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.
-
sendaifun Bundle Animation Reverse EngineeringReverse-engineer any motion reference (a video from X/Twitter, Dribbble, a screen recording, a GIF) into production animation code through frame-level dissection. Use when the user shares a video/URL and says "implement this animation", "recreate this motion", "port this interaction", "how does this animate", "clone this effect", or wants to study how a reference moves before building it. Covers both timeline choreography (entrances, text sweeps, staggers) and interaction-driven motion (scrubbers, sliders, drag-driven scenes). Also fires when the user asks where to find good animation references or inspiration — it suggests curated sites and X accounts to hunt, then reverse-engineers whatever they bring back. Ports default to React/TypeScript with framer-motion; the analysis phases are framework-agnostic.
-
willyu1007 Bundle Fetch Frontend DataFetch and mutate frontend data with a consistent cache strategy (query keys, invalidation, suspense/loading, error handling, optimistic updates).
-
nodejsmith Skill I AuditUse when the user says: "audit this UI", "frontend quality", "full UI audit", "design audit". Comprehensive audit of interface quality across accessibility, performance, theming, and responsive design.
-
agile-v Skill UX Spec AuthorConverts UX/design intent into testable design specifications that feed requirements. Use when defining user flows, accessibility, or design constraints.
-
willyu1007 Bundle Implement Frontend RoutingImplement frontend routing with predictable route definitions, lazy loading, nested layouts, and error/404 handling.
-
willyu1007 Bundle Fix Frontend Runtime ErrorsFix frontend runtime errors (console exceptions, blank screens) by capturing repro steps and diagnostics, applying a minimal targeted fix, and verifying user-visible behavior.
-
nodejsmith Skill I OptimizeUse when the user says: "optimize frontend performance", "improve load time", "fix rendering". Improve frontend performance and rendering efficiency.
-
nodejsmith Bundle I Frontend DesignUse when building frontend components or pages. Core design skill for creating distinctive, production-grade interfaces that avoid generic AI aesthetics.
-
willyu1007 Bundle Organize Frontend CodebaseOrganize a frontend codebase by feature/module with clear public exports, predictable naming, and minimal cross-feature coupling.
-
willyu1007 Bundle Optimize Frontend PerformanceOptimize frontend performance through measurement-driven improvements (render optimization, code splitting, caching, virtualization).
-
propane-ai Skill AccessibilityApply WCAG and accessibility best practices to design review and audits. Use when auditing flows or specs for accessibility, writing a11y acceptance criteria, or recommending design changes for accessibility.
-
willyu1007 Bundle Apply Frontend Typescript StandardsApply frontend TypeScript standards for safety and maintainability (strict typing, props DTOs, safe utilities, no implicit any).
-
dangeles Skill Genesis DesignUse when building or changing any Genesis surface — a white paper, the paper library, a KOL record, a deck, an explorable, the bioreactor screens, or genesis.bio — or when a design question needs the house answer: colour, contrast, type scale, layout, focus rings, chart palettes, alt text, voice. Triggers on CSS work in ~/repos/white_papers, ~/repos/papers or ~/repos/kol, on any tokens.css or Genesis stylesheet, on greenfield work for a Genesis surface ("build a landing page for", "new page on genesis.bio", "a deck for"), and on "what colour should", "is this accessible", "how many series", "which font size", "what is the focus ring". Pair it with frontend-design, which builds the interface while this supplies the house rules. NOT for non-Genesis web work, and NOT for editing the guidelines repository itself (that has its own CLAUDE.md).
-
brite-nites Skill Flow Inventory Codebase ScanRetrofit-mode inventory generator for the flow-architecture plugin (implements CDR-023). Mines code signals (routes, server actions, dialogs, menu items, API endpoints) from an existing Next.js App Router codebase and synthesizes the proposed inventory. Six phases — Phase 0 (PROJECT-INTENT priority filter) -> Phase 1 (app-classifier interview, shared with Q19 greenfield) -> Phase 2 (pattern-driven candidates, shared) -> Phase 3 (deterministic code scan, retrofit-only) -> Phase 4 (synthesis with 4-tag implementation-status taxonomy + value-priority) -> Phase 5 (user confirmation, shared). Framework locked to Next.js App Router for v1. Triggered by `/flow:retrofit-project` when `flow-preflight` mode classifier returns `retrofit`.
-
hack23 Skill Testing StrategyNode.js testing with Vitest/Jest, MCP protocol testing, European Parliament API mocking, integration tests, and 80%+ coverage
-
dangeles Skill Python DeveloperUse when implementing Python code, from a well-scoped single function through a production-quality multi-file component — including component-level design decisions, tests, and documentation. NOT for omics/bioinformatics analysis (use bioinformatician), system-level architecture (use systems-architect), algorithm design or complexity analysis (use mathematician), statistical method selection (use statistician), or code review (use copilot for inline, /pr-review-toolkit:review-pr for pre-PR).
-
dangeles Bundle Systems ArchitectUse when designing software architecture, defining data structures, planning scalability, or making technical design decisions for complex Python systems — including bioinformatics pipelines, services, libraries, or analysis frameworks. NOT for single-component design within an existing architecture or routine class layout (use python-developer).
-
telum-ai Bundle Visual TestingProduces host-specific visual and accessibility evidence. Use during UI LARP after the target build becomes reachable.
