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.
-
contentstack Skill Typescript Style 2Use when editing TypeScript or React files and matching this repo’s compiler and ESLint conventions.
-
dohyeon-kr Skill CSS JudgmentUse when modifying CSS — adjusting padding/margin/gap/width/height/position/z-index/overflow, hover/focus/responsive states, or directly using primitive tokens (raw spacing, raw colors). Guides the judgment of CSS work rather than the syntax. Determines sizing ownership (outer layout vs inner content), preserves the box model, enforces token hierarchy, and catches observable anti-patterns: child margin for sibling spacing, intentionless `flex:1` or `width:100%`, raw px / one-off token combinations, gradient hex composition at call sites, `margin: auto` for large-area distribution. For image assets (faces, photos, composite illustrations) trigger image-asset-strategy first; for post-work visual comparison trigger visual-reference-compare.
-
dohyeon-kr Skill Visual Design AuditUse at the end of any UI work — right before reporting "done" or opening a PR — to audit a rendered screen against two axes (심미성 / 유저 편의성). Captures viewport screenshots via cmux / agent-browser / playwright, then walks 16 lenses derived from Refactoring UI, NN/g 10 Heuristics, WCAG, Apple HIG, A List Apart, and Don Norman's "Design of Everyday Things." Enforces measurement (`getBoundingClientRect`, contrast, target-size in numbers) over eyeball judgment, with explicit guards for inner-scroll-container traps, carousel/swipe padding parity, page-vertical symmetry, and flex content-size shrinking. Returns a prioritized punch list with severity + lens + measured deltas + recommended fix. Distinct from `visual-reference-compare` — that skill compares a render against a supplied reference image; this skill judges whether the render is good design on its own terms. Triggers when no reference is supplied, when the user says "디자인 어때 / 괜찮아 보여 / 검토해줘 / 패딩 안 맞는 거 확인해", and as the standard final gate after frontend work.
-
getabyssale Skill HTML To AbyssaleRecreate an HTML/CSS banner (absolute-positioned elements over a fixed-size canvas — the shape of HTML5 ad banners, email banners, or design-tool HTML exports) as a native, editable Abyssale design, including basic CSS/GSAP animation mapped to Abyssale's tween system. Use when the user gives HTML/CSS for a banner and wants it rebuilt in Abyssale via import_design_from_json, not just referenced. Does not handle canvas-rendered banners; animation support is best-effort, not a full reproduction of every CSS/GSAP effect.
-
dcouple Bundle Review 2Performs a comprehensive PR code review. Reads the linked GitHub issue for context, runs quality checks, and reviews code for bugs, architecture, conventions, and frontend best practices. Posts structured findings as a PR review.
-
neetx Skill Radar Lab Sweep 2Sweep the primary security feeds — vendor/lab red-team & security blogs, research venues, and advisory feeds — on EVERY daily run (not rotated) so no attack-technique, red-team tool release, or disclosure is missed. Prefer RSS/Atom over HTML to survive JavaScript-rendered indexes. Use at the start of every daily scan, before the rotating exploration slot.
-
qwwiwi Skill Markdown New 2Clean Markdown extraction from any URL via markdown.new. Reduces token usage by ~80% vs raw HTML. Use when reading web pages, articles, documentation.
-
cyberagentgameentertainment Bundle Uloop Execute Dynamic Code 2Execute C# with Unity APIs when existing uloop tools cannot inspect or edit enough. Use for reachable scene/component state, scene/prefab/menu automation, and PlayMode checks
-
involvex Bundle Native Data Fetching 2Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (`useLoaderData`).
-
lekeopen Bundle Wechat Webview Font SizingUse when a responsive website looks enlarged, old-age-mode-like, reflowed, clipped, or inconsistent inside the WeChat embedded browser, especially when ordinary mobile browsers render correctly or CSS text-size-adjust changes do not survive production builds.
