventions, and an explicit anti-pattern list for this domain. Writes `.rune/design-system.md` as the persistent design contract that all UI-generating skills read before producing code. Prevents AI-generated UI from defaulting to generic patterns ("purple accent, card grids, centered everything") that signal "not designed by a human." |
| 6 | |
| 7 | ## Triggers |
| 8 | |
| 9 | - `/rune design` — manual invocation when starting a new UI project |
| 10 | - Called by `cook` (L1): frontend task detected, no `.rune/design-system.md` exists |
| 11 | - Called by `review` (L2): AI anti-pattern detected — recommended to run design skill |
| 12 | - Called by `perf` (L2): Lighthouse Accessibility BLOCK — design foundation may be missing |
| 13 | |
| 14 | ## Calls (outbound) |
| 15 | |
| 16 | - `scout` (L2): detect existing design tokens, component library, platform targets |
| 17 | - `asset-creator` (L3): generate base visual assets (logo, OG image) from design system |
| 18 | - `browser-pilot` (L3): render the surface and inspect it before claiming any visual property holds (Step 5.4) |
| 19 | - `review` (L2): accessibility violations found → flag for fix in next code review |
| 20 | |
| 21 | ## Called By (inbound) |
| 22 | |
| 23 | - `cook` (L1): before any frontend code generation |
| 24 | - `scaffold` (L1): design system for new project |
| 25 | - `brainstorm` (L2): when selected approach has UI/UX implications |
| 26 | - `ba` (L2): when requirements include UI/UX components |
| 27 | - `review` (L2): when AI anti-pattern detected in diff |
| 28 | - `perf` (L2): when Lighthouse Accessibility score blocks |
| 29 | - User: `/rune design` direct invocation |
| 30 | |
| 31 | ## Output Files |
| 32 | |
| 33 | ``` |
| 34 | .rune/ |
| 35 | └── design-system.md # Design contract for all UI-generating skills |
| 36 | ``` |
| 37 | |
| 38 | ## Executable Steps |
| 39 | |
| 40 | ### Step 0 — Load Design Reference |
| 41 | |
| 42 | Load the design knowledge base before reasoning: |
| 43 | |
| 44 | 1. Check for user-level override: `~/.claude/docs/design-dna.md` |
| 45 | - If exists → `Read` it. This is the primary reference (user's curated taste). |
| 46 | 2. If no user override → `Read` the baseline: `skills/design/DESIGN-REFERENCE.md` (shipped with Rune) |
| 47 | 3. The loaded reference provides: font pairings, chart selection, component architecture, color principles, UX checklist, interaction patterns, anti-pattern signatures |
| 48 | 4. Apply reference knowledge throughout Steps 3-5 (domain reasoning, token generation, checklist) |
| 49 | 5. **When the domain involves any UI motion** (transitions, animations, gestures, springs, micro-interactions) → also `Read` `skills/design/MOTION-CRAFT.md`. It is the canonical motion authority: the should-it-animate frequency gate, easing/duration budgets, physicality (never `scale(0)`, origin-aware popovers), spring physics, gesture handoff, motion performance, reduced-motion, and a reverse-lookup vocabulary. Cite its exact values in the design-system motion section; never approximate curves or durations. **When MOTION-CRAFT.md and DESIGN-REFERENCE.md disagree on a motion detail (easing, duration, interaction timing), MOTION-CRAFT.md wins** — it is the deeper, motion-specific source; DESIGN-REFERENCE.md's Animation Timing / Interaction Patterns tables are the general baseline. |
| 50 | |
| 51 | > **Advisory motion-audit mode**: When asked to "improve the animations" / "make this feel better" / "what could be animated here", operate read-only — survey the motion surface against MOTION-CRAFT.md, report frequency-gated findings (and deliberately rejected candidates), and hand precise recipes to `cook`/`fix`. Suggesting motion everywhere is worse than useless; expect to reject most candidates. |
| 52 | |
| 53 | > **Why two layers**: The baseline ships "good enough" universal design knowledge. Users who care about aesthetics create their own `design-dna.md` with curated palettes, font pairings, and style preferences. The design skill works well with either — it just works _better_ with a curated reference. |
| 54 | |
| 55 | ### External Data Source |
| 56 | |
| 57 | Design intelligence data from [UI/UX Pro Max](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) (MIT, 42.8k★). |
| 58 | Located at `references/ui-pro-max-data/` — 161 palettes, 84 styles, 73 font pairings, 161 reasoning rules, 99 UX guidelines. |
| 59 | |
| 60 | When `references/ui-pro-max-data/` is available: |
| 61 | - Step 2: query `styles.csv` for domain-matched visual styles (expands from 10 → 84) |
| 62 | - Step 3: query `ui-reasoning.csv` for industry-specific design rules (161 rules) |
| 63 | - Step 3: query `colors.csv` for palette alternatives (expands from 10 → 161) |
| 64 | - Step 6 (Anti-AI): cross-check proposed style against reasoning DB — if flagged as "AI-generic", suggest 3 alternatives |
| 65 | |
| 66 | ### Step 1 — Discover |
| 67 | |
| 68 | Invoke `scout` to detect: |
| 69 | - **Platform target**: `web` |