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.
-
opendatadiscovery Skill NavigateFind where a feature, component, or concept lives in the ODD codebase. Uses the navigation index for O(1) lookups.
-
pablolira-1982 Skill Omniroute Web FetchFetch a URL and convert to clean markdown via OmniRoute proxying Jina Reader, Firecrawl, raw HTML strip. Use when the user wants to ingest a webpage as markdown for context in an LLM conversation.
-
pablolira-1982 Skill Omniroute CompressionConfigure OmniRoute token compression to save 60–90% of context tokens. Covers RTK (command/tool output), Caveman (prose), stacked mode (both), and the MCP accessibility-tree filter (browser snapshots). Use when the user wants to reduce costs, fit long sessions into context windows, or speed up AI responses.
-
piyushverma0 Skill Material3Material 3 Expressive components and theming for Android AI agents. Use this skill for any M3 component: TopAppBar, LargeTopAppBar, CenterAlignedTopAppBar, BottomAppBar, FAB, ExtendedFAB, NavigationBar, NavigationRail, NavigationDrawer, NavigationSuiteScaffold, ModalBottomSheet, Chip (Filter/Assist/Input/Suggestion), Badge, SegmentedButton, DatePicker, TimePicker, SearchBar, Slider, Switch, Checkbox, RadioButton, ListItem, Divider, ProgressIndicator, Snackbar, Tooltip, PullToRefreshBox, ExposedDropdownMenuBox, Card/ElevatedCard/OutlinedCard, shape morphing, MotionScheme, dynamic color, tonal elevation, surface containers, color roles, M3 migration from M2. Always apply when using any androidx.compose.material3 API.
-
piyushverma0 Bundle Compose UIJetpack Compose UI best practices for AI agents building Android apps. Use this skill whenever writing any Composable function, building screens, handling UI state, working with Scaffold, LazyColumn, ModalBottomSheet, BottomSheet, edge-to-edge, IME keyboard insets, recomposition, side effects, LaunchedEffect, DisposableEffect, remember, collectAsStateWithLifecycle, StateFlow, SharedFlow, UiState, loading/error/empty states, accessibility semantics, Material 3 components, Coil images, TextField, animations, modifiers, or any Compose layout. Always apply this skill before writing any @Composable function.
-
piyushverma0 Skill AccessibilityAndroid accessibility for AI agents. Use this skill whenever implementing accessibility, TalkBack support, content descriptions, semantic properties, touch target sizes, contrast ratios, screen reader support, contentDescription, semantics modifier, clearAndSetSemantics, mergeDescendants, heading, stateDescription, traversalOrder, custom actions, live regions, accessibility service, WCAG compliance, accessibility audit, or any Compose accessibility. Required for Play Store submission in many markets. Always apply before shipping any screen.
-
pratchaya0 Bundle Ssdมาตรฐานการพัฒนาซอฟต์แวร์ของทีม SSD: React/TypeScript, .NET Core, Python, Git — ใช้เมื่อเขียนโค้ด, review, refactor, ตั้งค่าโปรเจค, หรือถามเรื่อง conventions ของ Smile Solution Development
-
pratchaya0 Skill Ssd React APIใช้ skill นี้เมื่อเรียก API ด้วย Axios ใน React, สร้าง React Query hook, ใช้ NSwag สร้าง API client, หรือจัดการ HTTP request/response ตามมาตรฐาน SSD
-
pratchaya0 Skill Ssd React Formใช้ skill นี้เมื่อสร้าง form ใน React ด้วย Formik, ต้องการ validation, ปรับแต่ง MUI component ให้ใช้กับ Formik, หรือถามเรื่องการจัดการ form submission ตามมาตรฐาน SSD
-
pratchaya0 Skill Ssd React Stateใช้ skill นี้เมื่อใช้งาน Redux ใน React, สร้าง slice, ตั้งค่า rootReducer, หรือ dispatch/subscribe state ใน component ตามมาตรฐาน SSD
-
pratchaya0 Skill Ssd Frontend Setupใช้ skill นี้เมื่อตั้งค่าโปรเจค Frontend ใหม่, ถามเรื่องโครงสร้าง folder ของ React, เครื่องมือที่ต้องติดตั้ง, naming conventions สำหรับ TypeScript/React, หรือ environment variables ของ SSD
-
pratchaya0 Skill Ssd Frontend Reviewใช้ skill นี้เมื่อต้องการตรวจสอบ code React/TypeScript (.tsx/.ts) ว่าตรงมาตรฐาน SSD หรือไม่ — ครอบคลุม naming, component structure, TypeScript types, Formik, Redux, React Query, และ environment variables
-
