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.
-
decentraland Skill Perf TierUse when changing the build config, lazy-loading, manual chunks, hero prerender, or any code that affects Lighthouse scores / LCP / bundle size. Covers the dual-shell lazy boundaries, manual chunks setup (including the CSS gotcha), hero prerender, and deferred analytics. Triggers on edits to `vite.config.ts`, `scripts/prerender-hero.mjs`, `src/modules/DeferredAnalyticsProvider.tsx`, `src/modules/deferredThirdParty.ts`, `src/App.tsx` (lazy imports). Also on mentions of "LCP", "Lighthouse", "manualChunks", "modulePreload", "hero prerender", "lazy loading", "deferred analytics", "Core Web Vitals", "bundle size", "render-blocking".
-
decentraland Skill Avatar Background ColorUse when adding or editing any avatar surface (AvatarFace, custom avatar styled components, EventCard avatar slot, navbar avatar). Enforces the deterministic background color from ADR-292's NameColorHelper so avatars render the same hue here as in the unity-explorer. Triggers on "avatar", "AvatarFace", "AvatarImage", "creator avatar", "profile picture", or edits to files matching `**/avatar*` or any styled component in `**/*.styled.ts` whose name contains `Avatar`.
-
deepgram Skill MonitorUse when you need to watch, observe, or react to human terminal activity. Examples: "monitor the terminal for errors", "watch what the user is doing and provide help", "audit terminal activity for security issues".
-
devkindhq Skill Evidence CustomEvidence.dev custom components and plugins — creating Svelte components, component queries, plugin development and publishing
-
devkindhq Skill Evidence Core ConceptsEvidence.dev core concepts — SQL queries in markdown, templated pages, loops, if/else, formatting, query functions, exports, themes and the Svelte/Markdown hybrid syntax
-
edhahn Bundle Zenstack V3ZenStack v3 schema-first ORM for TypeScript. Use when working with ZModel schemas, ZenStack ORM CRUD operations, access control policies (@@allow/@@deny), database migrations, server adapters (Next.js, Express), runtime plugins, computed fields, polymorphism, typed JSON, or migrating from Prisma/ZenStack v2. Triggers on: ZModel, ZenStack, zenstack, .zmodel files, @@allow, @@deny, auth(), PolicyPlugin, ZenStackClient, @zenstackhq/orm, zen generate, zen migrate.
-
eliasstravik Skill DemoThe demo skill owns turning a product concept, release artifact, checklist, or named demo into a convincing, self-contained local try-it experience. It stages only missing product context with deterministic, visibly simulated behavior; builds or revises the focal interaction; serves it on loopback; and verifies the exact preview, restart path, and QA result. It triggers when a user asks to build, revise, activate, or use /demo for a realistic local demo or artifact experience. It does not own feature integration into an existing app router, testing an already-running localhost or dist build, comparing prototype directions or state models, converting Markdown into durable HTML, making demo videos, writing sales scripts, explaining mock design, or reviewing bugs without edits.
-
eliasstravik Skill Voice ModeThe voice-mode skill owns the conversation’s delivery and interaction behavior when the user needs to listen instead of look at a display. It triggers on explicit “/voice-mode” or “activate Voice Mode,” and on concrete hands-free context such as “I’m driving,” “I’m away from the screen,” “I’m wearing headphones,” or “keep every reply spoken,” especially when the user requests concise conclusions, verbal numbering, or spoken follow-ups. It remains active until explicit exit, speaks plain prose, and places visual or exact technical material elsewhere. It is not a text-to-speech or audio-file tool, a voice-over-script writer, a conversational-copy editor, an accessibility or VoiceOver fixer, a dictation or microphone setup guide, or a substitute for normal Markdown and visible checklists.
-
eliasstravik Bundle PrototypingTriggers when a user asks to prototype a decision, compare visible or behavioral options in throwaway pages, keep prototyping through a consultant, grilling, or wayfinder session, or says /prototyping. It builds one loopback session that grows step by step and also handles a one-off "prototype this" request. Not for durable standalone HTML artifacts, polished product demos, browser QA, or integrating selected prototype code into an application.
-
endorphin-ai Bundle Designer Frontend ContractThe universal, tech-agnostic DESIGNER ↔ FRONTEND contract — how the web designer and the frontend dev help each other, where they store their shared data, how they communicate, and how the contract between them is written and ENFORCED. Three sides: the DESIGNER freezes an approved mockup into a canonical oracle (oracle-manifest.json + baseline renders + a region/element inventory + token parity + a four-part visual acceptance contract); the FRONTEND dev consumes that contract and PORTS the oracle 1:1 (transcribe, never redesign), self-gating census → DOM → pixel before handoff; the VERIFIER (design-diff) independently screenshots every built page × access state × breakpoint against the frozen baseline and reports per-page PASS/FAIL — report-only, a mismatch is a gate reject. Works on ANY stack (Phoenix/LiveView, Rails/Hotwire, React, …): stack facts (dev server, template language, settle signal, token source, seed accounts) are read at runtime from docs/project_config/info.md, never baked in. Use when: freezi
-
lavidrori0702 Bundle Tableau Dashboard CreatorGuides data analysts through a multi-step Tableau dashboard creation workflow - brand setup, data exploration, dashboard planning, interactive HTML mock creation, Tableau implementation spec, and experimental TWB workbook generation. Use when the user wants to create a Tableau dashboard, build a dashboard mock, plan KPIs and charts, or generate a Tableau implementation document.
