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
krlan/leverbrain/skills/claude-design Skill
no license1★ repoWeb3 skill marketplace for agents and operators
krlan/leverbrain/skills/kami Skill
no license1★ repoTypeset professional documents and product landing pages: resumes, one-pagers, white papers, letters, portfolios, slide decks, landing pages. Warm parchment, ink-blue accent, serif-led hierarchy. CN uses TsangerJinKai02, EN uses Charter, JA uses YuMincho (best-effort). Triggers on "做 PDF / 排版 / 一页纸 / 白皮书 / 作品集 / 简历 / PPT / slides / Marp / markdown slides / マークダウンのスライド / 落地页 / 官网 / landing page / product page", or "build me a resume / make a one-pager / design a slide deck / turn this into a PDF / make this presentable / create a landing page".
GustavoGutierrez/engineering-skills/skills/frontend-spec-writer Skill
1★ repoDesign complete frontend specifications from product requirements: UX flows, component hierarchies, component contracts (props/events), state management, responsive breakpoints, accessibility rules, and API integration mapping. Use when asking to design a frontend spec, component architecture, UI specification, or view specification.
GustavoGutierrez/engineering-skills/skills/observability-designer Skill
1★ repoTrigger: observability design, observability strategy, telemetry architecture, instrument a system, distributed observability, AI observability, workflow monitoring, design alerts. Design correlation-first observability strategies covering logs, metrics, traces, AI telemetry, and workflow visibility for distributed and AI-native systems.
GustavoGutierrez/engineering-skills/skills/workflow-designer Skill
1★ repoDesign state machines, orchestration workflows, saga patterns, and resilience strategies for distributed systems, AI agents, and complex async processes. Use when asking for a workflow, state machine, orchestration design, saga, HITL checkpoint, or process resilience strategy.
rmerk/crewai-headless-flow/.agents/skills/codebase-design Skill
1★ repoShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
The same file is in 19 other repositories
rmerk/crewai-headless-flow/.agents/skills/design-an-interface Skill
1★ repoGenerate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
The same file is in 15 other repositories
rmerk/crewai-headless-flow/.agents/skills/prototype Skill
1★ repoBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
The same file is in 6 other repositories
looties-io/looties-skills/cinematic-hyperframes Skill
1★ repoCinematic motion design workflow for Hyperframes/Hyperframer and HTML-to-video product films. Use when creating or revising SaaS, app, ecommerce, launch, social, or brand videos that need the /website-to-hyperframes or Website-to-Video pipeline, Hyperframes compositions, catalog-backed blocks/components/transitions, GSAP timelines, VFX-friendly motion, kinetic typography, responsive 16:9/9:16 variants, mock UI states, and export validation.
frankxai/starlight-design-intelligence/skills/design-audit Skill
no license1★ repoUse to review UI, websites, product screens, decks, screenshots, visual systems, or generated designs for hierarchy, usability, polish, brand fit, accessibility, and motion quality.
frankxai/starlight-design-intelligence/skills/design-system-extractor Skill
no license1★ repoUse to extract reusable design-system rules from an existing site, app, screenshot set, Figma file, brand pack, or repo.
frankxai/starlight-design-intelligence/skills/landing-page-polish Skill
no license1★ repoUse to improve landing pages, launch pages, homepages, waitlists, sales pages, and public product pages with premium hierarchy, proof, imagery, motion, and conversion clarity.
frankxai/starlight-design-intelligence/skills/motion-and-interaction Skill
no license1★ repoUse for premium motion and interaction design across FrankX, Starlight, Arcanea, and product UI: choreography, timing, state transitions, reduced-motion behavior, brand motion identity, and design-to-engineering handoff.
frankxai/starlight-design-intelligence/skills/product-ui-polish Skill
no license1★ repoUse to improve SaaS, dashboards, tools, portals, command centers, forms, tables, and repeat-use product UI for clarity, density, hierarchy, states, and interaction quality.
frankxai/starlight-design-intelligence/skills/typography-art-direction Skill
no license1★ repoUse when selecting, implementing, or reviewing type for a high-value web surface where font voice, hierarchy, licensing, performance, responsive line breaks, and fallback behavior affect brand quality.
frankxai/starlight-design-intelligence/skills/world-class-web-release Skill
no license1★ repoUse for any high-value website, landing page, homepage, partner page, product surface, brand experience, or redesign where language, typography, imagery, motion, implementation, and production proof must feel distinctive and human. Also use when upgrading a web-design quality system or release gate.
