Web & Frontend
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
-
paulingram Skill Frontend Route MappingUse when the route-mapper agent is producing a ROUTE_MAP.md for a frontend codebase, or when any agent needs to consult an existing route map. Defines the ROUTE_MAP.md schema, the navigation web format, route inventory + dynamic routes + modal routes + API endpoint catalog, and what "complete" means for review.
-
paulingram Skill Intuition Map LifecycleLane-callable lifecycle discipline for a frontend codebase's INTERACTION_INTUITION_MAP.md, with three verbs — ensure (guarantee the map exists before any Playwright test is authored, dispatching interaction-intuiter in pipeline context or running the same rubric inline with an inline bulk-verify ad hoc), grow (upsert the elements and routes a user-specified flow exercises as confirmed entries carrying source user-flow, with no bulk-verify round-trip because the user specifying the flow IS the confirmation), bug-path-upsert (record a resolved bug path with source bug-path plus regression_refs naming the covering debug-flow test and the SR or bug slug). Triggers — any lane about to author or review Playwright tests, a user handing over a concrete UX flow, a debugging lane closing out a bug. The deterministic engine lives under scripts/intuition_lifecycle/ and this skill is its contract.
-
paulingram Skill API Design From FrontendExtracts the "backend logic from frontend" portion (Stages 5+6+7) of visual-to-api-design as a standalone reusable skill. Stage 5 per-page REST returns → API_RETURNS_MAP.md. Stage 6 consolidated API design + desk-trace play-test → API_DESIGN_MAP.md. Stage 7 backend data architecture → DATA_ARCHITECTURE_MAP.md + openspec change via openspec-propose. Each stage's 3-reviewer convergence wraps in a ralph-loop with total-agreement completion-promise. Inputs: PERSONA_MAP.md + page catalog + COMPONENT_ARCHITECTURE_MAP.md (or equivalent frontend artifacts). Callers: visual-to-api-design (refactors to delegate Stage 5+ here), architect-team-pipeline Phase 0b (backend dispatch when frontend or docs are referenceable). v3.4.0.
-
paulingram Skill Playwright Suite BuilderCallable orchestrator that builds and maintains a durable, persona-grouped Playwright suite for a target frontend codebase, reached via /architect-team:playwright-suite. Ten phases — P0 target and e2e-dir resolution following the repo's own convention, P1 inventory reconciled against the suite manifest, P2 intuition-map freshness, P3 review of the existing tests by dispatching the existing checkers, P4 suite-wide gap analysis, P5 gap-fill authoring per the full playwright-user-flows discipline, P6 debug-flow registration, P7 persona grouping, P8 dev-versus-prod safety classification, P9 engine-validated manifest write plus report. Triggers — "build the Playwright suite", a project with no durable test registry, a full-integration run that needs the entire dev suite enumerated. Adds no new agents.
-
paulingram Skill Contract First ParallelismUse whenever a run needs BOTH backend surface work AND a frontend that visualizes that data — a full-stack build from scratch, or an integration with existing services where the frontend needs inbound surfaces. The architect's parallelism protocol: the frontend and backend agents co-design the inbound surface contract, the architect approves it, the backend IMMEDIATELY provisions the endpoint AT ITS REAL PATH serving a contract-conforming mock payload, and the frontend then builds a fully integrated interface against that LIVE endpoint while the backend replaces the mock internals underneath. Neither side waits for the other. The same protocol covers a surface that already exists but needs new attributes. Every provisioned mock is a tracked, temporary scaffold recorded in a ledger; the deterministic engine (scripts/contract/interface_contract.py) makes a run non-closable while any surface is still mock-serving, so the parallelism borrowed is always repaid.
-
paulingram Skill Visual Fidelity ReconciliationUse when QA-reviewing frontend work post-development against a codebase that has a DESIGN_MAP.md — any commit touching frontend files (.tsx / .jsx / .vue / .svelte / .astro / .css / .scss / theme tokens / Storybook stories / assets) MUST produce a reconciliation report verifying every (screen, element, state) tuple in scope matches the design contract PERFECTLY. Also use in Phase 5 integration to regression-check the visual contract, on-demand via /architect-team:visual-qa, or when the Phase 3 hook rejects a visual_fidelity_review=fail evidence file. The body mandates zero-tolerance defaults, exhaustive per-state walks, fix-to-spec by default, and the four narrow escalation exceptions.