-
lifenewjob Skill Nebo Frontend MasteryFRONTEND-MASTERY SuperSkill v2.0
-
lindoelio Bundle Admin UI SvelteUse this skill when building admin dashboards, control panels, or internal tools with Tailwind CSS v4, Skeleton UI, and Svelte 5. Triggers for layouts with sidebar navigation, data tables with pagination/sorting, forms with validation, authentication pages, and responsive admin interfaces — even if the user doesn't explicitly mention "admin" or "dashboard." Covers Skeleton components, Svelte 5 runes ($state, $derived), and Tailwind v4 patterns.
-
lindoelio Bundle Universal Live CheckUniversal live-check framework for coding agents. Executes incremental, deterministic validation across all software domains (CLI, backend, frontend, mobile, embedded, libs). Change-type-aware (feat, fix, hotfix, refactor, migrate, docs). Triggers whenever an agent needs to validate code quality, run linting, perform pre-commit checks, verify builds, or validate changes in real-time. Use this skill for live validation during coding, pre-commit hooks, CI pre-flight checks, and rapid feedback loops.
-
linuxfoundation Skill Setup DocsRun the docs site, blog, or Storybook locally. Use when contributing to documentation, previewing blog posts, or developing UI components in isolation. Not needed for regular frontend development.
-
longyenkai83 Bundle Kallaway Hook MasterViết hook video ngắn (TikTok/Reels/Shorts) + caption FB/IG theo phương pháp Kallaway — 6 Hook Frameworks (Fortune Teller/Experimenter/Teacher/Magician/Investigator/Contrarian) × 5 Dream Outcome Formats (About Me/If I/To You/Can You/He-She Just Did) × 4 Component Alignment (Spoken+Text+Visual+Audio). Use when user wants to write hook for short-form video, viết hook video, viết caption mở đầu, brainstorm hook viral, audit hook cũ, hoặc apply Kallaway framework. Vietnamese-first. Triggers — "viết hook", "hook kallaway", "kịch bản reels", "hook viral", "audit hook video".
-
lst97 Skill SimplificationComplexity reduction and architectural streamlining for Frontend, Backend, and Quality agents.
-
luna-prompts Skill CollectionChoose which SkillNote skill collection is active for this project. Use when user says "change collection", "switch skills", "use frontend skills", "show collections", or at first session in a new project when recommended.
-
manalkaff Bundle OpendesignUse when starting any design task — HTML pages, slide decks, interactive prototypes, UI kits, brand systems. Establishes the base designer role, workflow, and taste rules, and routes to specialist skills for the artifact type.
-
manalkaff Skill Setup OpendesignUse when ./opendesign/index.html does not exist in the current project. Initialises the OpenDesign output folder structure, copies the viewer, and writes an empty manifest.
-
manalkaff Skill Interactive PrototypeUse when the user asks for a working, clickable prototype — something that behaves like a real app rather than a static mockup. React + useState/useEffect, realistic fake data, working state transitions.
-
manutej Bundle Noether HarnessGenerate conservation-constrained agentic coding harnesses from the Noether Dual-Loop kernel — a μ meta-meta-prompt that emits a λ meta-prompt, which emits a concrete harness (typed conservation lens, four role prompts, per-framework fragments) for LangGraph, Aider, Cursor, OpenHands, AutoGen, ReAct+tools, or custom loops. Use whenever the user wants a self-refining coding agent where tests, type-checks, API stability, and architecture act as conserved invariants; a propose→tailor→commit→reflect dual loop with a bounded inner refinement loop and an outer invariant-learning loop; prediction-time "tailoring" (Alet et al.) transposed to LLM agents; or adaptation with ZERO weight updates / no fine-tuning. Also use to instantiate, extend, or explain such a harness. Trigger on "Noether harness", "conservation lens", "dual-loop agent", "tailoring loop", "tests-as-invariants harness", or a reference to the Noether meta-meta-prompt — even phrased only as "stop my agent breaking tests when it refactors."
-
manutej Skill Dry And ReuseStops duplication and reinvention — the failure GitClear measures as "rework" (copy-paste up, refactoring down, the signature of AI code with a short shelf life). Use before writing any helper, util, type, constant, or component, and when reviewing a diff for repeated logic. Enforces search-before-build, consolidate- don't-clone, and DRY-as-knowledge (one rule, one authoritative place). Triggers: "is there already a function for this", "this looks duplicated", "DRY this up", "extract the common logic", "we keep rewriting this", before adding any utility.