tdyzzsp47/claude-skills/skills/architecture-design Skill
1★ repo要件からアーキテクチャ設計・技術選定・ADR作成までを行うスキル。基本設計フェーズで「どう作るか」の骨格を固めるときに使う。
tdyzzsp47/claude-skills/skills/detailed-design Skill
1★ repo実装前に「手戻りが高くつく部分」だけを詳細化し、人間・エージェント問わず実装者が迷わず着手できる粒度の設計書を作成するスキル。機能追加・モジュール新設・API設計など実装委譲前に使う。
tdyzzsp47/claude-skills/skills/screen-design Skill
1★ repo要件定義から画面一覧・画面遷移図・ワイヤーフレーム・画面項目定義を作成するスキル。ユーザーストーリーを元に画面設計を行う際、または画面設計書の作成・レビューが必要な場面で使う。
tdyzzsp47/claude-skills/skills/ux-research Skill
1★ repoユーザーインタビュー・ユーザビリティテストを通じてユーザーの行動・課題・動機を明らかにするスキル。企画段階の課題発見からプロトタイプ検証・リリース前確認まで、定性リサーチが必要なタイミングで使う。
roronoazoroshao369/vibe-coding-os/skills/checklists/frontend-state-quality Skill
1★ repoFrontend state quality checklist for React, Vue, Svelte, stores, side effects, forms, and data fetching.
roronoazoroshao369/vibe-coding-os/skills/prompts/software-design-philosophy Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
ProdaZhang/aigd-zh/aigd-ui-capture Skill
1★ repoAIGD · 界面截图 → 界面 DSL(知识库捕获/工具1)。当要把游戏界面截图(竞品或自家)转成结构化 md(类型/层级/几何/交互/状态),以便 ui_render.py 还原成线框、并攒进 patterns/界面范式 知识库时使用。看图配方与文法的权威在 ../aigd/references/界面DSL规范.md;本 skill 只编排流程、不复制文法。是 aigd 包的一员。
ProdaZhang/aigd-zh/aigd Skill
1★ repoAIGD(AI Game Design)总入口 / 编排器。当用户要**从零开张一个游戏项目**、**不确定该用哪个阶段**、想**总览或推进整条研发流程**,或要**维护项目脊柱(项目档案/manifest)**时使用。本 skill 只做"读脊柱→判断进度→分派到对应子 skill";**已经明确某一步(立意/做系统/迭代/定稿/回写/截图入库)就直接用对应子 skill**(aigd-concept / aigd-system / aigd-iterate / aigd-handoff / aigd-sync / aigd-ui-capture)。方法论自带于 references/,不依赖具体项目。
duandigi/duandigi-growth-marketing-skill/skills/growth-loop-design Skill
1★ repoUse this skill when designing, auditing, or improving a compounding growth loop such as referral, review, content, SEO, product, community, partnership, user-generated content, or tool-led growth.
duandigi/duandigi-growth-marketing-skill/skills/growth-model-design Skill
1★ repoUse this skill when defining or revising a growth model, North Star Metric, input metrics, value moment, customer journey, or metric tree for a product, service, content business, marketplace, or multi-project portfolio.
cosmefae/claude-skills/skills/figma-shadcn-hygiene Skill
1★ repoAnalyzes and cleans up the selected Figma frame to make it semantic, consistent, predictable, and ready for structural handoff. This skill is Figma-only. It standardizes naming, taxonomy, auto layout, and token gaps. It does not generate code or decide final visual match.
cosmefae/claude-skills/skills/figma-shadcn-visual-match Skill
1★ repoRuns the Figma → shadcn → code pipeline with a visual fidelity gate. Consumes the Hygiene Report, implements components, generates screenshots (Figma and local), classifies diffs (blocker/major/minor), and iterates until approval.
po4yka/llm-wiki-skills/skills/llm-wiki-design Skill
1★ repoDesign a custom LLM-Wiki implementation, CLI, Obsidian plugin, repo-docs agent, team workflow, or product architecture. Use when the user wants to build their own system and needs data model, retrieval tier, provenance, storage, sync, review, agent integration, or MVP planning.
po4yka/llm-wiki-skills/skills/llm-wiki-human-first-design Skill
1★ repoDesign or audit an LLM-Wiki so it remains useful to humans without agents. Use when the user fears an agent-generated document dump or a new Confluence-like mess, or needs human-readable page contracts, navigation maps, and agent-free acceptance tests.
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/persona-ip-analyst Skill
1★ repoIP-analyst persona for the FlowLeap CLI — technology-landscape mapping, portfolio assessment, white-space identification, and filing-trend analytics. Trigger when the user asks the agent to act as an IP analyst, map a landscape, assess a competitor portfolio, or report patent filing trends.
