Design & frontend
15,938 rows, by stacks then stars
1,697 of these skill files have been read, by 1,179 distinct authors, and what they tell an agent counted. What Design & frontend authors agree on, and what they forbid
imtiazrayhan/agentscamp-library/skills/pagination-designer Skill
1★ repoDesign correct, scalable pagination (plus the filtering and sorting that ride with it) for a list endpoint — pick cursor (keyset) vs offset and justify it, define an opaque cursor with a unique tiebreaker so no row is skipped or repeated, return a consistent envelope, bound page size, and name the indexes the sort actually needs. Use when adding a list endpoint, when OFFSET pagination crawls on a large table, or when clients see duplicate or missing rows while paging.
imtiazrayhan/agentscamp-library/skills/property-test-designer Skill
1★ repoDesign property-based tests — generate hundreds of random inputs and assert invariants that must hold for ALL of them — to surface the edge cases hand-picked examples never reach. Use when code has a large input space (parsers, serializers, encoders, math, data transforms), when a bug keeps slipping through despite green example tests, or when you can't enumerate every case worth checking.
imtiazrayhan/agentscamp-library/skills/rate-limiter-designer Skill
1★ repoDesign and implement API rate limiting that actually holds under load — pick the algorithm (token bucket vs sliding-window-counter vs fixed window) and justify it, choose the limiting key and per-tier limits, use cross-instance atomic storage, and return standard 429 signals. Use when protecting an API from abuse or scrapers, enforcing per-tier quotas, or replacing an in-memory limiter that breaks behind multiple replicas.
imtiazrayhan/agentscamp-library/skills/rbac-designer Skill
1★ repoDesign the authorization model itself — fine-grained permissions on resources composed into roles, with the right amount of resource/tenant scoping — instead of scattering role-name checks through handlers. Use when building multi-user or multi-tenant authorization, when `if user.isAdmin` checks are sprawling across the codebase, or when 'who can do what' needs a real model rather than ad-hoc gates.
imtiazrayhan/agentscamp-library/skills/semantic-cache-designer Skill
1★ repoDesign a semantic cache for LLM responses — serve a cached answer when a new query is similar enough to a past one — to cut cost and latency on repetitive traffic, with the similarity threshold calibrated on real query pairs and a cache key that prevents cross-user/model leaks. Use when an LLM app sees many near-duplicate prompts (FAQs, support, search), when token spend on repetitive queries is high, or when latency on common questions matters.
imtiazrayhan/agentscamp-library/skills/structured-logging-designer Skill
1★ repoDesign a structured (JSON) logging strategy with a stable field schema, correlation-ID propagation, and a disciplined level policy — then migrate ad-hoc string logs toward it. Use when logs are unsearchable plain text, when debugging a request across services means grepping multiple log streams by hand, or when standing up logging for a new service.
Claude design animation capture
Jody09-dotcom/constructionx-skills/skills/claude-design-animation-capture Skill
1★ repoConvert a Claude Design Animation export (ZIP or folder) into a clean 1080x1920 H.264 MP4 ready for Reels, Shorts, TikTok, or any social upload. Use when the user asks for "render claude design", "capture animation export", "mp4 from claude design", "claude design to video", "export animation to mp4", or has a Claude Design Animation ZIP and wants a video file. Bridges the gap that Claude Design has no native MP4 export. Spins up a tiny local HTTP server to serve the React+Babel HTML, drives Playwright to record at the requested dimensions, runs ffmpeg to crop/trim/transcode. Requires Playwright and ffmpeg installed locally.
vindm/dotclaude/plugins/design/skills/design Skill
1★ repoElicit the project's design north-star + design-system reference (the two artifacts the consumed design audits read at runtime); no agent copies are authored. Derived from the project's actual UI surfaces, the user's named design benchmarks, and past design failure modes. Invoke /dotclaude:design in any project root that has a human-facing surface.
