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.
-
skyscanner Skill Backpack CSS Vars MigrationMigrate a Backpack component's SCSS mixin from static SASS tokens to CSS custom properties (CSS vars) for light/dark mode support, while preserving SASS tokens as fallbacks. Use when: (1) a component needs light/dark mode theming via the new CSS var system, (2) a component still uses bare SASS token values (e.g. tokens.$bpk-text-primary-day) instead of var() declarations, (3) you need to wire up BpkThemeProvider overrides to the new CSS var names. Covers the full migration: SCSS mixins, themeAttributes.tsx, stories, and tests.
-
skyscanner Bundle Backpack Code Review ChecklistSelf-improving multi-agent review orchestrator for Backpack component PRs. Runs 6 parallel specialist agents (including a learned-patterns agent that mines past PR comments), then confidence-scores findings. Use for PR review, Constitution compliance checks, and pre-merge validation. Run with "learn" to mine recent PRs and auto-update checklist rules.
-
smcllns Skill Obsidian HTML DocsUse when creating .html docs intended to render inline in Obsidian with the HTML Docs plugin (github.com/smcllns/obsidian-plugin-html-docs).
-
smixs Bundle Dbrain ProcessorPersonal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
-
soonjune Bundle NightshiftExecutes a user-written handoff document overnight as an unattended autonomous work session — running prioritized missions (implementation and verification, performance improvement, research, data generation, long-running job babysitting) under strict guardrails with an append-only journal, then producing a polished Korean morning report for 조간보고/scrum by a hard deadline. Use when the user prepares to leave work for the night or asks for overnight execution — requests like "nightshift", "야간 작업", "밤새 돌려줘", "밤새 작업해줘", "overnight run", "handoff 실행해줘", "핸드오프 작성", "인수인계 문서 만들어줘", "아침 보고서", "조간보고 준비", "poll cadence", "heartbeat 주기" — including drafting or validating the handoff document itself, adjusting the observation cadence of an active night run, and rebuilding or converting a morning report (HTML, PPT, Markdown) from a run journal. Do not use for cron or scheduled automation, or for recurring checks outside a night run.
-
ssheleg Bundle Agent HarnessUse when the question is what the agent is TOLD rather than how its loop is wired — writing or fixing a system prompt, shaping tools so the model picks the right one, deciding whether a job wants a workflow or an agent, or choosing between ReAct, reflection and voting. Also auditing an agent system somebody else built: tracks, evidence tiers and a prioritized plan instead of a score, plus a scanner. Carries Pi as a worked kernel implementation — SDK, RPC and extension seams — for embedding or extending a harness. Triggers - "system prompt", "tool description", "agent picks the wrong tool", "agent loops forever", "prompt engineering", "harness engineering", "ReAct loop", "react pattern", "workflow or agent", "static or dynamic", "audit this agent", "embed an agent", "agent SDK", "Pi harness", "системный промпт", "агент не вызывает тул", "аудит агента", "встроить агента". Not for the loop's plumbing, its evals, or its protocols — those are siblings.
-
sswconsulting Skill Process SurveyProcess a CSV/XLSX survey export into a comprehensive, multi-tab HTML dashboard using specialized analysis agents. Use when the user provides survey data, has a CSV/XLSX file to analyze, or mentions survey results. This is the PRIMARY skill for handling surveys.
-
sswconsulting Skill Generate ReportOne-shot full survey report. Takes one or more CSV/XLSX survey exports (e.g. Microsoft Forms), runs the complete analysis pipeline into a multi-tab HTML dashboard, records the narrated recap video (best-effort), and deploys to surge.sh (or reports the local path when surge isn't logged in). Use when the user wants the complete report from a survey file in a single command, says "generate a report", "full report", or invokes /generate-report.
-
stevysmith Bundle Rive ReactTrigger when: (1) Using @rive-app/react-canvas or @rive-app/react-webgl, (2) Using useRive hook or RiveComponent, (3) Building React components with Rive animations, (4) User mentions "Rive React" or "useRive", (5) Implementing scroll-based or parallax animations with Rive. Best practices for integrating Rive animations in React applications using the official Rive React package. Covers hooks, layout, and scroll animations.
-
studiolxd Bundle XapiUse when integrating xAPI (Experience API / Tin Can) in a web app or server with @studiolxd/xapi — sending/querying statements, managing State/Activity Profile/Agent Profile documents, parsing launch URLs, handling Result errors, or wiring the client across React, Vue, Angular, Svelte, vanilla JS, or LRS server helpers.
