designing-beautiful-websites
Designs UX/UI for websites and web apps: UX strategy, information architecture, user flows, wireframes, UI systems, component specs, and polished visual design. Use when the user asks to design, redesign, modernise, critique, or improve a website, landing page, web app interface, design system, style guide, or UI kit.
What this skill does
# Designing Beautiful Websites > **Core philosophy:** Make the next action obvious. Build from user goals upward. Systemise visuals. Validate early. ## Why this exists Websites fail when they look “nice” but: - don’t match user goals, - hide key actions, - require too much thinking, - or are visually inconsistent. This skill turns vague requests like “make it look better” into a **repeatable workflow** that produces: - clear structure, - usable interactions, - and a cohesive visual system. ## What “done” looks like Deliverables should be **usable by builders** (engineers, no-code builders, future agents): - **Design brief**: users, goals, constraints, success metrics. - **IA + flows**: sitemap (or nav model), and 1–3 key user journeys. - **Layout + wireframes**: responsive page structure, component inventory. - **Visual system**: tokens (type, spacing, colour, radius, shadow), and usage rules. - **Component specs**: states, behaviour, empty/loading/error. - **QA notes**: accessibility, responsiveness, edge cases. If time is limited, prioritise: **clarity + hierarchy + consistency + accessibility**. ## Quick start workflow Copy this checklist into the working notes and tick it off: - [ ] **0. Inputs**: goal, audience, content, constraints, brand signals. - [ ] **1. Strategy**: user goals + business goals + success metrics. - [ ] **2. Scope**: pages/features/content; prioritise “key paths”. - [ ] **3. Structure**: IA + navigation model + flows. - [ ] **4. Skeleton**: wireframes + component inventory + responsive layout. - [ ] **5. Surface**: visual system + page comps + states. - [ ] **6. Validate**: usability pass + accessibility pass + consistency pass. - [ ] **7. Hand-off**: tokens + component specs + implementation notes. **Default rule:** do not jump to surface polish until structure and skeleton are believable. ## Non‑negotiables ### 1) Reduce thinking Design so users rarely wonder: - “Where am I?” - “What do I do next?” - “Is that clickable?” - “Why did they call it that?” Prefer **obvious** over clever. ### 2) Use conventions aggressively Use familiar patterns unless there is a measured reason to deviate. Unusual UI is a tax on every user interaction. ### 3) Clear visual hierarchy Every screen must answer (at a glance): - what this page is, - what the primary action is, - where the navigation is, - what is secondary. ### 4) Grouping must be unambiguous If spacing is doing grouping work: - there must be **more space around groups than within groups**. ### 5) Feedback and forgiveness Users should: - see results of actions quickly, - understand system status, - and recover via undo/back/cancel where possible. Prefer preventing errors over scolding users. ### 6) Accessibility is part of “beautiful” Good aesthetics survive: - keyboard-only use, - low vision, - colour‑blindness, - small screens, - slow networks. ## Default outputs format When responding, produce: 1. **Design brief** (bullets) 2. **IA + key flows** (bullets + simple diagrams if useful) 3. **Component inventory** (table or list) 4. **Design tokens** (CSS variables or JSON) 5. **Page-level guidance** (for each page/section) 6. **States & edge cases** 7. **Implementation notes** (HTML structure, CSS approach, ARIA, etc.) If the user asked for a critique/audit, output: - issues (grouped by severity), - fixes, - and a “next iteration plan”. ## The workflow in practice ### Step 0 — Gather inputs (fast) Ask only what’s needed; otherwise assume and state assumptions. Minimum questions: - **Primary user**: who is this for? - **Primary goal**: what must they do? - **Business goal**: what does success look like? - **Content**: what is real copy/data? - **Brand signals**: existing colours/logo/type/voice? - **Constraints**: tech stack, deadline, accessibility level. If inputs are missing, create