vindm/dotclaude/plugins/design/skills/iterative-polish-autoloop Skill
1★ repoDrive a multi-screen flow from raw to award-quality through a bounded iterative loop — reset to a clean fixture, capture every state, grade across three scrutiny layers (reviewer agent + composition scan + backend-truth probe), apply ONE highest-ROI fix, commit atomically, re-run — until award-quality OR a hard iteration cap. Invoke for iterative UI/UX polish on a flow with an auto-capture harness.
vindm/dotclaude/plugins/design/skills/persona-testing Skill
1★ repoRun three orthogonal outside-eyes tests on every user-visible string — day-30 (frequency-jaded), partner (voice-register), and stranger (already-knows-me) — to catch voice violations that pass a deny-list but still feel wrong. Load at design time on every proposed string and at audit time on every visible string on a captured surface.
franzos/claude-plugins/plugins/forseti/skills/setup Skill
1★ repoUse to set up a new Forseti deployment (the web UI and OIDC front-end for the Ory Kratos + Hydra stack), with or without Docker. Brings up the Ory stack and Postgres, generates secure Kratos/Hydra/Forseti config with fresh secrets, wires the mandatory keys (audit webhook token, cookie secret, admin allowlist, service URLs), seeds an admin, and verifies the instance boots and the login flow works. Triggers: installing Forseti, first-time setup, standing up the Ory stack, getting Forseti running.
simanam/theaiteam/team/skills/design/accessibility Skill
no license1★ repoDesign, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).
The same file is in 3 other repositories
simanam/theaiteam/team/skills/design/canvas-design Skill
no license1★ repoCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
The same file is in 38 other repositories
simanam/theaiteam/team/skills/design/frontend-design Skill
no license1★ repoCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
The same file is in 39 other repositories
simanam/theaiteam/team/skills/design/theme-factory Skill
no license1★ repoToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
The same file is in 46 other repositories
simanam/theaiteam/team/skills/design/web-artifacts-builder Skill
no license1★ repoSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
The same file is in 33 other repositories
simanam/theaiteam/team/skills/qa/webapp-testing Skill
no license1★ repoToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
The same file is in 45 other repositories
cabbagecachekid/neon-jetpack/skills/using-neon-jetpack Skill
1★ repoUse when any writing, review, research, or shipping task begins — reviewing, polishing, or shipping human-facing writing or web pages, mapping a user journey, or protecting creative work. Routes to the right neon-jetpack skill (line-edit, ai-written-check, cringe-check, full-review, ux-web-design-review, journey-map, copyright-creative-work) and defines how they chain, so the right depth of review runs in the right order.
cabbagecachekid/neon-jetpack/skills/ux-web-design-review Skill
1★ repoUse when reviewing a website, web page, screenshot, or web copy against UX best practices grounded in human behavior rather than current fashion — auditing readability, scannability, visual hierarchy, cognitive load, or trust, separating what's evidence-backed from what's merely in style, with every claim tied to a real cited source. Triggers include "how strong is this page," "review my site's UX," "is this good design or just trendy," "evidence-based UX check," or asking whether a layout/copy follows web usability research.
SkillMedev/content-marketing-engine/skills/landing-page-copy Skill
1★ repoWrite landing-page copy section by section - hero, social proof, features-as-benefits, objections, CTA - leading with one promise and proving it down the page. Use when someone asks "write my landing page", "improve my hero headline", "what should the homepage say", "turn these features into benefits", or is shipping a new page for a launch or campaign. Do NOT use for testing and optimizing an existing page's conversion rate - use landing-page-cro instead; for the one-line claim itself use positioning-statement; for the full message ladder use messaging-hierarchy.
The same file is in 4 other repositories
SkillMedev/document-studio/skills/one-pager-designer Skill
1★ repoWrites a decision-driving one-pager - problem, evidence, impact, and a specific ask compressed into a single page readable in under three minutes. Use when someone asks "turn this into a one-pager", "write a brief for leadership", "I need a one-page pitch for this decision", or is preparing a document a busy reader must act on from one page. Do NOT use for a client-facing sales proposal with pricing and scope - use sales-proposal-writer instead; for condensing an existing long document use executive-summary; for multi-slide narratives use slide-deck-builder.
