frontend-design
Skill0 starsChanged 3 months agoMITView on GitHub
Create distinctive, production-grade frontend interfaces with high design quality. Load when building web components, pages, layouts, dashboards, landing pages, React components, Astro sites, Streamlit apps, Python dashboards, HTML/CSS artifacts, or any task where visual quality matters — including styling, redesigning, implementing from a mockup, or choosing a component library. Also load it when the user says "make this look good", "style this", or "build a UI for X". Avoids generic AI aesthetics. Do NOT trigger for backend, data pipeline, CLI, or document-only tasks.
187 other projects use a version of this, 110 of them edited.
Adopted by
Most recently taken up by
- RostislavDugin/postgresustheir own version, first seen Nov 8, 2026
- databasus/databasustheir own version, first seen Nov 8, 2026
- ceilf6/FrontAgenttheir own version, first seen Nov 8, 2026
- maxtrigify/Ottotheir own version, first seen Nov 8, 2026
- rvdbreemen/OTGW-firmwareedited, first seen Nov 8, 2026
- open-slide/open-slideedited, first seen Nov 8, 2026
Used with
Projects with it also use instantly-campaign, albert-dm and 10 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.
yawningwhaleAISkillinstantly-campaign
Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.
Also in 6 projects that use this
yawningwhaleAISkillalbert-dm
Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).
Also in 5 projects that use this
naman10parikhSkillecosystem-reference
Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.
Also in 5 projects that use this
naman10parikhSkillfractal-delegation
Also in 5 projects that use this
julianoczkowskiSkillbrief-to-tasks
Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".
Also in 7 projects that use this
SeifBenayedSkillfile-reading
Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.
Also in 6 projects that use this
- +6 more from naman10parikh
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 110
- novuhq/novu★ 40k11% same
- Dokploy/dokploy★ 38k12% same
- 1weiho/open-slide★ 9.7k11% same
- open-slide/open-slide★ 9.7k11% same
- basketikun/infinite-canvas★ 9.5k11% same
- mfts/papermark★ 9.2k11% same
- papermark/papermark★ 9.2k11% same
- anbeime/skill★ 7.9k10% same
- midudev/preguntas-entrevista-react★ 7.8k11% same
- steipete/agent-scripts★ 7.4k10% same
100 more not listed
Wrote their own version · 77
- anthropics/skills★ 189ksame name
- bytedance/deer-flow★ 85ksame name
- anthropics/claude-plugins-official★ 46ksame name
- markmead/hyperui★ 12ksame name
- mengxi-ream/read-frog★ 10ksame name
- databasus/databasus★ 9.3ksame name
- RostislavDugin/postgresus★ 9.3ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- BuilderIO/agent-native★ 7.6ksame name
67 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.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- data-workSkill
- geospatialSkill
- git-workflowSkill
- project-contractSkill
- python-devops-stackSkill
- research-protocolSkill
- review-protocolSkill
- setupSkill
- test-qualitySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
16 rules. 0 are common, 15 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 181 edited versions we read keep these.
15
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
- Distinctive: line 14
Before any aesthetic decision, determine the surface type.
- Distinctive: line 25
Avoid generic AI aesthetics, but don't break an established product language for the sake of differentiation
- Distinctive: line 27
When no project design system exists, default to Brand-surface thinking.
- Distinctive: line 50
Commit to a cohesive palette via CSS custom properties.
- Distinctive: line 62
Create atmosphere and depth: gradient meshes, noise/grain overlays, geometric patterns, layered transparencies, dramatic shadows, …
- Distinctive: line 91
Every design decision must be verifiable against the full constraint list before writing code.
- Distinctive: line 95
When given a screenshot or mockup:
- Distinctive: line 99
Ask if ambiguous: "Should I match this exactly or use it as inspiration?"
- Distinctive: line 103
After implementing, verify visually before declaring done.
- Very specific: line 111
Read the screenshots with the image tool to analyze them.
- Distinctive: line 113
User screenshots: when Playwright is not available or when subjective assessment matters.
- Distinctive: line 115
Call out which viewports to check: mobile 375px, tablet 768px, desktop 1440px.
- Distinctive: line 121
Before writing any custom control, check in this order:
- Distinctive: line 132
Read the design context (tokens, layout, component structure)
- Distinctive: line 135
Verify against the original design for fidelity
- Distinctive: line 137
Do not blindly import generated code — it bypasses the project's component architecture, accessibility patterns, and styling conventions.
“Common” is measured: kept by at least 6 in 10 of the 181 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
Frontend Design
Guide for creating distinctive, polished frontend interfaces that avoid generic "AI slop" aesthetics.
The goal is working code with exceptional aesthetic intentionality — not beautiful in a generic way, but specifically designed for the context.
Surface Type
Before any aesthetic decision, determine the surface type. This changes which rules apply:
Brand surface (marketing, landing page, portfolio, campaign):
- Strong independent typography, bold visual direction, expressive color
- This is where distinctive fonts and dramatic aesthetics matter most
- Generic defaults are weakest here — audiences judge visual quality first
Product UI (app, dashboard, tool, admin):
- Established design system tokens take precedence: colors, typography, spacing, components
- System/product fonts (Inter, Roboto, system fonts) are fine when they belong to the existing design system
- Readability, information density, and consistency beat visual distinction
- Avoid generic AI aesthetics, but don't break an established product language for the sake of differentiation
When no project design system exists, default to Brand-surface thinking.