-
nekoai-lab Skill Security ReviewAIが生成・修正したコードのセキュリティレビュースキル。「セキュリティレビューして」「コミット前に確認して」「これ安全?」「脆弱性チェックして」などと言ったとき、またはコミット・プッシュ前の確認を求められたときに使う。入力系・認証認可系・外部通信系・運用系・AI固有系の5カテゴリで脆弱性を検出し、CVSSベースの深刻度判定と具体的な修正案を返す。GCP / Python / Next.js が混在するプロジェクトに対応。OWASP Top 10 および OWASP LLM Top 10 準拠。
-
nicholasswhite Bundle I Am Not A Smart ManExplain a project or file in plain language and generate a local HTML report with Mermaid diagrams. Use when the user asks how a project works, requests a project walkthrough or debrief, or invokes "i am not a smart man," "iamnot," or "smart man." Do not use for a single-function explanation, a pull-request summary, or a how-to article.
-
prangishviliabe Bundle UI UXDesign, critique, specify, and improve complete digital product experiences — user flows, information architecture, interaction models, navigation, forms, dashboards, onboarding, empty and error states, responsive layouts, design systems, component APIs, accessibility, content hierarchy, usability, and frontend-ready handoff specs. Use when creating or reviewing websites, apps, SaaS products, admin tools, mobile interfaces, checkout and conversion flows, or component libraries, especially when product logic, user behavior, and buildability matter beyond visual styling.
-
prangishviliabe Bundle Premium Web MotionDesign, audit, and implement purposeful premium website motion without copying a brand's visual identity. Use for UI animation, microinteractions, hover and press feedback, page and view transitions, scroll storytelling, gesture and drag behavior, loading and skeleton choreography, motion-system and token design, and motion performance or accessibility reviews in HTML/CSS/JavaScript, React, Next.js, and component libraries.
-
processmission Skill Interactive Gdb DebuggingDrive GDB interactively through persistent tmux sessions for local binaries, remote targets, QEMU gdbstub connections, cross-debuggers, stepping, breakpoints, state inspection, and core-dump analysis. Use when a task needs gdb, gdb-multiarch, an architecture-specific GDB, QEMU -s -S, target remote, or an adaptive debugging workflow that must react to debugger output.
-
sandbornm Skill Tufte Data VizMake data visualizations potent in the tradition of Edward Tufte's "The Visual Display of Quantitative Information." Use BEFORE building ANY chart, graph, plot, table, diagram, dashboard, coverage bar, stat callout, or node-link graphic — in HTML/SVG, a plotting library, or an artifact. Triggers: "chart", "graph", "plot", "visualization", "dashboard", "make it potent / Tufte-style", "data-ink", "small multiples", "sparkline", "bipartite", "coverage bars", or any request to show quantities visually.
-
tuyv Bundle Tw Blazor CSS StrategyHow to style Blazor + FluentUI components in this repo without Tailwind. The "isolation-first hybrid" convention — CSS isolation by default, global design tokens, and two documented exceptions for FluentUI shadow-DOM and light-DOM children. Use when authoring or restyling any .razor component, choosing where CSS lives, or styling a FluentUI component.
-
ben-lau1 Bundle Read With MarkitdownConvert document and data files to Markdown with Microsoft MarkItDown before reading or analyzing them. Use whenever Codex is about to inspect PDF, HTML, DOCX, PPTX, XLSX/XLS, EPUB, CSV, JSON, XML, ZIP, Outlook messages, images with OCR or metadata, or audio requiring transcription, especially for text extraction, summarization, search, comparison, and citation. Do not rely on conversion alone when exact visual layout, figures, scanned pages, formulas, spreadsheet cell fidelity, or dynamic or authenticated web content matters; pair it with native visual or structured inspection.
-
blue-b-code Bundle MiProjet MI (MobileInvoice, Orange Money, PayNote / Y-Note) : stack locale Docker, branche de démarrage develop-sp-local, validation obligatoire du code dans le conteneur orangemoney_web-mi (PHPUnit, Vitest, phpcs, phpstan, phpmd, eslint-vite, tsc, jscpd), et tests fonctionnels UILicious (manifeste ci/uilicious-tests.json, exécution via uilicious-cli sur le projet Paynote-MI). À utiliser pour tout travail sur /home/y-note/OrangeMoney/MobileInvoice : diagnostiquer la stack locale, valider du code PHP/TS/React, ou ajouter/fixer/valider des tests fonctionnels UILicious, ou gérer les données de recette sur une branche donnée : passer des factures en « payé » (branche + ids de factures) et mettre un solde sur une entreprise (branche + company + méthode de paiement + montant).