The same file is in 1 other repository
MattModeCode/claude-skills/skills/mashuai-brand Skill
1★ repoThe MashuAI brand system — the single source of truth for how anything under the MashuAI umbrella looks, reads, and feels (logo, colour, typography, UI components, voice). Load this skill whenever you build, design, style, or write copy for ANYTHING visual or brand-facing: websites, web apps, dashboards, React components, HTML pages, landing pages, UI mockups, app icons, n8n workflow diagrams, marketing material, or product names. Also trigger on "use my brand", "MashuAI style", "make it look good", "make it on-brand", "dark theme", "our colours", or any request that produces something a user will see. This brand is dark, minimal, and quietly technical. Never guess at colours, type, or layout — always apply this skill.
luminary19/atelier/skills/atelier-data Skill
no license1★ repoOn-demand reference DATA for the Atelier suite — a local, searchable (BM25) library of per-industry color palettes, font pairings, UI-style definitions, product-type design reasoning, landing-page patterns, chart guidance, and current Next.js / React / shadcn / Vue / Three.js do-and-don't tables. Use it to look up STARTING POINTS and cross-checks (e.g. "a starting palette/fonts/style for a fintech dashboard", "what does shadcn recommend for forms", "design reasoning for a SaaS product type", "search the design dataset"), or to feed a rubric into a review. It is a lookup tool, NOT a decision-maker: defer final craft to atelier-direction / atelier-foundations / atelier-typography / atelier-layout / atelier-components, and the compliance gate to atelier-perf-a11y / atelier-review. Do not use it as a token engine (it emits raw hex, not OKLCH) or as a code auditor (it cannot read your files).
luminary19/atelier/skills/atelier-dataviz Skill
no license1★ repoAtelier suite — the data-visualization layer. Turn data into charts that read clear and premium, not rainbow slop: choose the right chart for the question, encode values honestly (position > length > color), build on the house stack (shadcn Charts/Recharts → Tremor → visx/D3 → ECharts), strip to signal (restrained axes/legends/grid, direct labels, tabular number formatting), and ship ACCESSIBLE charts (keyboard, data-table fallback, real alt/aria, reduced-motion) — because canvas/SVG is invisible to screen readers. Use whenever building or fixing a chart, graph, plot, sparkline, KPI/metric/stat, gauge, heatmap, or the data *inside* a dashboard — or when a visualization looks cluttered, misleading, 3-D, or generic. Pulls categorical/sequential/diverging palettes from atelier-foundations; the dashboard *shell* + KPI-card layout is atelier-components; gated by atelier-perf-a11y. This is the canonical home for charting craft — prefer it over reaching for a chart lib blindly. Part of the Atelier suite.
luminary19/atelier/skills/atelier-direction Skill
no license1★ repoAtelier suite — the art-direction brain. Decide the design direction BEFORE writing any frontend code: which aesthetic, which "world" (production vs award-grade), the concept, the palette mood, type voice, motion budget, layout archetype, and signature moment. Produces a Direction Doc scaled to the task (a one-line read for small tweaks, a full one-pager for substantial builds/redesigns) that the rest of the suite (atelier-foundations, atelier-typography, atelier-layout) consumes. This is the canonical Atelier entry point — prefer it over older/general design skills. Use this FIRST whenever building a new website, landing page, web app, dashboard, portfolio, or editorial site — or deciding the look/feel/aesthetic of one — and ESPECIALLY whenever frontend output risks looking generic, templated, or "AI-made." If the user mentions design, UI, a new page, a look/vibe, an aesthetic, names a reference site, or wants to see several distinct creative directions to choose from (a moodboard of options), start here. For upgrading or redesigning an EXISTING site or app, start with atelier-redesign instead — it audits first, then pulls this skill in to set the new direction.