-
studiolxd Bundle ScormUse when integrating SCORM 1.2/2004 in a web app with @studiolxd/scorm — initializing a session, reading/writing CMI data (score, completion, suspend data, interactions, objectives), handling Result errors, or wiring lifecycle/auto-commit across React, Vue, Angular, Svelte, Web Components, or vanilla JS.
-
subsquid-labs Bundle Squid PerfCompare sync-time performance across one or more Squid SDK deployments. Fetches logs via sqd CLI, parses per-service progress, and generates a self-contained HTML report plus a Markdown summary with wall-clock/active-time/downtime breakdowns at percentage-based block breakpoints. Supports single-indexer mode (metrics only, no comparison). Use when the user invokes "/squid-perf", asks to compare Squid deployment sync times, or references squid performance profiling.
-
sungjunlee Bundle Spec GrillCreate or refine spec/capabilities.md from repo signals when a consumer, a cross-tree contract, or a 3-axis audit needs it. Use for capability specs, component contracts, middle-layer specs, repo boundaries, 능력 명세, or grill.
-
willmusubi Bundle Immersive Dialogue UI沉浸式对话体验的前端输出模块框架生成器。当用户需要为角色扮演、互动小说、AI伴侣等场景创建美化的对话界面模块时使用。支持:(1) 生成单个或组合模块(时间地点、人物状态、记忆、群聊、公众讨论、旁白、好感度、选项分支等);(2) 根据用户需求定制模块;(3) 应用主题美化(赛博朋克、古风、现代等);(4) 与frontend-design skill协作实现高级美化。输出为可渲染的React JSX或HTML组件。
-
willmusubi Skill Mufy Style GeneratorMUFY 角色卡美化工具。用户用自然语言描述视觉需求(色系/顶部栏/气泡/按钮/折叠栏/简介卡/背景/特效),生成纯 CSS 代码粘贴到「小剧场」输入框生效。仅改视觉样式,不改功能交互。
-
wso2 Skill Oxygen FormGenerate forms with Form.* components and validation. Use when creating input forms, multi-step wizards, or form validation.
-
wso2 Skill Oxygen LayoutGenerate application layouts with AppShell, Header, and Sidebar. Use when creating app shells, navigation structures, or dashboard layouts.
-
wso2 Skill Oxygen MigrateMigrate existing MUI code to Oxygen UI patterns. Use when converting @mui/material imports, replacing MUI components, or updating to Oxygen UI conventions.
-
wso2 Skill Oxygen ComponentGenerate Oxygen UI React components following best practices. Use when creating new components, data tables, cards, or UI elements with the Oxygen UI library.
-
xerrors Bundle Product Launch Card Kit为应用、开源项目、Agent Skill、插件、开发者工具或版本更新制作发布素材。适用于小红书图文卡片、产品发布卡、可交互 HTML 工作台、PNG 批量导出、发布文案、整套视频和背景音乐等需求。采用稳定的 Node.js framework 与可替换 theme 架构。
-
yotharit Skill Pm Status ReportComprehensive Huly project status report for stakeholders. Includes executive summary, key metrics, milestones, velocity trend, team performance, exhaustive task list grouped by component and broken down by status, bottlenecks, risks, quality, documentation, and recommendations. Trigger on: /pm-status-report, 'full project status', 'comprehensive status report', 'weekly status report', 'project report for PROJ', 'status report'.
-
yuezhiai Skill Openkb Deck NeonUse when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black background, teal/sky/magenta/amber neon accents, glassmorphism panels, aurora gradient atmosphere) — opened in a browser, full-screened, shared. For the warm, printed, serif look use openkb-deck-editorial instead. Does NOT apply to generating skills (`openkb skill new`), research reports, or scrolling long-form documents.
-
yuezhiai Skill Openkb HTML CriticUse to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every other. Also catches missing keyboard navigation, bullet-dump / wall-of-text failure modes, broken self-containment (external link/script/img). Patches the file in place; never changes the original content (slide text, numbers, named entities are the author's work, not yours).
-
yuezhiai Skill Openkb Deck EditorialUse when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content. Generates a polished single-file HTML deck in the Editorial Monocle visual direction (warm cream background, serif type, brick-red accent) — designed to be opened in a browser, full-screened, and shared. Does NOT apply to generating skills (that's `openkb skill new`), long-form research reports, or interactive prototypes.