The same file is in 1 other repository
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/persona-patent-attorney Skill
1★ repoPatent-attorney persona for the FlowLeap CLI — prior-art search, claim-scope analysis, and freedom-to-operate clearance. Trigger when the user asks the agent to act as a patent attorney, review prior art, analyze claim scope, or clear FTO for a product.
The same file is in 1 other repository
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/persona-researcher Skill
1★ repoResearcher persona for the FlowLeap CLI — parallel academic-literature and patent exploration to map what is published versus what is protected. Trigger when the user asks the agent to act as a researcher, survey a technology across papers and patents, or find gaps between academic work and filed IP.
The same file is in 1 other repository
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/persona-startup-founder Skill
1★ repoStartup-founder persona for the FlowLeap CLI — novelty sanity checks, freedom-to-operate scans, and competitor-patent monitoring. Trigger when the user asks the agent to validate a startup's IP position, check whether an idea is already patented, or scope competitor patents before building.
The same file is in 1 other repository
yoelgal/better-dev/skills/design-brief Skill
1★ repoUse when a work item has real UI surface and its visual direction isn't settled - a request to make something look good, design a landing page or a screen, pick an aesthetic or a design system, fix a UI that reads as generic AI slop, or turn a vague "looks nice" into visual done-criteria the loop can verify. This is the design front-end `/groundwork` composes to settle foundation tokens and `/plan-grill` composes for a UI feature. Composes the host's design skill and sources one on a gap; hardcodes no aesthetic or stack. Not for auditing existing UI code against accessibility or style guidelines - that is a host design-review skill (`/web-design-guidelines`) or `/review`.
dy/skills/skills/deslop Skill
no license1★ repoRemove AI slop from prose and code — the merged canon of the field's most effective deslop/humanizer skills (blader/humanizer, stop-slop, fuck-slop, no-ai-slop, humanize-writing, Rossmann's rules, story-deslop, cursor/deslop and others), deduplicated and reworked. Use when the user wants to deslop, humanize, de-AI, or naturalize text; remove AI patterns, tells, or "AI smell" from writing; check whether text reads as AI-generated; or clean AI slop from a code diff. For UI/design slop use the hallmark skill instead.
chobizzy/llm-wiki/skills/obsidian-layout-adjustment Skill
1★ repoWorkflow for working with Dan on changing how Obsidian looks using CSS snippets. Use this whenever Dan asks to restyle Obsidian, tune a vault's visual layout, adjust tabs, sidebars, note surfaces, properties, backlinks, graph panes, file explorer rows, icons, links, shadows, active states, or CSS snippets. Also use it when Dan says a visual CSS change did nothing, still looks wrapped, is not lifted, is unreadable, or needs to be refactored without changing the current appearance.
The same file is in 1 other repository
Ivor-NCUT/course-producer/skills/course-outline-design Skill
1★ repo根据课程定位与证据化知识卡设计成果优先、螺旋递进的课程模块和章节蓝图。Use when the user says 课程大纲、课纲重排、模块设计、成果优先课纲、系统课结构,或 Course Producer 完成知识萃取后进入 outline 阶段。
ifitsmanu/landing-studio/skills/creative-direction Skill
1★ repoDevelop distinctive, evidence-led visual directions for one landing-page section at a time. Use before design or implementation when a team needs category research, creative territories, a visual concept, art direction, anti-sameness analysis, or a defensible choice among multiple directions. Research beyond software galleries, produce three materially different territories, audit originality and usability, and wait for an explicit human selection before handing off the active section.
ifitsmanu/landing-studio/skills/landing-design-system Skill
1★ repoBuild or extend a production landing-page design system from the brand kit and target project's existing UI: accessible color roles, typography, spacing, layout, radii, elevation, motion and reduced-motion tokens, themes, and reusable component states. Use for design tokens, type scales, color systems, themes, buttons, form states, responsive primitives, or before implementing an approved visual direction. Emit stack-appropriate tokens and verify contrast. Own the reusable system, not page composition, copy, media, motion production, or full-build orchestration.
ifitsmanu/landing-studio/skills/landing-page-build Skill
1★ repoOrchestrate a production landing page one page and one section at a time, from evidence and creative direction through implementation, browser proof, and independent red teaming. Use when building, rebuilding, launching, or materially improving a full landing page, homepage, product page, or campaign page. Persist approvals and artifacts in a run manifest, route work to Landing Studio specialists, block unlicensed media and unsupported claims, and never certify the producer's own work without a separate critic pass.