luminary19/atelier/skills/atelier-foundations Skill
no license1★ repoAtelier suite — the design-system engine. Build the token foundation that makes a frontend look coherent and "expensive": a perceptual OKLCH color system (ramps + semantic tokens + accessible dark mode), a modular + fluid type scale, an 8-point spacing scale, and depth (radii, shadows, grain). Outputs ready-to-use CSS custom properties, Tailwind v4 @theme (mapped to shadcn/ui theme variables), or W3C/DTCG design tokens. Use this whenever starting any frontend that needs a consistent visual system, when building a color palette / design tokens / chart & data-viz palettes / theme / dark mode, or when colors, spacing, or sizing feel inconsistent, muddy, or generic. Run after atelier-direction; before building components. (Choosing and setting the actual fonts → atelier-typography; scaffolding and building components → atelier-components.)
luminary19/atelier/skills/atelier-layout Skill
no license1★ repoAtelier suite — premium layout & composition. Structure pages and sections so they read intentional and "expensive": choose the right layout archetype, build it with modern CSS (Grid, Subgrid, Flexbox, container queries), apply composition models (rule of thirds, F/Z patterns, asymmetry/broken grid), use Gestalt grouping and clear visual hierarchy, and deploy generous active whitespace. Use this whenever laying out a page or section, building a grid / bento / dashboard / hero, making something responsive, or when a layout feels cramped, flat, centered-and-boring, or templated. Run after atelier-direction (layout archetype) using atelier-foundations spacing tokens.
luminary19/atelier/skills/atelier-motion Skill
no license1★ repoAtelier suite — motion & micro-interactions (the "feel" layer). Add animation that reads premium, not gimmicky: correct easing/spring defaults, the right durations, the 12 animation principles applied to UI, component/gesture/layout/exit animation with Motion (motion/react), micro-interactions (buttons, toggles, likes), and the often-skipped states (skeleton/shimmer, optimistic UI, empty/loading/error). Use whenever adding or fixing UI animation, transitions, hover/press feedback, loading states, or when motion feels janky, abrupt, excessive, or cheap. Default stack: Motion for React UI — with Anime.js v4 / native CSS / GSAP for vanilla & non-React work, and Lottie / Rive for designer-authored assets; defer scroll-driven work to atelier-scroll and pre-ship checks to atelier-perf-a11y. Part of the Atelier suite.
luminary19/atelier/skills/atelier-perf-a11y Skill
no license1★ repoAtelier suite — the performance & accessibility gate. The cross-cutting quality bar every Atelier build passes before it ships: animate only compositor-safe properties, hit Core Web Vitals (LCP ≤2.5s, CLS ≤0.1, INP ≤200ms), respect prefers-reduced-motion, meet WCAG 2.2 AA (contrast, focus, keyboard, target size, semantics, screen readers), give canvas/WebGL accessible fallbacks, and run the anti-slop "AI Tells" design-integrity check. Use whenever finishing or reviewing a frontend, optimizing performance / Core Web Vitals / Lighthouse, fixing jank or layout shift, doing an accessibility/a11y audit, handling reduced motion, running a pre-ship check, or checking whether a build reads as AI-generated/templated. This is the canonical home for the perf/a11y rules the other Atelier skills reference. Part of the Atelier suite.
luminary19/atelier/skills/atelier-redesign Skill
no license1★ repoAtelier suite — audit & upgrade existing sites/apps to premium without breaking them. Audit-first: inventory the current brand/IA/stack, name the specific AI-slop tells and the missing "expensive" levers, score gaps by impact vs risk, then apply the Atelier suite (direction → foundations → type → layout → motion → components → scroll/webgl) selectively, preserving functionality, content, SEO, and accessibility, and verifying with the perf/a11y gate. Use whenever improving, modernizing, polishing, or redesigning an existing website or app, fixing a design that looks dated/generic/templated/cheap, or doing a UI audit. This is the front door for EXISTING-site work — start here rather than atelier-direction when the site/app already exists; it brings the rest of the suite (direction included) in as needed. Supersedes older redesign skills. Default stack: Tailwind v4 + shadcn. Part of the Atelier suite.