-
blue-b-code Bundle OpenimisApply the standard git + PR workflow for a feature in OpenIMIS repos: main openIMIS (/home/y-note/openimis — frontend-packages modules and openimis-be-*_py backends: create feature-<n> from develop, commit once, push to ynote, open a PR to openimis develop with the description filled from the official openIMIS PR template) and OpenIMIS front-end modules under /home/y-note/openimis-comores and /home/y-note/openimis-csu (create feature-<n> from the correct base (develop-comores for Comores, test-csu for CSU), commit once, open the PR with the pr script, then fan out the same commit with the gff script to test-comores/main-comores for Comores or hotfix-csu/release-csu for CSU). Use when the user asks to develop an openimis feature (main repo, Comores or CSU), do 'le même travail'/'same work' in another module, or port a patch between modules.
-
jjuke Bundle Graphifyany input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when user asks any question about a codebase, project content, architecture, or file relationships — especially if graphify-out/ exists. Provides persistent graph with god nodes, community detection, and BFS/DFS query tools.
-
rayekry777 Bundle Native Multiplatform Frontend创建、改造、审查或构建 Vue Web、微信小程序、iOS、Android 原生前端。锁定唯一目标端并按接口状态实现或预留产品空间;新设计或明显改版按逐阶段审批流程完成设计契约、Pencil 令牌展示、组件、状态和完整界面,再生成可直接导航的响应式 HTML 实验网站并忠实实现到目标平台。
-
rayekry777 Bundle Pencil Cupertino Web Workflow使用 Pencil .pen 文件和 React Cupertino UI 构建并维护 Apple/Cupertino 风格的网页界面。适用于创建 Pencil 组件库、建立 Pencil 组件与 React 组件映射、同步 CSS 设计令牌、将 Pencil 页面实现为 React、在 Pencil 中还原现有 React 页面、使用已映射组件组合新页面,以及审计设计与代码的偏差和视觉一致性。
-
rayekry777 Bundle Dockerize Spring Web Compose Cicd为分离的 Java Spring Boot 后端、静态 Web 前端和独立部署仓生成或改进生产 Docker、GitHub Actions、GHCR 与 Docker Compose 配置。适用于 Spring Boot 与 Vue、React、Angular、Svelte、Astro、Vite 或静态 Next.js 导出项目的容器化、分仓 CI/CD、镜像发布、Compose 编排、自动部署、反向代理或中间件部署任务。
-
scotttylertech Skill Ngrx PatternsNgRx global store and component store patterns for this project. Use when writing or reviewing actions, effects, reducers, selectors, state, facade services, or component stores (ComponentStore). Covers operator selection, entity adapter usage, routing effects, pagination actions, and selector testing conventions.
-
scotttylertech Skill Rxjs Best PracticesRxJS best practices for Angular frontends using NgRx. Use when: writing or reviewing component observables, using shareReplay, subscribing to store selectors, managing feature flags, adding takeUntil cleanup, using BehaviorSubject, or deciding between async pipe and manual subscriptions.
-
zhiqingresearch Skill Dl API Doc For Frontend给前端 AI 看的后端接口联调文档生成器(团队 NestJS 项目通用)。当用户开发/改完一个较大的后端模块,需要"生成接口文档 / 联调文档 / 给前端的 API 说明 / 本次改了哪些接口 / 入参返回值字段说明",或要把某个 controller 模块整理成前端能照着联调的文档时,用这个 skill。产出是面向**前端 AI**、机器可读性强的 Markdown:含本次改动摘要、每个接口的完整路径/方法/鉴权/入参/返回值/字段释义/枚举/错误码/请求响应示例,并把**该项目实测到的**全局约定(响应包装、路由前缀、鉴权、参数校验行为)写进文档头,避免前端 AI 踩坑。全局约定一律**读目标项目的代码核对**(团队 dl-nestjs-starter 默认值只作 fallback),绝不照抄死值。手动触发,结果写到 docs/(不进版本管理),主要针对大模块开发。
-
velt-js Bundle Velt Comments Best Practices 2Velt Comments implementation patterns and best practices for React, Next.js, and web applications. Use when adding collaborative commenting features, comment modes (Freestyle, Popover, Stream, Text, Page), rich text editor comments (TipTap, SlateJS, Lexical), media player comments, chart comments, comments sidebar setup and customization (embed mode, floating mode, focused thread, V2 sidebar), sidebar filtering with accessModes for privacy, isAnnotationPrivate() visibility routing, CommentDialogActionService.isSubmitInFlight() for duplicate-submit guards, VeltCommentDialogAgentSuggestion primitives for AI suggestion accept/reject UIs, agent comment annotations via REST API (agent block with agentSource/agentId/executionId, agent-specific GET filters, suggestionAccepted/suggestionRejected client events, sourceType "agent" UI rendering), or binding Comment Bubble / Comment Dialog / Comment Tool wireframe slots via template variables (velt-data, velt-if, velt-class).
