agentleFS
harshsinghmpharshsinghmp/muse-skills/skills/agency-delivery/design/SKILL.md

design

Skill1 starsChanged 18 days agoMITView on GitHub

Full website design department: creates original visual design from a brief, idea, or reference — UI design, UX flows, wireframes, logos, brand identity, social templates, graphic assets, prototypes, component UI kits, visual storytelling, dynamic visual canvas previews, and interactive 3D web scenes — routed through fifteen modes. Use when asked to design a website, page, or dashboard, create a wireframe or mockup, design a logo or brand identity, build social media templates, produce graphic assets, prototype flows, build UI kits, architect visual narratives, stream live component canvas previews, or integrate 3D Spline/Three.js assets. Not for refactoring existing UI (refactor-ui), extracting a design system from a reference (designscope), or animation (animate).

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 176 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every invocation resolves to exactly one mode.

    line 38
  2. Distinctive:

    Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.

    line 56
  3. Distinctive:

    Every landing page or homepage design MUST strictly match the client's industry vertical.

    line 77
  4. Distinctive:

    Intake: run the department intake gate in Quick Reference.

    line 145
  5. Very specific:

    Default OS artifacts: generic blue ::selection, default OS scrollbars, or unpadded focus rectangles.

    line 158

“Common” is measured: kept by at least 6 in 10 of the 176 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🎨 design — Website Design Department

One head skill for the whole design department. Creates original design from an idea, brief, or approved reference — structure first, then direction, then final art. Every decision is emitted as tokens and specs an engineer can build from.


Modes

Every invocation resolves to exactly one mode. Match the request, then load only the matched reference:

ModeTrigger phrasesBehaviorReference
ui"design the homepage", "hi-fi mockup", "design this screen"Full interface design pass: layout, hierarchy, tokens, statesreferences/ui.md
ux"map the user flow", "improve the UX", "information architecture", "ux-architect", "ux-researcher", "persona-walkthrough", "onboarding-ux", "ux-patterns"UX architecture, user research, persona cognitive walkthroughs, onboarding flows, heuristic auditsreferences/ux.md
wireframe"wireframe the homepage", "low-fi layout", "structure first"Grayscale structure with content plan, pre-visual-designreferences/wireframe.md
logo"design a logo", "new mark", "refresh our logo"Logo concept territories → refinement → variants + usage rulesreferences/logo.md
branding"brand identity", "brand guidelines", "brand system", "brandkit", "brand immersion"Full identity system: color, type, spacing, voice → brand.md, tokens, and immersion standardreferences/branding.md & references/brand-immersion.md
socials"social templates", "post designs", "profile kit"Social template system: profiles, post formats, grid consistencyreferences/socials.md
graphics"banner", "OG image", "hero art", "flyer", "banner-creator"One-off graphic assets: banners, OG/social share, print-adjacentreferences/graphics.md
prototype"prototype this flow", "clickable mock", "test the riskiest screen first"Riskiest-visual-unknown-first clickable mock → fast test → locked/iterate/kill verdictreferences/prototype.md
uikit"uikit", "ui kit", "component library", "starwind-ui", "stitch-design-taste", "design system components", "primitives"Component libraries, headless primitives, Starwind UI / Tailwind component kits, tokens-to-componentsreferences/uikit.md
story"visual storytelling", "visual narrative", "storyboard", "data storytelling", "infographic narrative", "emotional journey"Visual narrative design: story arcs (setup → conflict → resolution), video storyboards, infographics/data storytelling, emotional journeys, cross-platform visual adaptationsreferences/story.md
canvas"design canvas", "canvas relay", "live component preview", "component preview pipe", "oklch visualizer", "mermaid export", "visual sandbox"Dynamic visual artifact streaming, live component preview pipe (375px/768px/1440px), OKLCH palette contrast visualizer, and interactive Mermaid graph exporterreferences/canvas.md
3d"3d scene", "spline", "three.js", "r3f", "blender model", "3d asset optimization"Interactive 3D web scenes, Spline embeds, Three.js/R3F setups, and glTF optimizationreferences/3d.md
audit"design audit", "design QA", "audit this screen", "contrast check", "design handoff review"Score the view against hierarchy, contrast, states, tokens, and responsive integrity; severity-routed fixesreferences/audit.md

Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.