pratchaya0 Skill Ssd React Componentใช้ skill นี้เมื่อเขียน React component, กำหนด Props type, ใช้ Refs/Fragments, ตั้งชื่อ component, page, หรือ module ตามมาตรฐาน SSD
-
pratchaya0 Skill Ssd Frontend Refactorใช้ skill นี้เมื่อต้องการแก้ไข code React/TypeScript (.tsx/.ts) ให้ตรงมาตรฐาน SSD อย่างปลอดภัย โดยไม่ทำให้ compile พัง — ใช้หลัง ssd-frontend-review หรือใช้เดี่ยวเมื่อรู้ violations อยู่แล้ว
-
pratchaya0 Skill Ssd Bug Std Version Checkerใช้ skill นี้เมื่อ user ไม่เห็น version ใหม่หลัง deploy, browser โหลด JS เก่า, หรือ popup แจ้ง version update ขึ้นซ้ำ / ไม่ขึ้นเลย — แก้ bug VersionChecker ใน project ที่ใช้ react-ts-template-2023
-
pratchaya0 Skill Ssd Bug Std Auth Redirect Loopใช้ skill นี้เมื่อ user เจอหน้าขาว, redirect loop ไม่หยุด, หรือหลัง login แล้วไม่เข้าหน้าหลัก — แก้ bug auth redirect loop ใน project ที่ใช้ react-ts-template-2023 (oidc-client-ts)
-
rotoslider Bundle Web ScrapingScrapes webpages for text and images using a headless browser (JS-rendered) or static HTML. Downloads images and files from the web.
Audited -
taxueseek Bundle Taxue Career Resume简历/JD 引擎——简历诊断、JD 解码、双向改写、简历生成、定向投递优化,覆盖不同行业与人群。求职者写简历、匹配 JD;雇主写 JD、筛选简历。 产出层:建立简历母版(master.json),从母版派生各投递版本(custom.json → 独立 HTML → 浏览器打印 PDF + ATS 纯文本 + 匹配报告)。 触发:/taxue-career-resume、帮我看看简历、简历投了没回音、帮我写简历、改简历、JD看不懂、简历怎么改、简历没回音、简历母版、简历版本、简历 HTML Not for: 面试 → taxue-career-interview;选Offer → taxue-career-offer。
Audited -
fei2-labs Bundle Research To WechatA native research-first pipeline that turns a topic, notes, article, URL, or transcript into a sourced article with an evidence ledger, polished Markdown, inline visuals, cover image, WeChat-ready HTML, browser/API-ready draft assets, and optional multi-platform distribution. Use when the user wants 深度研究、改写成公众号、写作、排版、配图、HTML 转换、公众号草稿生成、多平台分发.
Audited -
jdinkla Skill Story A11Y LinterCheck a user story against WCAG 2.2 standards — find accessibility issues with cited WCAG criteria, conformance level (A/AA/AAA), impact, affected users, code examples, and assistive-tech considerations. Use when the user asks for an a11y review, accessibility check, WCAG audit, or to catch a11y issues before implementation.
-
jdinkla Skill Story NonfunctionalExtract 6–12 specific, measurable nonfunctional requirements (performance, scalability, security, reliability, accessibility, observability, usability, maintainability) for a user story, with priority and rationale. Use when the user asks about NFRs, quality attributes, SLAs, or "what should this thing do besides the functional part?".
-
jdinkla Skill Story ImplementationProduce a rough technical implementation plan for a user story — 6–12 tasks organized by phase (Data/Backend, Frontend, Integration, Testing, Deployment) with effort estimates, technical considerations, and risks. Use when the user asks "how would we build this?", wants a task breakdown, or needs an implementation sketch before starting work.
-
jdinkla Skill Story Visual RegressionPredict which existing screens or components may break visually based on the CSS/component changes described in a user story — affected screens, risk levels, affected visual elements, screenshot checklist. Use when the user asks about visual regression risk, which screens to screenshot-test, or what downstream UI to re-check after a style/component change.
-
launch52-ai Bundle A11YAudit and implement accessibility in Flutter apps. Use when adding semantic labels, testing screen reader compatibility, ensuring WCAG compliance, fixing accessibility issues, or making UI accessible to all users. Covers Semantics widgets, contrast ratios, touch targets, and assistive technology support.
-
leoluyi Bundle Eli5Explain a topic to someone who knows nothing about it, as a single-file HTML picture explainer: big visuals, very few words, no jargon. Trigger on /eli5 <topic>, 「用五歲小孩聽得懂的方式解釋」, 「幫我做一個超簡單的圖解說明」, "explain X like I'm 5", or "make me a dead-simple picture explainer of X". Not for plain-language rewrites of existing prose (plain-speak), dense information graphics for informed readers (infographic-design), slide decks, or accurate technical documentation.