-
selina2025-alt Bundle Ljg Present演讲铸造器(Outline-Faithful)。基于 orgmode/markdown outline 层级 1:1 视觉化呈现——色块大字、ultra-bold 错位,原文不动只做美化。三档主题色 black/red/yellow(默认 black 或按 filetags 推断),可用 -r/-b/-y 显式覆盖;可用 --cyber 走黑底绿字 cyber-hacker 风。使用时用户会说:'讲这个'、'present'、'做成演讲'、'呈现一下'、'铸成演示'、'做个 slides'、'标语流'、'宣言体'、'slogan'、'manifesto'、'按 outline 美化'。输出单文件 HTML 到 ~/Downloads/。
-
selina2025-alt Bundle Huashu Xhs Image为小红书笔记生成高质量配图。默认AI生成(Gemini),仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。
-
selina2025-alt Bundle Huashu Wechat Image为微信公众号文章生成高质量配图。支持封面图(2.35:1)、正文插图(16:9/4:3)、信息图。提供两条路径:AI生成(视觉创意型)和HTML渲染(文字精确型)。当用户提到"公众号配图"、"公众号封面"、"文章配图"、"正文插图"、"公众号图片"时使用此技能。
-
buildpad-ai Bundle Add Microfrontend ZonesAdd Micro-Frontend (Multi-Zones Composition)
-
marvin-lijunzan Skill Radix ColorsPrecision color grading system using Radix Colors (radix-ui/colors). Systematic 12-step perceptual scales designed for accessibility (WCAG AA 4.5:1), dark mode symmetry, and natural P3 color gamut.
-
marvin-lijunzan Skill Readme StatsVisual metrics and dynamic statistic cards inspired by GitHub Readme Stats (anuraghazra/github-readme-stats). Generates polished, vector-sharp SVG/HTML overview cards, progress meters, and dashboard KPI summaries.
-
dragoon0x Skill Focus 3Generate a complete focus ring system. Creates consistent, visible :focus-visible styles that match the design aesthetic while meeting accessibility requirements.
-
dragoon0x Skill Palette 3Generate a complete 50-950 shade palette from a single hex color. Outputs 11 perceptually uniform shades with CSS variables, Tailwind config, and design token formats.
-
dragoon0x Skill Spacing 3Generate a complete spacing scale from a base unit. Outputs CSS custom properties and shows recommended usage for each step.
-
dragoon0x Skill A11Y Fix 3Auto-fix detectable accessibility issues. Adds focus styles, semantic HTML, ARIA attributes, and touch target sizing.
-
jpoindexter Skill IOSUse when the user invokes /ios, or when starting ANY native iOS/SwiftUI screen, component, flow, or review and it's unclear which ios-* skills apply. Dispatcher that routes to the right 2-4 companion ios-* reference skills instead of loading the whole family or designing from memory.
-
jpoindexter Skill DesignUse when the user invokes /design, or asks to design/build/audit/polish a web or cross-platform UI or create a design case study — screen, component, layout, table, chart, form, color system, portfolio narrative — and it's unclear which design reference skills apply. Dispatcher that routes to the right companion skills, delegates case studies to /case-study, and routes native iOS work to /ios.
-
jpoindexter Skill IOS ComponentsApple HIG component rules for native iOS 26 — bars (tab/nav/toolbar/search incl. floating + concentric corners), buttons (44pt hit region, prominence, roles, no destructive-primary), menus/pull-down/pop-up, toggles/pickers/segmented/sliders/steppers/text fields, lists & tables, sheets + detents, alerts vs action sheets vs popovers, modality, progress/gauges, with the SwiftUI mapping. Use when choosing or reviewing any iOS control or presentation.
-
jpoindexter Skill Grid And SpacingReference-grade system for spacing scales, column/baseline grids, responsive breakpoints, and modern CSS Grid/container-query layout built on an 8pt base with copy-pasteable tokens.
-
jpoindexter Skill Color And ElevationBuild perceptually-uniform color palettes and physically-consistent depth systems with OKLCH ramps, WCAG/APCA contrast, semantic tokens, and elevation-as-lightness dark mode — concrete values and copy-pasteable CSS.
-
jpoindexter Skill Components And StatesReference-grade guide to designing and building UI components — anatomy, the full interaction-state matrix, variants vs sizes vs states, sizing tokens, per-component anatomy/states/a11y, and modern headless/data-state/CSS patterns across web, iOS, Android, and desktop.
-
jpoindexter Skill Interaction And MotionReference-grade motion and micro-interaction system — duration scales, easing tokens, choreography, modern CSS (view transitions, scroll-driven, @starting-style, linear()), performance, and accessibility for any screen on any platform.
-
jpoindexter Skill IOS Flows And PatternsApple HIG behavioral patterns for native iOS — onboarding, launch screens, loading, modality decisions, feedback, settings, search, privacy & permission flows (purpose strings, priming screens, ATT), account deletion, in-app purchase, ratings, notifications — plus motion/reduce-motion, haptics (UIFeedbackGenerator patterns), and the accessibility floors (contrast AA, touch targets, Dynamic Type 200%, VoiceOver). Use when designing any flow, permission prompt, empty/loading state, or feedback moment on iOS.
-
jpoindexter Skill Layout And CompositionReference-grade system for composing any screen — visual hierarchy, Gestalt grouping, alignment, whitespace, scanning patterns, and modern intrinsic CSS layout (Grid/Flexbox/subgrid/container queries/:has) with copy-pasteable recipes.