Support references (load on topic)

Loadable by topic; also routable as /design-<file> commands (not separate routed modes):

  • slides.md

When to Use

  • Designing a new site, page, or dashboard from a brief, idea, or approved mood references.
  • Creating wireframes, user flows, or information architecture before any visual design.
  • Designing a logo or full brand identity system (colors, type, voice rules).
  • Building a social template system or graphic assets (banners, covers, OG images).
  • Building industry-specific landing pages using structured layout templates (e.g. SaaS, Developer Tools).

Layout Templates & Vertical Selector Matrix

Every landing page or homepage design MUST strictly match the client's industry vertical. Never apply technical or code-first templates to non-developer verticals:

Vertical TypeTarget Buyer / UserCanonical Template / FlowCore Elements & Visual Language
Developer Tools & InfrastructureSoftware Engineers, DevOps, Architectstemplates/developer.md1-line install, code grid, zero-auth demo, architecture diagram, GitHub stars
B2B SaaS (Business / Ops)Founders, Managers, Execs, Sales/Opstemplates/saas.md9-section problem-to-solution, ROI justification, enterprise logos, value tiers
E-Commerce & RetailConsumers, Shoppers, Retail BuyersRoute to webdev:ecommerce / Retail flowLifestyle imagery, product catalog/grid, variant selector, cart, reviews
Professional Services & AgenciesClients seeking consulting/servicesRoute to brand:pipeline / Service Lead-genDeliverable scope, client case studies, team credentials, booking CTA
Local Business & HealthcareLocal clientele (clinics, legal, trade)Local Lead-Gen flowLocation/hours, phone/booking CTA, service menu, verified testimonials
Creator, Media & CommunitiesReaders, listeners, community membersMedia / Newsletter flowContent samples, subscriber count, episode highlights, community benefits

Layout template details:

  • SaaS (templates/saas.md): Canonical 9-section problem-solving landing page layout (Header/Nav → Hero → Logos/Trust Marquee → Features → Product Showcase → Pricing → Testimonials → Final CTA → Footer) aligned with 9 copywriting frameworks (AIDA, PASTOR, 4 P's, PRUNE, SLAP, So What?, PAPA, Star-Story-Solution, SPIN).
  • Developer (templates/developer.md): Canonical 7-block developer homepage layout (Hero with 1-Command Install → Frictionless Demo / Playground → Architecture & Mechanics → Code-First Feature Grid → Developer Social Proof & OSS Stats → Quickstart & Integration Surface → Transparent Pricing & License) synthesized from Jakub Czakon's developer marketing framework. Strict negative guards prevent application to non-technical verticals.

Anti-Triggers

  • Improving or refactoring an existing interface → refactor-ui.
  • Extracting a design system from a reference (screenshot/URL/Figma) → designscope.
  • Adding motion or animation → animate.
  • Scaffolding the project repository → new-project.

Quick Reference

Department intake gate (every run)

QuestionWhy
What is the business goal of this design?Design without a goal is decoration
Who is the audience, and on what device/context?Audience picks hierarchy, not taste
What brand inputs exist (tokens, brand doc, logo)?Existing brand wins — never invent over it
What references or mood direction is approved?Prevents rework after hi-fi

Client has a live brand but no tokens → run designscope on their site first.

Deliverable ladder

StageModeApproved before next?
Structurewireframe, uxYes
Directionui style tile, branding tokensYes
Final artui hi-fi, logo, socials, graphicsYes

Skipping an approval gate is how rework happens.

Defaults (client tokens override whenever they exist)

  • Spacing: 4px base scale — 4/8/12/16/24/32/48/64.
  • Type: one display + one text family, 1.25 (minor third) scale.
  • Color roles: primary (brand), action (CTA), neutral (text/surface), semantic (success/warn/danger).
  • Contrast: 4.5:1 body text, 3:1 large text — verified before delivery.
  • Output shape: decisions as tokens (OKLCH/hex, DTCG naming) + component specs, not just pictures.