luminary19/atelier/skills/atelier-review Skill
no license1★ repoAtelier suite — the adversarial pre-ship review. A full multi-step red-team of a FINISHED frontend build: fan out independent reviewers across dimensions (accessibility, performance, motion/reduced- motion, design-integrity/anti-slop, code quality), adversarially verify every finding to kill false positives, verify live in a real browser, synthesize a prioritized fix list, apply serially, and re-verify. Built to run with the ordinary Task/subagent tool — it does NOT require ultracode/Workflow. Use whenever a substantial build is "done" and needs a real audit before shipping, when asked to review / red-team / audit / "is this ready to ship" / find problems / pre-ship review a frontend. This is the heavyweight, adversarial counterpart to the atelier-perf-a11y self-checklist. Part of the Atelier suite.
luminary19/atelier/skills/atelier-scroll Skill
no license1★ repoAtelier suite — scroll choreography & advanced interaction. Build award-grade scroll experiences: smooth/inertia scroll (Lenis), scroll-triggered reveals, scrubbing, pinning, horizontal sections, sticky-stacking cards, parallax, native CSS scroll-driven animations, page/route transitions (View Transitions API), infinite marquees, magnetic buttons, and custom cursors. Use whenever adding scroll-based animation or storytelling, smooth scrolling, parallax, pinned/horizontal sections, page transitions, marquees, or custom/magnetic cursors — or when scroll feels static, abrupt, or janky. Default stack: GSAP + ScrollTrigger + Lenis, with native CSS scroll-driven animations as progressive enhancement. Honors prefers-reduced-motion. Part of the Atelier suite.
luminary19/atelier/skills/atelier-typography Skill
no license1★ repoAtelier suite — expensive typography. Choose and pair fonts with a point of view, build a fluid modular type scale, control tracking/leading/measure, switch on the right OpenType + variable-font features, set editorial detail (drop caps, pull quotes, hierarchy), tune font loading for zero layout shift, and animate type (kinetic / scroll-driven) tastefully. Use this whenever typography matters: picking or pairing fonts, headings that feel generic or "default Inter/Playfair," body readability, display type, variable fonts, font loading / FOUT / web-font CLS, RTL & non-Latin (CJK) type, numbers in tables, or animated/kinetic text. Run after atelier-direction (type voice) and alongside atelier-foundations (which owns the scale tokens).
luminary19/atelier/skills/atelier-ux Skill
no license1★ repoAtelier suite — the UX architecture & flows layer (planning-first). Decide how a product is STRUCTURED before any page is styled: the information architecture (content/feature inventory, grouping, sitemap, labels in the user's words), the navigation model (top-nav / sidebar / tab-bar / hub-and-spoke, URL structure, breadcrumbs, search), the critical user flows (signup → activation, the core task, checkout) with their dead-ends and decision points, and the five states every screen must handle (ideal / empty / loading / error / partial). Produces an IA + Flow artifact — analogous to the Direction Doc — that atelier-layout realizes as page structure and atelier-components builds. Use whenever structuring a new app/product/site, deciding what pages or screens exist and how they connect, designing a user flow, journey, navigation model, sitemap, onboarding/activation, or progressive disclosure — or when a product feels confusing, disorganized, or full of dead-ends. Runs right after atelier-direction: ux owns structure, direction owns aesthetic, layout owns the visual grid. Part of the Atelier suite.
luminary19/atelier/skills/atelier-webgl Skill
no license1★ repoAtelier suite — 3D, WebGL & shader craft (the flagship layer). Build award-grade 3D and generative graphics: React Three Fiber + Drei scenes, hand-written GLSL/TSL shaders (fresnel, fbm noise, mesh gradients, distortion, dithering), WebGPU via WebGPURenderer, Spline integration, Gaussian splatting, faux-3D, and WebGL image hover/scroll distortion — always with lazy-loading, static fallbacks, and accessibility. Use whenever building 3D scenes, WebGL/Three.js/R3F, shaders/GLSL, a 3D or generative hero, product viewers, shader gradients/grain/distortion, Spline scenes, Gaussian-splat / radiance-field scenes, or interactive 3D graphics. Default stack: React Three Fiber + Drei; vanilla Three.js / OGL for non-React or shader-only work. Gate everything with atelier-perf-a11y. Part of the Atelier suite.