-
hack23 Skill Secure Code ReviewSecurity code review using OWASP Top 10, input validation, and Hack23 ISMS secure development policy for TypeScript/MCP
-
telum-ai Skill Project Design SystemDefines tokens, primitives, and component standards. Use after project-architecture before project-plan for shared UI.
-
florinsenoner Skill Codebase AuditComprehensive codebase audit across 8 dimensions — backend, frontend, security, code quality, Convex patterns, Tailwind/UI, performance, and testing
-
djankies Skill Configuring Serverless ClientsConfigure PrismaClient for serverless (Next.js, Lambda, Vercel) with connection_limit=1 and global singleton pattern.
-
hack23 Skill Typescript Strict PatternsTypeScript strict mode patterns, branded types, discriminated unions, and type-safe architecture for MCP servers
-
hack23 Skill C4 Architecture DocumentationDocument system architecture using C4 model with context, container, component views and Mermaid diagrams
-
shaul1991 Skill API ContractAPI Contract Agent. OpenAPI 스펙 정의, Mock Server 생성, Contract-First 개발을 담당합니다. Frontend/Backend 간 API 계약을 관리합니다.
-
shaul1991 Skill Code ReviewerCode Reviewer Agent. Frontend/Backend 코드 리뷰를 담당합니다. 코드 품질, 테스트 커버리지, 보안, 성능을 검토합니다.
-
dangeles Bundle Scientific Analysis ArchitectUse when planning multi-chapter scientific research analyses with expert consultation — produces markdown analysis documents with pseudocode for RNA-seq, proteomics, or other data analysis workflows. NOT for software architecture (use systems-architect) or single-component design within an existing analysis (use python-developer).
-
joaquimscosta Bundle Tilt SetupInstall Tilt and scaffold or audit Tiltfile + tilt/ configurations with ecosystem-aware templates. Auto-detects Java/Gradle (Spring Boot), Next.js, Python/uv, and external infrastructure; recommends single-file or modular tilt/*.star + service-config.yaml + environments.yaml patterns based on project complexity. Bakes in production-context safety guards, PVC persistence toggles, JDWP debug ports, and optional Prometheus/Grafana/Traefik scaffolds. Use when user runs /devtools:tilt-setup, mentions "tilt setup", "setup tilt", "scaffold tiltfile", "audit tiltfile", "tilt configure", "tilt project setup", "Tiltfile", "local kubernetes dev", or "kubernetes development environment".
-
florinsenoner Skill Tailwind AuditAudit Tailwind CSS classes for redundancy, inconsistency, and legacy patterns
-
florinsenoner Skill Webapp TestingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
-
packmindhub Skill Create Run E2e TestsGuide for writing and running new Playwright end-to-end tests in the `apps/e2e-tests/` directory of the Packmind monorepo. Use this skill whenever you add or modify a spec that drives the real frontend and API — for example testing a user flow, a new page/route, a feature behind a flag, or a UI behavior end-to-end. Triggers on "write an e2e test", "add a Playwright test", "test this flow end-to-end", "cover this page with an e2e", "e2e for the frontend", or any work that lands a `*.spec.ts` under apps/e2e-tests/src/. Prefer this over hand-rolling raw Playwright `test()` calls — the codebase has mandatory fixtures and a Page Object Model you must follow.
-
packmindhub Skill Feature Flags AuthoringAdd, edit, or remove a Packmind feature flag across the shared registry, the frontend gate, and the backend helper. Use when the user wants to create a new feature flag, gate a feature behind a flag, open or restrict a flag to a domain/email, change a flag audience, retire or delete a flag, or asks how the feature-flag system is wired. This is the developer how-to counterpart to the feature-flags-audit skill.
-
ab-aswini Bundle Mobile DesignMobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.
-
packmindhub Bundle Working With Pm Design KitThis skill provides guidance for using the Packmind UI component library (@packmind/ui). It should be used when building or modifying frontend UI with PM-prefixed components, working with Chakra UI in the Packmind codebase, or when questions arise about available components, theming, or layout patterns. Triggers on mentions of PM components, @packmind/ui, Chakra UI usage, design kit, or frontend component implementation.
-
packmindhub Skill Michel Run Local Dev StackThe canonical recipe for starting, checking, and stopping the Packmind local dev stack with Docker Compose — the single source of truth other skills and the Michel agent defer to. Covers bringing the full stack (PostgreSQL, Redis, NestJS API, React/Vite frontend on :4200, MCP server, nginx) up in the background, the init services (dependency install + TypeORM migrations) you must wait on, the critical host-port trap that the API on container port 3000 is NOT exposed to the host and must be reached via the frontend Vite proxy at localhost:4200/api/v0, confirming the API and frontend are actually serving before you depend on them, the persistent-volume gotcha that leaves stale Postgres schema and node_modules behind between runs, building the CLI, and tearing everything down so no container is left blocking the run. Use this whenever you need Packmind running locally — to verify a change, record a UI or CLI demo, hit the API, seed data, or reproduce a bug — and whenever you are about to start or stop `docker co
-
packmindhub Bundle Hexagonal ArchitectureDescribes the hexagonal architecture (ports and adapters) used across the Packmind monorepo. This skill should be used when creating new domain packages, use cases, services, repositories, or any architectural component to follow established patterns.
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 ux-spec-author, mobile-design, animation-reverse-engineering. 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.