-
zachjxyz Skill Stack KnowledgeProject technology stack patterns for Next.js + Neon Postgres + Drizzle ORM + Better Auth + Tailwind CSS
-
zerx-lab Bundle GpuiGPUI framework knowledge covering actions/keybindings, async/background tasks, context management (App/Window/Context<T>/AsyncApp), custom elements (low-level Element trait), entity state management, event system, focus handling, global state, layout/styling (flexbox/CSS-like), and testing. Use when working with any GPUI framework concept, building GPUI applications, or needing guidance on GPUI-specific APIs and patterns.
-
zerx-lab Skill Gpui App从零搭建 gpui / gpui-component 桌面应用的起步模板。涵盖 Cargo.toml git 依赖(gpui + gpui_platform + gpui-component)、main.rs 入口(application().run / open_window / Root)、资产与图标注册、WindowOptions、退出与激活。创建新 gpui 项目、初始化工程、写 main.rs 或配置依赖时使用。
-
zerx-lab Bundle Gpui ComponentHow to use the gpui-component UI library in GPUI applications. Use when building UIs with gpui-component components (Button, Input, Select, Dialog, Tabs, Sidebar, List, Table, etc.), setting up the library, handling component state, theming, or finding the right component for a given UI need.
-
zerx-lab Skill Gpui Migrationgpui 新旧 API 对照表(2025-01 大重构前 → 当前)。遇到 ViewContext/WindowContext/View/Model/new_view/FocusableView/旧 spawn 闭包等旧 API,或迁移旧 gpui 代码、修复相关编译错误时使用。同时收录 gpui-component 的更名(TextInput→Input、open_modal→open_dialog 等)。
-
zhanlincui Bundle Wechat PublishUse when publishing HTML articles to WeChat Official Account drafts, especially when you need cover upload, automatic cover generation, body image rewriting, CSS-variable compatibility, or draft metadata like author and comment settings.
-
zhanlincui Bundle Markdown2wechatUse when converting Markdown into WeChat-compatible inline HTML with theme styles for preview, copy-paste, or downstream draft publishing.
-
zhylq Bundle Zhy Wechat PublishUse when publishing HTML articles to WeChat Official Account drafts, especially when you need cover upload, automatic cover generation, body image rewriting, CSS-variable compatibility, or draft metadata like author and comment settings.
-
zhylq Bundle Zhy Markdown2wechatUse when converting Markdown into WeChat-compatible inline HTML with theme styles for preview, copy-paste, or downstream draft publishing.
-
twofourlabs Skill React Native Migration 0 79 X To LatestThis skill provides a migration guide for react native from 0.79.x to latest 0.83.x version.
-
tylergibbs1 Bundle Designing AgentsDesigns agentic AI systems by selecting the right architecture pattern and context engineering strategy. Triggers on "build an agent," "agent architecture," "agent design," "multi-agent," "agent pattern," "orchestration," "context engineering," "sub-agents," "agent workflow," "Ralph loop," "ReAct," "swarm," "coordinator pattern," "how should I structure my agent," "my agent loses context," "agent keeps failing on long tasks." For tool-level design, see designing-agent-tools.
-
uplift-technology-company-limited Bundle Vercel Gha DeploySet up (or fix) deploying a Next.js / frontend repo to Vercel from a GitHub Actions workflow — with an org-level VERCEL_TOKEN, a main-only branch gate, and an auto-bumped vX.Y.Z version tag baked into the build and shown in the UI. Use this WHENEVER the user wants to add a Vercel deploy pipeline via GitHub Actions, move a repo from manual `vercel --prod` to CI deploy, run the build on a self-hosted runner, wire auto-versioning onto Vercel deploys, or bootstrap a not-yet-set-up repo (git init → GitHub → vercel link → deploy) — even if they don't name this skill. NOT for: fixing app/code bugs that happen to surface in a Vercel build, one-off manual `vercel --prod` runs, Vercel dashboard settings (env vars, domains, rollbacks), Vercel's native git integration (this skill uses GitHub Actions instead), or deploys to other targets (AWS ECS, Docker, a VPS).
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 backpack-css-vars-migration, backpack-code-review-checklist, obsidian-html-docs. 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.