luminary19/atelier/skills/codex-imagegen-taste Skill
no license1★ repoPremium, anti-slop DESIGN layer over /codex-imagegen: turn a brief into an art-directed, one-image-per-section website comp (landing page, hero, full mockup, design reference) by injecting a taste preamble + a locked house style into EACH call of the codex-imagegen helper. This is the BRAIN (what to draw, how, anti-slop); /codex-imagegen stays the HANDS (renders key-free via the local Codex CLI and finds the PNG). Use when asked for a "landing page mockup", "full website comp", "hero image", "premium UI mockup", "design reference image", or "make a nice <page> image". DEFER to bare /codex-imagegen for a quick moodboard, a single abstract sketch, a simple icon/texture/logo, or atelier-direction's 8-direction board - those do NOT need the taste layer.
luminary19/atelier/skills/forge-animate Skill
no license1★ repoForge suite — animation craft layer. Authors keyframes and F-curves, sets interpolation and easing (BEZIER/BACK/ELASTIC/BOUNCE), builds NLA clip libraries, bakes IK/constraint/sim motion to raw TRS keys, and exports skeletal + morph (blend-shape) animation to glTF/GLB, FBX, and USD formats — all headlessly from bpy Python. Use whenever animating objects or armatures, setting up keyframes, editing F-curve handles, choosing easing (ease-in-out, overshoot, bounce, spring), creating looping idles (Cycles modifier), adding camera shake (Noise modifier), baking IK/constraints before export, building NLA multi-clip sequences, exporting animated GLB for Three.js/R3F/Godot/Unity/UE5, or producing USD SkelAnimation. Also use for morph target / shape-key animation. Web/mobile compression of the exported GLB is forge-optimize's job (always Meshopt, never Draco, for animated/morph assets) — this skill hands off to it, it does not run gltf-transform itself. Run = call the Skill tool with the exact name. Saying "now run forge-X" in prose runs nothing. HEADLESS-ONLY: driven from code, output verified by reading a PNG. Part of the Forge suite.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-prevention-design Skill
1★ repoConverts a systemic root cause into EXACTLY ONE concrete, buildable guard — a test, validation, checklist item, or gate — with a named owner, a home ("where it lives"), and a build-now/follow-up call. Use for the Prevention step of a SEV1/rollback RCA session, when turning a root cause into a safeguard, or when a proposed prevention is vague ("be more careful", "review better"). Rejects wish-lists and unbuildable preventions; picks the single guard that kills the whole failure class. Called by rca-session-facilitator; usable standalone.
jpoindexter/typography-skills/skills/design-token-generation Skill
1★ repoTypography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.
jpoindexter/typography-skills/skills/editorial-web-typography Skill
1★ repoTypography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.
jpoindexter/typography-skills/skills/international-typography Skill
1★ repoTypography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.
jpoindexter/typography-skills/skills/motion-typography Skill
1★ repoUse when type moves or changes over time — animated headlines, kinetic type, text transitions, animated or responsive logotypes, scroll-driven text effects, typing/counting animations, variable-font axis animation, or loading and streaming text. Also use when motion is making text hard to read, causing discomfort, or failing reduced-motion and accessibility requirements.
jpoindexter/typography-skills/skills/responsive-typography Skill
1★ repoTypography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.
jpoindexter/typography-skills/skills/type Skill
1★ repoUse when the user invokes /type, or when any task involves setting, choosing, scaling, spacing, loading, tokenizing, auditing, or critiquing type — a font choice, a type scale, body copy, headings, a data table, a UI label, responsive text, webfont performance, or non-Latin script. Also use when a screen "looks off" and the cause may be typographic. Dispatcher that routes to the focused typography-* skills.
