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.
-
hongmaple0820 Bundle Quiz HTML把题目数组生成一个**可独立运行的网页练习页**(HTML 文件)。当用户完成 quiz-mastery 的「从资料出题」或「从文件提取题目」流程后,应主动询问是否需要"在网页里练习",确认后调用本 skill 把题目注入模板,生成 HTML 给用户。也支持用户直接说"把这些题做成网页/HTML/练习页"时触发。**不处理**:出题(→ quiz-mastery)、评分(→ quiz-mastery)、长期复习计划(→ study-buddy)。
Audited -
hongmaple0820 Bundle Quiz Mastery出题、测验、复习、掌握度追踪工具。**用户说"复习"、"巩固"、"回顾"任一关键词时优先触发本 skill**。当用户的请求与"题目/复习"相关时触发:把学习资料/PDF/材料转成题目练习("给这个 PDF 出几道题")、导入题目文件做练习("我有一份题目文件,帮我做")、复习已学内容("复习一下昨天的"、"巩固一下"、"回顾下昨天"、"用艾宾浩斯帮我安排")、遗忘曲线追踪、掌握度评分。**🔴 强制规则**:每次出题/导入题目成功后,**首轮展示题目前必须问一句**"要不要生成网页练习页?",用户说要 → 调用 quiz-html skill。**不处理**:长期学习项目的进度管理、计划制定(→ study-buddy)。
Audited -
hongmaple0820 Bundle Lark Apps把本地 HTML 文件或目录部署到飞书妙搭(Miaoda),生成一个公网可访问的应用及其链接(URL)。当用户要创建 HTML 或要把 HTML、静态网站或 Web demo 发布成公网可访问的链接 / 可分享链接、设置应用共享范围,或提到妙搭 / Miaoda 时使用。凡产出可独立访问的 HTML 产物都属本 skill 的潜在归宿,是否真要部署由 skill 内部协议判断。不用于:上传普通文件到云空间/云盘/云存储(用 lark-drive)、编辑飞书云文档内容(用 lark-doc)、创建飞书原生幻灯片 / 演示文稿(用 lark-slides)。
-
kovrichard Bundle Consulting ReportBuild a beautifully-typeset consulting-report PDF from a typed data file and a React layout. Use when generating an assessment, strategic review, operational readiness check, or any McKinsey-style consulting deliverable as a PDF.
Audited -
tomorrowlm Skill Vercel React Best PracticesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Audited -
crbnos Bundle Carbon DocsAuthor, edit, or extend the Carbon documentation site at `docs` (a built Fumadocs + Next.js app). Use whenever creating or changing reader-facing docs for Carbon: editorial Guide chapters, Reference/entity pages, the docs IA, or "document this feature" requests — anything destined for the docs site. Covers the grounded-in-source authoring workflow, the flow-based Guide architecture, the real MDX components for each surface, the warm-paper house style, and the build verification loop. Trigger even if the user doesn't say "docs" but clearly wants explanatory, reader-facing written material about how Carbon works.
-
crbnos Bundle Pr ExplainerBuild a self-contained HTML review aid at .pr-review/{branch}.html that teaches a reviewer what a PR changes and why — problem, system context, before/after flow, focused diffs, verification evidence, takeaway. Use when asked to explain a PR, help reviewers understand a complex change, or produce a review page for a branch. Do not use it as a substitute for review itself (/self-review) or instead of a PR description.
-
ceilf6 Bundle Semgrep Scanner纯本地 Semgrep 静态代码分析 Skill。对指定仓库执行全量扫描,查找 Blocker(ERROR)和 Critical(WARNING)级别的安全与质量问题,直接在对话中输出报告。支持 TypeScript、JavaScript、Python、HTML、CSS 等语言。当用户提到静态扫描、代码分析、安全审计、Semgrep、查找 Blocker/Critical 问题、代码质量检查、全量扫描时使用。
-
ceilf6 Bundle Tui Render OptimizerAudit and optimize the terminal rendering layer for React-based TUI applications. Use when a request involves terminal flicker, slow frame rate, excessive redraws, high CPU during streaming output, Ink performance, React terminal render pipelines, HostConfig behavior, Yoga layout churn, dirty-flag rendering, screen diffing, or atomic terminal output. Not for browser-only rendering, general app-state design, or CLI entry architecture.
-
ceilf6 Bundle Agent State ArchitectDesign and audit the runtime state layer for AI agent interfaces. Use when a request involves streaming state, unnecessary re-renders, useSyncExternalStore, external stores, React and non-React state sharing, side-effect centralization, command queues, file watchers, or tiering state by frequency and lifecycle. Not for CLI entry architecture or terminal renderer internals.