ifitsmanu/landing-studio/skills/landing-page-design Skill
1★ repoCompose or critique one active landing-page section at a time: hero anatomy, hierarchy, whitespace, product proof, responsive behavior, CTA path, and its relationship to adjacent sections. Use for landing-page layout, page structure, hero design, homepage composition, wireframes, section critique, or responsive staging. Work from the brand kit, page frame, selected creative territory, real media, and sourced proof. Produce an implementation-ready section spec; route creative territories, tokens, copy, media rights, motion, 3D, and orchestration to their owning skills.
ifitsmanu/landing-studio/skills/landing-page-implementation Skill
1★ repoImplement an approved landing-page design and copy deck as production code in the target repository. Use for building or revising a landing page, homepage, campaign page, or launch route after the design/copy direction is known. Inspect repository rules and existing components first, reuse the project's stack and maintained libraries, preserve unrelated work, implement semantic accessible responsive markup, wire real CTA/form destinations, integrate approved media and metadata, and verify the built route. This owns code implementation, not research, strategy, copy approval, analytics interpretation, or final QA.
ifitsmanu/landing-studio/skills/landing-page-qa Skill
1★ repoBrowser-based release QA for landing pages and marketing sites. Use after implementation, before shipping, or whenever the user asks to test, browse, inspect, verify, screenshot, compare, or audit a landing page in a real browser. Exercise responsive layouts, primary journeys, forms, links, media, motion, keyboard and accessibility behavior, performance, metadata, console/network health, visual regressions, and agent-readable DOM. Produce evidence-backed blockers and rerun fixed cases. Code inspection alone is never sufficient.
ifitsmanu/landing-studio/skills/landing-red-team Skill
1★ repoPerform an independent, fresh-context release attack on one implemented landing-page section. Use after browser implementation or when the user asks for a brutally strict design, copy, interaction, accessibility, performance, evidence, rights, privacy, or deception critique. Inspect the real rendered page, scroll and capture exact states, score against a high bar, report reproducible P0-P3 findings with acceptance tests, block unresolved P0/P1, and require explicit ownership for P2 rather than letting the producer self-certify.
ifitsmanu/landing-studio/skills/landing-research Skill
1★ repoResearch and evidence intake for a landing page before design or copy begins. Use whenever the user asks to understand a product, repository, customer, market, competitors, reference sites, positioning, traffic source, or existing landing page before building or revising it. Inspect the real project and source material, browse current primary sources when facts can drift, separate evidence from hypotheses, and return a decision-ready discovery brief and evidence ledger. This is the required discovery stage for landing-page-build unless equivalent project research already exists and is current.
ifitsmanu/landing-studio/skills/motion-video Skill
1★ repoDesign and produce professional product motion, hero loops, interactive demos, launch films, ads, social cutdowns, and live landing-page animation. Use when the user asks for video, motion, animation, product demo, ad creative, launch film, hero media, kinetic type, scroll motion, Rive/GSAP/Motion, Remotion, capture, storyboard, shot list, or cutdowns. Choose the production lane from the brief and available assets: live web motion, deterministic product capture, programmatic video, traditional post-production, or approved generative footage. Require sourced claims, licensed assets, disclosure where needed, a strong static/reduced-motion state, performance budgets, and browser/video QA.
wjlgatech/design-anything/skills/design-anything Skill
no license1★ repoTurns any design intent — a text brief or a picture — into an execution-ready, gate-verified blueprint: 3D-printable models (STL), construction floor plans, garment sewing patterns, game/sim scenes. Discovers what the user wants to design, retrieves survival-tested principles and constraint tables, emits deterministic parametric source, and verifies with machine gates (watertight, clearances, egress, zero-waste, fit). Use when the user wants to design, redesign, or validate a physical or spatial thing: "design me a…", "is this printable / buildable / cuttable", "turn this sketch or photo into a plan", "redesign my room / house / garden / apron / game level", "make it 3D-print ready". NOT for graphic/UI/logo design, photoreal rendering, or engineering certification (a gate is never a permit or PE stamp).
wjlgatech/design-anything/skills/design-research Skill
no license1★ repoRun the three-window research method on any design question: /last30days (engagement — what's alive now), /last30years (survival — what's load-bearing), /last300years (endurance — what governs taste). Trigger: "research X for this design", "what's the state of the art in Y", "has Z ever worked".