Design Thinking (Before Code)
Pause and decide before writing any CSS or HTML. Rushing to code before committing to a direction produces mediocre output — the aesthetic decisions are the hard part.
- Purpose — what problem does this interface solve? Who uses it?
- Aesthetic direction — commit to ONE clear tone. Examples:
- brutally minimal, maximalist, retro-futuristic, organic/natural
- luxury/refined, playful, editorial/magazine, brutalist/raw
- art deco/geometric, soft/pastel, industrial/utilitarian Pick an extreme and execute it with precision. Bold maximalism and refined minimalism both work — the key is intentionality, not intensity.
- Constraints — framework, performance budget, accessibility level
- Signature element — what single thing makes this memorable?
Aesthetic Guidelines
Typography
Choose distinctive, characterful fonts. Pair a display font with a refined body font. For new surfaces without an existing design system: generic fonts (Inter, Roboto, Arial, system fonts, Space Grotesk) signal low effort — use Google Fonts or self-hosted alternatives. For product UI with an established design system: use the system tokens. Always specify fallbacks.
Color and Theme
Commit to a cohesive palette via CSS custom properties. Dominant color with sharp accents outperforms timid, evenly-distributed palettes. Purple gradients on white backgrounds are the cliché to avoid. Vary between light and dark themes across designs — no two should converge on the same defaults.
Motion and Interaction
CSS-only animations for HTML/vanilla projects — they're faster and simpler to maintain. Focus on high-impact moments: a staggered page-load reveal with animation-delay creates more delight than scattered micro-interactions. Add scroll-triggered effects and hover states that surprise. For React, use Motion (framer-motion) when available.
Spatial Composition
Break predictable layouts. Asymmetry, overlap, diagonal flow, and grid-breaking elements create visual interest. Generous negative space OR controlled density both work — avoid the mushy middle where neither reads clearly.
Backgrounds and Texture
Create atmosphere and depth: gradient meshes, noise/grain overlays, geometric patterns, layered transparencies, dramatic shadows, decorative borders. Flat solid-color backgrounds are only appropriate when that restraint IS the aesthetic direction.
Accessibility
Accessibility isn't optional — poor accessibility excludes users and is fixable with almost no visual cost.
- Semantic HTML: proper heading hierarchy, landmarks, lists
- Visible focus states on all interactive elements (don't remove outlines without replacing them)
- WCAG AA contrast minimum: 4.5:1 for body text, 3:1 for large text
- Descriptive
aria-labelon buttons and links when text alone is ambiguous - Screen-reader-friendly: visually hidden headings for navigation where needed
- Touch targets at least 44×44px on mobile
- Respect
prefers-reduced-motionfor animations
Negativregeln (Anti-Pattern Constraints)
These are hard constraints — any output matching these patterns is disqualified as "AI slop."
Read before generating any UI: references/anti-patterns.md
Quick reference (must never do):
- Inter, Roboto, Arial, system fonts, Space Grotesk as defaults
- Purple-blue gradient on white hero sections
- Generic card grids with identical rounded corners and shadows
- Single centered column layouts with no asymmetry
transition: all 0.3s easeon everything- Flat solid backgrounds without atmosphere or texture
- Any of the 5 specific combinations listed in the reference file
Every design decision must be verifiable against the full constraint list before writing code.
Working with Screenshots or Mockups
When given a screenshot or mockup:
- Analyze the visual language: colors, spacing, typography, hierarchy
- Identify the design system if present: recurring patterns, component conventions
- Reproduce with precision — match spacing, proportions, and visual weight
- Ask if ambiguous: "Should I match this exactly or use it as inspiration?"
Visual Verification
After implementing, verify visually before declaring done.
Self-service with Playwright (preferred when a dev server is running):
npx playwright screenshot http://localhost:3000 /tmp/ui-check.png
npx playwright screenshot --viewport-size="375,812" http://localhost:3000 /tmp/ui-mobile.png
npx playwright screenshot --viewport-size="1440,900" http://localhost:3000 /tmp/ui-desktop.pngRead the screenshots with the image tool to analyze them. Check Playwright is installed first (npx playwright install chromium).
User screenshots when Playwright is not available or when subjective assessment matters.
Call out which viewports to check: mobile 375px, tablet 768px, desktop 1440px.
See references/verification.md for the full responsive and accessibility QA checklist.
Reuse-first rule
Before writing any custom control, check in this order:
- Existing project components
- Chosen library or framework primitives
- Accessible primitives (Base UI, Radix, framework-native)
- Custom implementation — only when no existing source fits
Design-tool handoff
Figma, v0, or other design output is reference or authorized source material, not automatically production-ready code:
- Read the design context (tokens, layout, component structure)
- Map tokens to the project's theme system
- Rebuild components using the project's selected library and conventions
- Verify against the original design for fidelity
Do not blindly import generated code — it bypasses the project's component architecture, accessibility patterns, and styling conventions.
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
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.