-
speakeasy-api Skill FrontendRules and best practices when working on the dashboard React frontend codebase (including the inlined Gram Elements code)
-
speakeasy-api Skill Admin ShadcnUse when adding, changing, or styling UI in client/admin (the Gram admin dashboard) that touches shadcn/ui — a button, dialog, table, sidebar, badge, select, tabs, tooltip, card, sheet, or any file under client/admin/src/components/ui/. Triggers include "add a shadcn component", "install shadcn X", "npx shadcn add", "restyle this button", "change the dialog", "that variant does not exist", any edit to client/admin/src/components/ui/, and the errors "No components.json was found" or "sh: 1: oxfmt: not found".
-
speakeasy-api Skill Page ToolbarBuild the control bar (search, filters, sort, view) on dashboard list/collection pages with the unified `Page.Toolbar` compound component. Activate whenever adding or editing the controls above a list/grid/table on a `client/dashboard` page — a search box, filter chips/sheet, sort dropdown, grid/table view toggle, result count, or a mode toggle — so the page uses `Page.Toolbar` instead of hand-rolled controls. Phrases like "add a search/filter to this page", "filter bar", "sort dropdown", "view toggle", or "let users filter the list" should trigger it.
-
wachawo Bundle XLSXUse this skill whenever a spreadsheet file is the primary input or output. This includes any task in which the user wants to: open, read, edit, or repair an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., add columns, compute formulas, formatting, charts, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user mentions a spreadsheet file by name or path — even in passing (e.g., "the xlsx in my downloads") — and wants something done with it or produced from it. Also trigger when cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into normal spreadsheets. The artifact must be a spreadsheet file. Do NOT trigger when the primary artifact is a Word document, an HTML report, a standalone Python script, a database pipeline, or a Google Sheets API integration, even if tabular data is involved.
Audited -
guillaumelessard Skill Qector Two Stage CSSTwo-stage CSS decoding for QECTOR (manual chapter 12). Independent X and Z decoders assume P(X, Z) = P(X) P(Z); depolarising noise violates this. Two-stage decoding removes the cross-talk explicitly. Load for any question about depolarising noise, CSS sector coupling, feedforward X->Z syndrome updates, or the Theorem 13 joint-faithfulness guarantee.
-
nadav011 Bundle A11YWCAG 2.2 AAA accessibility — ARIA patterns, 44x44px touch targets, focus management, RTL
Audited -
nadav011 Skill Rtl FixUse when user wants to auto-fix RTL violations in code. Replaces physical directional Tailwind classes and CSS properties with logical equivalents (ms/me/ps/pe/inset-s/inset-e). Handles React/Next.js/CSS and Flutter. Also adds rtl:rotate-180 to horizontal directional icons.
Audited -
nadav011 Bundle Perf ExpertUse when user wants to analyze or improve web performance — Core Web Vitals (LCP, INP, CLS), Lighthouse audits, bundle size analysis, runtime profiling, image/font optimization, caching strategy, or React/Turbopack performance
Audited -
nadav011 Skill Bundle AnalyzeBundle size analysis — Vite chunks, code splitting, 100KB component rule
Audited -
nadav011 Skill React PatternsReact patterns for modern apps — Server vs Client Component decisions, use client boundaries, error boundaries, Suspense, and custom hooks.
Audited -
nadav011 Skill Nextjs PatternsNext.js App Router conventions — file structure, Server Actions, Route Handlers, Metadata API, Image and Font optimization
Audited -
puckapi Bundle Elo EngineeringBuilds multi-variant Elo rating systems for sports prediction. Use when user asks about Elo ratings, rating systems, team strength, K-factor, home field advantage, season carryover, margin-of-victory adjustments, or mentions 'Fading Elo', 'Form Elo', 'Component Elo'. Do not use for general feature construction -- see feature-engineering instead. Do not use for team stats without ratings -- see team-analysis instead.
-
a-v-ershov Skill Audit ProductDrive the whole running product through the spec's user flows end to end and, since it is already in the real UI, check the accessibility target on the same journeys. Use in the release phase (run by release-product) or standalone once features are built. It proves the cross-feature integration a per-task verifier could not see — state carried across steps, the seams between features, success and error states — then re-walks the core journeys with an automated axe pass plus what automation misses (keyboard operability, focus order, screen-reader semantics, contrast, reduced motion, form errors).