-
leoluyi Bundle Visual Output QAReview rendered visual artifacts against one shared delivery standard. Use after producing or materially editing SVG, browser-rendered HTML, exported graphics, PPTX, PDF, or other fixed-layout visual output, and when the user asks to 檢查爆版、裁切、碰撞、字型、缺字、對比或交付品質. Do not invoke for choosing a visual style, writing slide content, or reviewing prose without a rendered artifact.
-
leoluyi Bundle Infographic DesignDesign or review explanatory graphics as SVG or single-file HTML: infographics, 資訊圖表, 懶人包, 圖解, one-pagers, visual summaries, timelines, comparisons, process explainers, learning recaps, and figures for documents. Route standalone charts, dashboards/BI, slide decks, syntax cheatsheets, knowledge documents, and exact-scale data charts elsewhere; plain-language explanations go to plain-speak. Explicit infographic requests qualify even when data is precise.
Audited -
lichtblick-suite Skill Panel LogDeep Log panel knowledge: react-window VariableSizeList virtualization, dynamic measured row heights, autoscroll/tail behavior, multi-format log normalization, and level/text filtering.
-
lichtblick-suite Skill Message PathDeep knowledge about the message-path package: path syntax, parsing grammar, data extraction from nested messages, and React hook integration. Shared across Plot, RawMessages, StateTransitions, and general panel agents.
-
lichtblick-suite Skill Message PipelineDeep MessagePipeline implementation knowledge: zustand store shape, React context provider, subscription merging/memoization, render-state flow, and the Player→panel data bus.
-
lichtblick-suite Skill Panel Raw MessagesDeep RawMessages panel knowledge: legacy (react-json-tree) vs virtual (@tanstack/react-virtual) implementations, flattenTreeData, TreeNode shape, expansion-state management, shared logic hook, and diff mode.
-
endalk200 Bundle Improve Codebase ArchitectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
-
mjcreativelab Bundle Game UI DesignWorld-class game UI design expertise covering visual style direction, motion design, HUDs, menus, controller navigation, diegetic interfaces, and safe-zone handling — from Nintendo-style clarity and Dead Space-style in-world UI to Persona-style kinetic menus and esports readability. Makes UI look and move like a shipped modern video game via style archetypes, choreographed animation, and copy-paste CSS recipes. Use whenever the user touches game ui, game interface, title screen, main menu, pause menu, hud, heads up display, game menu, inventory ui, health bar, stamina bar, minimap, crosshair, button prompt, controller ui, gamepad navigation, diegetic interface, in-world ui, quest tracker, damage numbers, cooldown indicator, radial menu, game feel, juicy ui, game animation, game-style ui, console ui, or handheld ui — even if they do not explicitly say "game UI".
-
mjcreativelab Bundle Branch Visualizegit ブランチ単位で実装内容を可視化する。対象ブランチとマージ先ブランチの差分を分析し、 変更モジュール・ライブラリ増減・データ/ドメインモデルと直接の関連範囲を Mermaid / D2 / HTML(ノード数で自動選定、--format で明示指定可)の構成図として docs/branch-diagrams/ に出力する。--models でモデルの内部構造(クラス図/ER 図・ メンバー単位の差分マーカー付き)も描ける。対象はブランチ名のほか PR 番号(#123) でも指定できる。レビュー準備・作業内容の俯瞰に使う。 リポジトリ全体のアーキテクチャ図は作らない(変更箇所と直接関連範囲に限定)。 ユーザーが「ブランチを可視化して」「変更内容を図にして」「/branch-visualize」と言ったら起動する。
-
mjcreativelab Bundle Structure Visualize指定された開発構造(インフラ構成、ER 図、コンポーネント設計、クラス構成、モジュール依存など)を 自己完結 HTML の構成図として docs/structure-diagrams/ に出力する。入力は会話で説明された設計・ 設計ドキュメント・リポジトリ内の実体(IaC / DB スキーマ / ソースコード)のいずれでもよい。 カテゴリ別配色とエリア枠(レイヤー・所属のグルーピング囲み)、ノード詳細パネル・ズーム/パン付き。 git ブランチ差分の可視化は /branch-visualize(本スキルは指定内容のスナップショット構造を描く)。 ユーザーが「構造を可視化して」「構成図にして」「/structure-visualize」と言ったら起動する。
-
black-yt Bundle Markdown To PDF当需要用 Python 将 Markdown 转为 PDF,并保留表格、代码块、图片路径和基础 CSS 样式时使用。
Audited
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 ssd-react-component, branch-visualize, ssd-react-form. 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.