-
manutej Bundle Design DnaExtracts a prospect's real brand palette from their public materials, harmonizes it into a WCAG 2.2 AA-audited token set, and fuses it with CETI house rigor so every deliverable feels already theirs. Emits design/tokens.css (the versioned sf-tokens schema every artifact skill consumes) and design/palette.md (provenance + contrast matrix). Use when the user says "design DNA for [company]", "extract their colors", "brand the deliverables for this prospect", "tokens for this client", or automatically as the design stage of any factory run before artifacts are built. Refuses to ship invented colors or failing contrast pairs.
-
manutej Bundle Pitch DeckBuilds the proposal slide deck for a prospect — an animated single-file HTML deck by default, .pptx when the buyer's meeting culture demands Office, or both — walking from evidenced weaknesses (tells) to the sign-here moment. Use when the user says "pitch deck", "proposal deck", "slides for [prospect]", "deck for the meeting", or as the 05-deck stage of a factory run. Every number comes from SYNTHESIS; every scope item traces to a tell; the tells ↔ scope ↔ price bijection is the spine. The HTML artifact is a precise, buildable spec (16:9 stage, anime.js v4, `--sf-*` tokens, ≤2.5MB, zero console errors, WCAG AA, prefers-reduced-motion) — not a vibe.
-
mark2685 Skill Buf BumpBumps generated protobuf packages in the flow-frontend monorepo and fixes the resulting TypeScript breakage. Use when the user says "buf bump", "bump protos", "update proto types", "pull the latest protos for a service", or "/buf-bump". User-invoked only — this rewrites package pins and patches consuming code.
-
mark2685 Skill New PageScaffolds a new page in flow-global or flow-factory following all project conventions. Use when user asks to "create a page", "add a new route", "scaffold a page", or "/new-page".
-
mark2685 Skill BrainstormingShapes a rough idea into an approved written spec before any code, through one-question-at-a-time dialogue — the generalist planning step ux-planner (UI-only) doesn't cover. Use when the user says "let's brainstorm", "help me shape this idea", "I want to plan this before building", "write a spec for", or "/brainstorming".
-
mark2685 Skill New ComponentScaffolds a new React component following project conventions. Use when user asks to "create a component", "add a new component", or "/new-component".
-
mark2685 Skill Proto MigrationFixes flow-frontend breakage after a proto bump — updates converters, server actions, and forms — distinguishing mechanical renames from semantic changes that must be escalated. Use when the user says "fix the proto breakage", "the buf bump broke types", "migrate after the proto change", "update converters for the new protos", or "/proto-migration". User-invoked only — it is the side-effecting post-bump companion to buf-bump, gated to match.
-
mark2685 Skill E2e Test FixtureMakes flow-frontend Playwright tests runnable against the real stack — seeds employee + capabilities, authenticates through the authtest OIDC flow, and points the runner at flow-factory:3001 or flow-global:3000. Use when the user says "set up an e2e fixture", "my Playwright test won't authenticate", "seed state for e2e", "run e2e against the local stack", or "/e2e-test-fixture".
-
mark2685 Skill Frontend TestingScaffolds and strengthens flow-frontend tests with Vitest + React Testing Library, asserting rendered DOM through the real UI path, and hands E2E off to Playwright. Use when the user says "add a test", "write tests for this component", "strengthen these tests", "test this hook", or "/frontend-testing".
-
mark2685 Bundle Systematic DebugRoot-cause debugging workflow for the flow-frontend monorepo — Vitest failures, TypeScript strict/`lint:tsc` errors, eslint-plugin-boundaries violations, proto type mismatches, hydration mismatches, and Turbo build issues. Use when working in flow-frontend and a test, type-check, lint, or build fails, or the user says "debug this", "why is this failing", or "/systematic-debug". For non-flow-frontend code use the generic diagnose skill.
-
mark2685 Skill Add Server ActionAdds a flow-frontend server action wired to an RPC via @hadrian-mtv/connect-server-actions, placed in the _lib/actions folder with proto conversion at the edge and getErrorMessage surfacing. Use when the user says "add a server action", "call this RPC from the server", "wire up a mutation to the backend", or "/add-server-action".
-
mark2685 Skill Receiving Code ReviewTriages incoming code-review comments on a flow-frontend change, verifying each is real and confirming the fix actually landed before applying — never editing on confidence alone. Use when the user says "address the review comments", "handle this PR feedback", "apply the reviewer's suggestions", "go through the review", or "/receiving-code-review".
-
martin1847 Bundle Frontend Explorer探索型前端测试——派一个「第一次见这个产品」的探索者,用 playwright-cli 驱真浏览器走完一段旅程,回一份按挡路程度排序的「在哪卡住 / 哪里看不懂」清单,每条带屏幕原文与截图证据。触发:探索一遍 / 走一遍 / 踢踢轮胎 / UX pass / 找新用户会在哪迷路。不用于判据已知的验收探针、回归测试、性能、代码评审。
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 perf-tier, evidence-custom, kallaway-hook-master. 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.