-
jpoindexter Skill Design System FrameworksReference-grade survey of the named design systems (Material 3, Apple HIG, Fluent 2, Carbon, SLDS, Polaris, Atlassian, Primer, Ant, Spectrum) and the modern build stack (Tailwind, shadcn/ui, Radix/React Aria/Ark, MUI/Chakra/Mantine/Base) — each system's actual philosophy and rules, plus how to choose adopt-vs-adapt-vs-build.
-
jpoindexter Skill IOS Liquid Glass SwiftuiiOS 26 Liquid Glass design language + the SwiftUI APIs that implement it, sourced from Apple's WWDC25 sessions 219/323 and developer.apple.com. Covers the functional-layer-over-content mental model, regular vs clear variants, glass-on-glass/over-tint don'ts, the floating tab bar, scroll edge effects, concentric corners, accessibility behavior, and a verified-vs-community API table. Use when building or reviewing any iOS 26 native screen's chrome, materials, or glass effects.
-
jpoindexter Skill IOS Sf Symbols And IconsSF Symbols usage (weights, scales, the four rendering modes, fill-vs-outline variants, animations, SF Symbols 7 gradients/Draw, accessibility labels, version-gating) and iOS 26 app icons (layered design, Icon Composer, square-unmasked layers, the six appearances, specs) per Apple HIG. Use when picking icons, choosing rendering modes, or producing an app icon for a native iOS app.
-
jpoindexter Skill Accessibility And Inclusive DesignReference-grade guide to shipping WCAG 2.2 AA accessible, inclusively designed interfaces across web, native iOS/Android, and desktop — semantic-first markup, contrast/APCA, keyboard, screen readers, forms, touch/motor, motion/cognition, testing, and the legal floor (EAA/Section 508).
-
dauquangthanh Bundle Kiss C4 Diagrams 2Authors C4 model diagrams (Context / Container / Component) as Mermaid flowcharts. Produces three files per project so the system can be described at every zoom level. Draws what the user has declared; does not invent components. Use when creating architecture diagrams, visualising system structure, or when the project needs Context, Container, or Component-level views.
-
dauquangthanh Bundle Kiss Tech Research 2Researches technology options for a named decision area (frontend framework, database, messaging, identity, etc.) using WebSearch / WebFetch when available. Produces a pros/cons table + typical cost signal per candidate. Records sources. Does not pick the winner. Use when evaluating technology choices, comparing frameworks or databases, or before writing an ADR for a technology decision.
-
dauquangthanh Bundle Kiss Vue Spa Mockup 2Scaffolds a working Vue 3 SPA mockup with Vite, TypeScript, Tailwind CSS v4, PrimeVue, Vue Router v4, Pinia, vue-i18n v9, and 3-way theming (system / light / dark). Produces a ready-to-run project directory the developer can open immediately with `npm install && npm run dev`. Interactive mode asks for the output directory, app name, views, theme, and supported locales. Use when prototyping a feature UI, bootstrapping a front-end mockup, or when the team needs a runnable Vue SPA skeleton before the production app is built.
-
dauquangthanh Bundle Kiss React Spa Mockup 2Scaffolds a working React SPA mockup with Vite, TypeScript, Tailwind CSS v4, shadcn/ui, React Router v7, react-i18next, and a 3-way theme system (light / dark / system). Produces a ready-to-run project directory the developer can open immediately with `npm install && npm run dev`. Interactive mode asks for the output directory, app name, pages, theme default, and supported locales. Use when prototyping a feature UI, bootstrapping a front-end mockup, or when the team needs a runnable SPA skeleton before the production app is built.
-
fbakiyev Skill Frontend E2e TestingСоздать или оценить браузерные регрессионные тесты критичных пользовательских путей через UI, навигацию и сервисы. Применять для наблюдаемого в браузере поведения и относящихся к нему проверок доступности; чистую логику проверять на нижних уровнях, реализацию продукта относить к frontend-разработке.
-
fbakiyev Skill Frontend EngineeringСоздать или изменить интерактивный frontend-сценарий, компонент или переход клиентского состояния, включая доступность и адаптивность. Применять для реализации продукта; браузерные регрессионные тесты относятся к E2E-тестированию frontend, а запрос только на проверку — к review кода.
-
nexadevapp Skill AuditRuns a comprehensive implementation audit for a delivered use case in a Go web application. Checks Definition of Done, i18n completeness and correctness, error message i18n, accessibility, visual fidelity against the design, htmx loading/error/empty states, and E2E traceability. Run after /deliver-use-case or before /merge-use-case for a quality deep-dive. Use when the user asks to "audit UC-XXX", "run a quality audit", "check accessibility", "check translations", or mentions a deep quality review. Results are advisory — Critical and Major findings should be fixed; Minor findings are observations.
Frequently asked questions
What are Web & Frontend agent skills?
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
Which Web & Frontend skills are most installed?
Popular Web & Frontend skills on SkillMD right now include frontend-route-mapping, intuition-map-lifecycle, api-design-from-frontend. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Web & Frontend skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.