-
arnavpuri Skill Dark ModeDark theme design patterns with proper color adaptation, surface hierarchy, and CSS implementation. Trigger: user asks to "add dark mode", "create a dark theme", "dark mode support", "implement dark/light toggle", "design for dark background", "night mode", or any dark theme design work.
Audited -
arnavpuri Skill UI DesignCore UI design patterns and component architecture for building polished interfaces. Trigger: user asks to "design a UI", "build a component", "create an interface", "style a form", "make it look good", "improve the design", "add hover states", "make it accessible", or requests any general UI/UX design work.
Audited -
arnavpuri Skill Card DesignCard-based layout patterns including product cards, feature cards, and interactive cards. Trigger: user asks to "design a card", "build card layout", "create a product card", "make a card grid", "design a testimonial card", "blog post card", "feature card", "pricing card", or any card-based UI component.
Audited -
arnavpuri Skill Icon DesignDesign consistent icon systems with SVG: grids, styles, animation, and accessibility. Trigger phrases: "icon design", "svg icon", "icon system", "custom icons", "icon animation", "icon grid", "icon accessibility", "duotone icon", "icon set", "animated icon"
Audited -
adelabdelgawad Bundle DockerProduction-ready Docker infrastructure for fullstack apps — multi-service Docker Compose, nginx reverse proxy, SSL termination, and service wiring for FastAPI + Next.js stacks. Use when setting up Docker infrastructure, adding containers or services, or configuring nginx, monitoring, or SSL. Do not use for application code changes inside the containers.
Audited -
adelabdelgawad Bundle NextjsGenerate production-ready Next.js pages with SSR initial load, client-side data management, and server-response-based updates. Use when creating Next.js pages, admin or settings pages, or adding CRUD functionality to the frontend. Do not use for backend FastAPI code (use fastapi); for full entity data-table pages prefer data-table.
Audited -
adelabdelgawad Bundle FastapiGenerate production-ready FastAPI CRUD modules — SQLAlchemy model, Pydantic schemas, CRUD helpers, and routers following the simplified architecture. Use when creating or extending backend entities, models, or REST endpoints with SQLAlchemy and Pydantic. Do not use for Next.js frontend code (use nextjs or data-table).
Audited -
adelabdelgawad Bundle Data TableCreate Next.js data table pages with SSR initial load, simplified state management, and server-response-based UI updates. Use when asked to create a new data table page, entity management page, CRUD table, or admin list view. Generates page.tsx (SSR), table components, columns, context, actions, and API routes following a proven architecture with centralized reusable data-table component. Do not use for non-table pages (use nextjs) or backend code (use fastapi).
Audited -
adelabdelgawad Bundle Fetch ArchitectureClient and server-side fetch utilities for Next.js — direct backend calls from server code and API route proxying with auth refresh for client code. Use when setting up fetch utilities, configuring client-side API calls, or implementing server-side data fetching. Do not use to scaffold per-entity fetch code (use fetch-plan then fetch-implement).
Audited -
adelabdelgawad Skill Rust Nextjs ContractWire-contract parity for Rust APIs serving the shared Next.js frontend — camelCase JSON matching CamelModel output, limit/skip pagination, search and is_active filters, list envelopes with total, Bearer auth, and route prefixes, so Rust and FastAPI services are interchangeable behind the same frontend. Use when exposing ANY Rust endpoint that Next.js (or the existing fetch-architecture) will consume. Do not use for service-to-service-only APIs with their own contract.
-
adelabdelgawad Skill Using Fullstack AgentsAuto-triggering guide for fullstack-agents — ensures Claude automatically invokes the right code generation, review, and debugging skills before writing any FastAPI or Next.js code.
-
adelabdelgawad Skill Frontend TransformationMigrate an existing React (or other framework) frontend to a target framework (e.g. Next.js App Router) at 1:1 fidelity — same pages, routes, layouts, components, styling, state, and interactions, with nothing redesigned or reimplemented. Use when asked to port, migrate, convert, or transform a frontend to another framework while preserving it exactly. Do not use for greenfield pages (use nextjs / data-table) or backend migrations (use backend-migration-from-frontend).
Audited -
adelabdelgawad Skill Rust Clean ArchitectureClean Architecture + DDD for Rust API microservices — Cargo workspace with domain/application/infrastructure/shared crates, ports and adapters, use-case-owned transactions, parse-don't-validate value objects, four-stage error model, and composition root. Use when creating or structuring a Rust service, deciding where Rust code belongs, or generating Rust entities end-to-end. Do not use for Python services (use python-clean-architecture) or frontend code. No Leptos — Rust serves JSON APIs only.
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 audit-product, quiz-html, quiz-mastery. 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.