wjlgatech/design-anything/skills/scene-to-layout Skill
no license1★ repoTurn a room photo, scan, or point cloud into a structured layout — walls, openings, furniture as typed objects with dimensions — using SpatialLM-class models, ready for blueprint-validate and re-design. Trigger: "here's a photo of my room", "measure this space", "redesign from this picture".
fullREFIT/skills/skills/logo-designer Skill
1★ repoProfessional logo and visual identity design system that translates brand strategy into optimized AI image generation prompts for external tools. Creates comprehensive visual identity concepts using methodologies from 11 elite design studios. Generates tool-specific prompts for Midjourney, DALL-E, Ideogram, Flux, Freepik, and Google Nano Banana Pro. Use when you need logo prompts to run in external AI tools rather than direct in-session generation. MANDATORY TRIGGERS: logo prompts, AI logo prompts, logo concepts, visual identity prompts, Midjourney logo, DALL-E logo, Ideogram logo, Flux logo, logo prompt suite, logo prompt engineering, logo ideas, prompt for logo, logo prompt.
fullREFIT/skills/skills/web-app-builder Skill
1★ repoConvert one or more markdown files into a single-file HTML web application using the default design system (Carbon Forge). Handles full content analysis (format selection, interface pattern selection), responsive rendering (collapsible sections, tabs, sidebar navigation, interactive checklists, code blocks with copy buttons, styled tables, callout boxes), and single-file HTML output (all CSS and JS inline, no build step, no frameworks). Outputs are browser-ready HTML files. MANDATORY TRIGGERS: web app from markdown, markdown to HTML, convert markdown, web app builder, web app, single-file app, HTML from docs, interactive docs, doc viewer, markdown viewer, documentation site, web app from docs, build me a web app.
SuperTapir/tapir-skills/skills/tapir-presentation-craft Skill
1★ repoDesign, prompt, review, and refine concise, forceful, imageable presentations using Tapir's preference for one clear claim per slide, one memorable visual relationship, poster-like hierarchy, selective icon use, semantic typography contrast, restrained color, and perceptible decisive motion. Default unspecified presentation, slides, deck, or PPT creation requests to a Slidev HTML deck with presenter mode; use native PPTX, PowerPoint, Keynote, or Google Slides only when the user explicitly requests that format. Use when creating or critiquing presentations, pitch decks, technical talks, product presentations, conference talks, or presentation design systems; translating dense material into a visual narrative; preparing art direction for slide visuals; or diagnosing slides that feel generic, crowded, dry, UI-like, templated, weak, over-abstract, or over-animated.
gabros20/ai-skill/skills/ai Skill
1★ repoBuild model-powered behavior — model routing, context engineering, structured outputs, tools/MCP, agents, RAG, memory, evals, guardrails, and cost/observability — across chat, agent, RAG, batch, and multi-agent systems, any provider or language. Use to route a model, engineer context, build an agent or tool loop, add RAG or memory, write evals, or add guardrails. Not for system/threat design (→ architecture), serving or MCP hosting (→ backend), data pipelines (→ data), chat UI (→ frontend), independent QA (→ quality), deploy (→ operate), or deterministic workflows (→ automation).
SageV1/makepad-skills/skills/makepad-layout Skill
1★ repoCRITICAL: Use for Makepad layout system. Triggers on: makepad layout, makepad width, makepad height, makepad flex, makepad padding, makepad margin, makepad flow, makepad align, Fit, Fill, Size, Walk, "how to center in makepad", makepad 布局, makepad 宽度, makepad 对齐, makepad 居中
SageV1/makepad-skills/skills/makepad-reference Skill
1★ repoCRITICAL: Use for Makepad troubleshooting and reference. Triggers on: troubleshoot, error, debug, fix, problem, issue, no matching field, parse error, widget not found, UI not updating, code quality, refactor, responsive layout, adaptive, api docs, reference, documentation, 故障排除, 错误, 调试, 问题, 修复
The same file is in 2 other repositories
Aiweline/WelineFramework/.codex/skills/frontend-components Skill
1★ repoAiweline/WelineFramework/.codex/skills/theme-development Skill
1★ repoAiweline/WelineFramework/.codex/skills/ui-ux-pro-max Skill
1★ repoUI/UX design intelligence with searchable database
Aiweline/WelineFramework/dev/ai/codex/plugins/weline-codex-plugin/skills/ui-ux-pro-max Skill
1★ repoUI/UX design intelligence with searchable database for WelineFramework frontend work. Use when improving UI quality, layout, visual hierarchy, product surfaces, dashboards, landing pages, responsive behavior, charts, or frontend design decisions.