CLI Engine Commands (brand-assets.ts)

CommandActionOutput / Target
bun brand-assets.ts --scaffoldScaffold complete brand immersion suiteCSS, adaptive favicon SVG, webmanifest
bun brand-assets.ts --scaffold-cssGenerate brand immersion micro-interactions::selection, custom scrollbars, :focus-visible
bun brand-assets.ts --scaffold-faviconGenerate adaptive dark/light favicon & manifestpublic/favicon.svg & site.webmanifest
bun brand-assets.ts --auditAudit project directory for brand immersion standardsStructured aesthetic scorecard (0-100)

Procedure

  1. Intake. run the department intake gate in Quick Reference; client brand inputs win over invented direction every time.
  2. Resolve the mode. Match the request against the mode table; exactly one mode. Ambiguous → ask one question, then proceed.
  3. Execute the mode playbook. Load references/<mode>.md and follow its Intake → Deliverable → Procedure → Quality gate in order.
  4. Gate and deliver. Pass this file's Verification checklist plus the mode's quality gate, then deliver the artifact where the client expects it.

Pitfalls

  • Designing hi-fi before structure is agreed — rework machine. Wireframe approval comes first.
  • Inventing brand colors when the client already has a brand — designscope their assets; existing tokens win.
  • More than 2 type families, or decorative faces on body text.
  • Happy-path-only components — every component needs hover, focus, disabled, loading, empty, and error states.
  • Default OS artifacts: generic blue ::selection, default OS scrollbars, or unpadded focus rectangles.
  • Static dark favicons that disappear on dark-mode browser tabs.
  • Page-to-page aesthetic drift — one token set per project, extended, never forked.
  • Delivering pictures without specs or tokens — engineers guess, pixels drift.
  • Wrong mode resolved (branding request treated as ui) — deliverable shape is wrong; re-route.

Verification

  • Exactly one mode resolved and its reference playbook followed end to end.
  • Every visual decision traces to an intake input (goal, audience, brand, or approved reference).
  • Text/background pairs pass AA: 4.5:1 body, 3:1 large text.
  • Spacing and type come from a stated scale; at most 2 type families.
  • Brand immersion styling verified: ::selection has WCAG AA contrast, custom scrollbars match palette.
  • Keyboard accessibility preserved: :focus-visible offset ring configured without square clipping.
  • Adaptive dark/light SVG favicon and site.webmanifest present in public/.
  • Components specified with all interactive states and responsive behavior.
  • Existing-brand work used the client's tokens verbatim — nothing invented over them.

Download now (ZIP)

  • Other versions198 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 198

    1. nextlevelbuilder/ui-ux-pro-max-skill★ 144ksame name
    2. Yeachan-Heo/oh-my-codex★ 34ksame name
    3. tokio-rs/toasty★ 3.3ksame name
    4. PaulWoitaschek/Voice★ 3.2ksame name
    5. joye61/pic-smaller★ 2.9ksame name
    6. oxsecurity/megalinter★ 2.6ksame name
    7. Infisical/agent-vault★ 2.5ksame name
    8. static-web-server/static-web-server★ 2.4ksame name
    9. SethGammon/Citadel★ 927same name
    10. Ohh-889/skyroc-admin★ 795same name

    188 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 banner-design, ui-styling 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.
    • lithStudySkill

      banner-design

      Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.

      Also in 32 projects that use this

    • MicrosoftSkill

      ui-styling

      Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.

      Also in 33 projects that use this

    • mayankjain1815-commitsSkill

      infra-audit

      Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.

      Also in 3 projects that use this

    • JetBrainsSkill

      slides

      Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.

      Also in 36 projects that use this

    • henrikthome-archSkill

      infra

      Manage all infrastructure for the Volos school project — Render (API backend), Cloudflare (DNS + Pages frontend), PostgreSQL database, and GitHub Actions workflows.

      Also in 3 projects that use this

    • MicrosoftSkill

      perf

      Speed and memory performance rules for Rust crates, the Node addon, webui-framework, and webui-router.

      Also in 5 projects that use this

  • In this repository49 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.