a **working brief** with explicit assumptions. ### Step 1 — Strategy (align intent) Produce: - primary + secondary user goals, - business objectives, - success metrics, - constraints/risk. ### Step 2 — Scope (decide what exists) Define: - pages/screens, - features, - content requirements, - and what is out of scope. Pick 1–3 **key paths** (the journeys that matter most). Optimise these first. ### Step 3 — Structure (make it findable) Create: - sitemap / nav model (global + local nav), - page purpose statements, - user flows for key paths. Rule: navigation labels should be self‑evident; avoid internal jargon. ### Step 4 — Skeleton (arrange the UI) Create: - wireframes per page, - component inventory, - layout constraints (container widths, grids, spacing rhythm), - and priority order per breakpoint. Rule: start with the **feature/content**, not the “app shell”. ### Step 5 — Surface (make it beautiful) Build a consistent system: - spacing + sizing scale, - typography scale, - colour palette + shades, - radius + border rules, - elevation/shadow scale, - icon + illustration style, - motion rules (optional). Apply to page comps. ### Step 6 — Validate (fast loops) Run these checks: - **Glance test (5–10 seconds):** can someone tell what this is and what to do? - **Key‑path walkthrough:** can a first‑time user complete the main task? - **Consistency pass:** are tokens respected? is hierarchy consistent? - **Accessibility pass:** contrast, focus states, semantics, error messaging. ### Step 7 — Hand-off (make it buildable) Provide: - tokens, - component specs (states + spacing + behaviour), - responsive rules, - and edge cases. ## Default starter system Use this system unless the project already has one. ### Spacing & sizing scale (px) Use a **non-linear** scale so choices are easy: `0, 4, 8, 12, 16, 24, 32, 48, 64, 96, 128` Rules: - pick from the scale; avoid “one-off” numbers. - for grouping: **inside-group spacing < between-group spacing**. ### Typography scale (px) Keep it tight: 6–8 sizes is enough. Suggested: - `12` caption - `14` small/body-secondary - `16` body - `20` subheading - `24` h3 - `30` h2 - `40` h1/hero Rules: - default body line-height ~ `1.5–1.7`. - limit line length for reading (~45–80 characters). - use weight/colour/spacing before adding new sizes. ### Colour system - define neutrals (backgrounds + text), one primary, and semantic accents. - define **shades up front** (e.g., 100–900), don’t generate ad-hoc lightens/darkens. - “Grey” can be warm or cool; keep a consistent temperature. Contrast rules: - normal text target: **≥ 4.5:1** - large text target: **≥ 3:1** ### Elevation / shadow system Use 3–5 shadow levels that map to meaning: - 1: buttons/cards (subtle) - 2: popovers/menus - 3: sticky headers - 4: modals - 5: high priority overlays ### Borders Prefer: - spacing, - subtle shadows, - or small background changes over heavy borders. ### Empty states Empty states are a first impression. They must: - explain what’s empty, - why it matters, - and what to do next. ## Progressive disclosure Use these reference files when deeper detail is needed: - **Workflow & deliverables** → [references/WORKFLOW.md](references/WORKFLOW.md) - **Page patterns** → [references/PAGE-PATTERNS.md](references/PAGE-PATTERNS.md) - **Audit / critique** → [references/DESIGN-AUDIT.md](references/DESIGN-AUDIT.md) - **Usability & navigation** → [references/USABILITY.md](references/USABILITY.md) - **Visual design systems** → [references/VISUAL-DESIGN.md](references/VISUAL-DESIGN.md) - **Interaction & forms** → [references/INTERACTION-DESIGN.md](references/INTERACTION-DESIGN.md) - **Information architecture** → [references/INFORMATION-ARCHITECTURE.md](references/INFORMATION-ARCHITECTURE.md) - **Content & microcopy** → [references/CONTENT-COPY.md](references/CONTENT-COPY.md) - **Responsive rules** → [references/RESPONSIVE.md](references/RESPONSIVE.md) - **Accessibility** → [references/ACCESSIBILITY.md](references/ACCESSIBILITY.md) - **Checklists & templates** → [references/CHECKLISTS.md](references/CHECKLISTS.md) ## Quick search If running locally: ```bash grep -i "empty state
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".