jpoindexter/typography-skills/skills/typography-accessibility Skill
1★ repoUse whenever type carries information — always co-load this with body text, UI, and editorial typography work. Specifically for contrast, 200% zoom, user text-spacing overrides, Dynamic Type, dyslexia and low-vision needs, screen-reader compatibility, images of text, and any claim that typography is "accessible".
jpoindexter/typography-skills/skills/typography-audit Skill
1★ repoUse when systematically reviewing existing typography against criteria — "check this page", "audit our type", pre-launch review, design-system compliance, or inherited work of unknown quality. Produces a pass/fail finding list with evidence. Use typography-critique instead when the question is about taste rather than compliance.
jpoindexter/typography-skills/skills/typography-critique Skill
1★ repoUse when the question is quality or taste rather than compliance — "is this any good", "does this feel right", "why does this look generic or AI-generated", art-direction review, or judging whether a typographic risk pays off. Use typography-audit instead when checking against defined criteria.
jpoindexter/typography-skills/skills/typography-layout-systems Skill
1★ repoUse when composing type in space rather than sizing it — deciding how a poster, hero, editorial spread, dashboard, or landing page is structurally organized. Also use when a layout feels arbitrary, elements float without relationship, a grid is being applied by reflex, or a composition needs deliberate tension or movement.
jpoindexter/typography-skills/skills/ui-component-typography Skill
1★ repoTypography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.
pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/test-design Skill
no license1★ repoWhat to test and how — regression test fails first, boundary tables, behavior over implementation, boundary-only mocks, the mock-echo trap. Use when writing tests, adding regression coverage for a fix, or judging whether existing tests protect anything.
pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/verify-ui-visually Skill
no license1★ repoVerify UI changes by rendering and looking — screenshot, browser, or running app — never by reading the markup and imagining it. Use after any change to components, styles, layouts, templates, charts, emails, or generated documents/images.
praveentewatia26/award-grade/skills/motion-choreography Skill
1★ repoDesigns a project's complete motion system — token sheet, orchestration patterns, tool selection, spring tuning, scroll choreography, and reduced-motion parallel track — turning the suite's motion canon into project-grade choreography an agent can implement without inventing timing values. Owns the TIMING SYSTEM transitions obey (durations, easing, overlap), not the transition technique itself. USE WHEN: "design a motion system", "animation feels random/inconsistent", "pick durations and easings", "should I use GSAP or Framer Motion or CSS", "stagger this list", "what timing should transitions between states share", "scroll-linked animation", "scrub this timeline to scroll", "spring feels wrong / too bouncy", "make this hero breathe", "animate layout change without jank", "FLIP animation", "reduced-motion version", "animations are janky / dropping frames", "orchestrate enter and exit".
praveentewatia26/award-grade/skills/ux-narrative Skill
1★ repoStructures award-grade sites so they convert — narrative arcs for landing pages, information architecture that survives heavy art direction, delight budgeting, and calm conversion flows inside designed worlds. USE WHEN: "structure this landing page", "what's the story of this site", "our beautiful site doesn't convert", "plan the scroll narrative", "map sections to story beats", "information architecture for a creative site", "users get lost in the experience", "where should the wow moment go", "the form feels off-brand", "content strategy before design", "how long should this page be", "run a 5-second test", "rank which interactions to keep", "mobile version of this narrative", "scroll-depth drop-off analysis".
praveentewatia26/award-grade/skills/video-motion-studio Skill
1★ repoProduces programmatic video, motion graphics, and product film for the web — Remotion compositions, product teasers, kinetic-type captions baked into a rendered film, Lottie/Rive motion assets, polished screen-capture demos, and scroll-scrubbed video, all cut to web performance budgets. USE WHEN: "make a product teaser video", "create a launch video", "animate this demo recording", "build a video with Remotion", "kinetic-type captions for this video/teaser", "turn this screen recording into a polished demo", "should I use Lottie or Rive", "add a hero video to the site", "scroll-scrubbed video section", "render 15 and 30 second cuts", "captions for muted autoplay", "explainer animation for this feature", "app store preview video", "video is too heavy, fix it".