-
velt-js Bundle Velt Node Sdk Best Practices 2Velt Node SDK (`@veltdev/node`) implementation patterns for Node.js / TypeScript backends. Use whenever the user is writing server-side code that integrates with Velt — initializing `VeltSDK`, calling `sdk.api.*` (REST API services like Organizations, Documents, Comment Annotations, etc.) or `sdk.selfHosting.*` (MongoDB+S3 self-hosted services like Comments, Reactions, Attachments), generating JWT auth tokens for the frontend SDK from Node, configuring MongoDB or AWS S3 for self-hosting, handling the SDK's typed error classes (`VeltSDKError`, `VeltDatabaseError`, `VeltValidationError`, `VeltTokenError`, `VeltApiError`), debugging response-envelope mismatches between the two backends, or shipping Node code that talks to Velt in any way. Triggers on any mention of `@veltdev/node`, `VeltSDK`, `sdk.api`, `sdk.selfHosting`, Velt server-side Node.js, MongoDB-backed Velt storage, or env-var auth (`VELT_API_KEY` / `VELT_AUTH_TOKEN`) — even if the user doesn't say "Node SDK" explicitly.
-
velt-js Bundle Velt REST Apis Best Practices 2Velt REST API v2 and webhook best practices for server-side integration. Use when calling Velt REST API v2 endpoints, generating JWT tokens for frontend authentication, handling Velt webhooks (comment events, huddle events, CRDT updates), managing users/documents/organizations via REST, or implementing server-side Velt operations. Triggers on any task involving Velt REST API, JWT token generation for Velt, Velt webhooks, x-velt-api-key headers, or server-side comment/notification/activity management — even if the user doesn't explicitly say 'REST API'. For the Python SDK (velt-py) for self-hosting, see velt-self-hosting-data-best-practices instead.
-
velt-js Bundle Velt Notifications Best Practices 2Velt Notifications implementation patterns and best practices for React, Next.js, and web applications. Use when adding in-app notifications, notification panels, email notifications via SendGrid, webhook integrations, user notification preference management, cross-organization notification feeds with enableCrossOrganization/disableCrossOrganization, or binding Notifications Panel / Notifications Tool wireframe slots with template variables (velt-data, velt-if, velt-class).
-
velt-js Bundle Velt Self Hosting Data Best Practices 2Velt self-hosting data implementation patterns and best practices for React, Next.js, and web applications. Use when storing sensitive user-generated content (comments, attachments, reactions, recordings, user PII) on your own infrastructure instead of Velt servers, implementing data providers (endpoint-based or function-based), building backend API routes, or debugging data provider events.
-
onewave-ai Skill CSS Animation Creator 2Create professional CSS animations, transitions, micro-interactions, and complex motion design. Use when adding animations, hover effects, loading states, page transitions, scroll animations, or any motion design work.
-
onewave-ai Skill Error Boundary Creator 2Create error boundaries, error handling, and fallback UIs for React applications. Use when implementing error handling, creating fallback components, or setting up error reporting.
-
onewave-ai Skill Design System Generator 2Create design systems with tokens, components, and documentation. Use when building design systems, creating component libraries, or establishing design tokens.
-
cdeistopened Skill Listing Optimizer 3Write Amazon KDP book descriptions (HTML-formatted), select categories with ghost/duplicate screening, and build author bios. Use when preparing a book for upload or optimizing an existing listing.
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 typescript-style, css-judgment, visual-design-audit. 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.