praveentewatia26/award-grade/skills/wow-director Skill
1★ repoRuns the full award-grade agency pipeline as a creative director — boots from the project taste ledger (design/TASTE.md) so settled taste stays settled, interrogates the brief down to one feeling, forces a choice between three concept territories, commits to a single signature moment, assigns sibling skills and budgets, and drives the build/judge/ship loop until verified numbers exist. USE WHEN: "build me an award-worthy site", "make this feel like an Awwwards winner", "design a landing page that people remember", "I have a brief, where do we start", "plan a portfolio site with wow factor", "creative direction for this product page", "which effects should this site have", "orchestrate a full redesign", "our site looks generic, direct a rework", "pitch me three creative directions", "what's the signature moment for this project", "scope this design engagement", "assemble the design pipeline for this app", "turn this Figma into something jury-grade".
kaustavr19/claude-skills/skills/competitive-benchmark Skill
1★ repoBenchmark a brand's website against named competitors and synthesise a strategic direction. Detects business model (B2B / B2C / D2C / marketplace) and scores every site across seven axes — visual design, UX writing, brand voice & positioning, conversion hooks, IA & journey, social proof & trust, and differentiation — producing a comparison matrix plus a synthesis of what to STEAL, DIFFERENTIATE, and AVOID. Orchestrates the visual-aesthetics-audit, ux-writing, and ux-audit skills for depth; hands off to product-requirements or market-intelligence to build. Use whenever the user shares their site AND one or more competitor sites and wants a comparison, benchmark, or teardown. Triggers: "benchmark my site against these", "how do I compare to competitors", "what are they doing better", "what should I steal / avoid / do differently". Distinct from market-intelligence (business/pricing strategy) — this is about the website and digital experience layer.
kaustavr19/claude-skills/skills/ux-audit Skill
1★ repoPerform a thorough, professional UI/UX audit of any existing website or web product. Runs a CORE six-framework audit by default — Nielsen's 10 Heuristics, WCAG 2.2 Accessibility, Gestalt, UX Writing & Microcopy, Mobile/Responsive, and Performance & Core Web Vitals — and offers optional DEEP LENSES on request: Classic Usability Extended (Shneiderman, Gerhardt-Powals, Bastien & Scapin), Behavioural Laws (Hick's, Fitts's, Miller's, Jakob's, Peak-end), Trust & Persuasion (Fogg, Cialdini), and Interaction Design Principles (Norman, Tognazzini). Produces a markdown report with severity tiers, RAG status, fix recommendations, and effort estimates. Use whenever the user wants to audit, review, or critique a website, app, or web product's UI/UX — including "roast my site", "review this product", "what's wrong with this UI", "give me a UX review". Also trigger when the user shares a URL or screenshots for design feedback, or asks for a persuasion / behavioural-psychology / cognitive-load / dark-pattern review.
kaustavr19/claude-skills/skills/visual-aesthetics-audit Skill
1★ repoCritique and audit the visual aesthetics of any existing UI from screenshots and/or URLs. Evaluates six dimensions: typography & type hierarchy, colour system & palette harmony, spacing/rhythm/layout, motion & microinteractions, iconography & illustration style, and overall visual personality & brand cohesion. Benchmarks against design systems (Material, Apple HIG, Fluent), design movements (Swiss, Bauhaus, Brutalism), and industry peers. Outputs diagnosis + specific fix values (hex, type scale, spacing) + inspiration refs. Adapts output: written brief, design tokens, or critique report as needed. Trigger when user shares screenshots or URL and asks about visual quality, aesthetics, look and feel, or design critique. Also trigger for "roast my design", "aesthetic audit", "visual critique", "does this look good", "what's off", or "how do I make this feel more premium/modern/cohesive".
omarfarahatoglu-tur/ai-agent-skills/skills/ai-team/rag-system-designer Skill
1★ repoOpen-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.
omarfarahatoglu-tur/ai-agent-skills/skills/frontend-team/frontend-architect Skill
1★ repoOpen-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.