Web & Frontend

kevintsai1202 Bundle

Use this skill when you have structured course content (or any chapter-based dataset) in markdown form and need to turn it into a working interactive website — without picking a framework, without a build step. Triggers on phrases like "做成網頁", "轉成 SPA", "course-data.js", "render 函式", "把講義變網頁", "static site from markdown", "vanilla JS site", "no-framework site", "single-page app from markdown". The output is a vanilla HTML + JS single-page app that opens with `npx serve` and persists state in localStorage. Always invoke AFTER `course-content-authoring` (content stable), BEFORE `static-spa-interactions` (this skill produces the scaffold; interactions adorn it).

kevintsai1202 Skill

Use this skill when an existing multi-day public-class teaching site needs to be condensed and re-packaged for a corporate in-house training — typically a half-day or one-day intensive (e.g. 4-day public class → 6-hour corporate). Triggers on phrases like "企業包班", "濃縮版", "客製化課程", "corporate edition", "intensive version", "in-house training", "single-file deliverable", "客戶端課程", "壓縮成一天", or when the user wants a single-folder zippable deliverable for a client. This skill builds on top of an existing site — picking units, condensing time allocation, embedding data into a single HTML, setting up asset fallback chains, and producing an offline-ready package.

khangnhoang Bundle

Product-aware visual design for VocaSpace/DevSpace UI. Use when building or reshaping product-facing UI; apply distinctive visual direction proportionally while preserving safe, maintainable UX.

khangnhoang Bundle

Repository-specific strategy for unit, schema, component, form interaction, Server Action, Route Handler/API, integration, regression, smoke E2E, and broader browser tests. Use before adding, changing, refactoring, or reviewing tests, and whenever a code change requires test-layer or coverage reasoning.

khangnhoang Bundle

Repository-specific rules for Next.js Server Actions, Route Handlers, FormData, query/route/search params, webhook and upload payloads, Zod validation, React Hook Form contracts, DTOs, inferred types, trust boundaries, and schema/type SSOT. Use before changing actions, handlers, forms, schemas, helpers, or payload types that cross client/server or external-input boundaries.

kohoj Bundle

Transform technical descriptions into interactive animated HTML visualizations starring Mogu — a mushroom character whose cap adapts to each concept. Generates self-contained HTML files with Canvas 2D animations, interactive parameter controls, and a consistent character brand. Use when: "explain how X works", "visualize this concept", "make an interactive demo of", "show me how Y works visually", "mogu", "technical animation", "interactive diagram", "concept visualization", or any request to turn a technical mechanism into an interactive, visual, character-driven explanation. Also use when the user describes a system they want to understand better and would benefit from seeing it animated, even if they don't say "visualize" — e.g., "I don't get how Kafka partitions work", "can you show me load balancing", "explain consensus algorithms".

laojin1900 Bundle

Use when planning, building, migrating, validating, previewing, diagnosing, or releasing a Shopify Online Store 2.0 theme, including Liquid, JSON templates, sections, snippets, theme CSS or JavaScript, Theme Editor preservation, draft-theme writes, stale previews, dynamic DOM enhancements, or multi-page acceptance.

leifermendez Bundle

Enterprise UI/UX auditor for SaaS. Enforces Tailwind, Atomic Design, accessibility. Optimized for small LLMs.

leifermendez Bundle

Auditor de CSS/SCSS para proyectos web. Enforcea mandamientos CSS, metodologías BEM/ITCSS, organización de archivos, performance y accesibilidad. Optimizado para cualquier stack (vanilla, React, Vue, Angular, etc).

leifermendez Bundle

Performance bottleneck detector for any codebase. Scans backend, frontend, database, and connection layers for N+1 queries, blocking I/O, missing indexes, render thrashing, bundle bloat, pool exhaustion, Big-O complexity issues, and over-engineering anti-patterns. Produces a severity-ranked audit report with actionable quick wins.

liberatedpixelcup Skill

Measure lab CLS with profile:cls, debug layout shift from loading shells and first-paint jump, and keep budgets tied to a CI artifact. Use when editing first-paint CSS, loading shells, critical-shell, or when the user mentions CLS, layout shift, or Lighthouse.

liberatedpixelcup Skill

Thread CatalogReader and State through Mithril attrs, never a hidden global. Handle Result/LoadError, seed test catalogs, and keep URL hashes stable. Use when adding or editing a component, a browser spec, or sources/state/ code, or when the user mentions catalog, state, hash, or aliases.

liberatedpixelcup Skill

Run or add Playwright visual specs and know when a layout or CSS change needs npm run test:visual. Use after first-paint, panel-layout, or PurgeCSS safelist changes, or when adding a Playwright case.

logicleap-labs Skill

MANDATORY acceptance gate before declaring ANY visual or UI work "done", "good", "working", or before screenshotting an interface and ending the task. Use whenever you build, redesign, restyle, or fix a user-facing screen in ANY stack — Xcode/SwiftUI/UIKit apps, iOS/macOS, web (Next.js/React/HTML), Electron, Flutter, generated design mockups — and whenever you are asked to "review the screenshot", "check what you built", "is this good", "spot the issues", or "look at this design". Forces a structured, written, adversarial inspection of the ACTUAL rendered pixels (not the code, not your memory of intent) so obvious defects — blank/unlabelled elements, dead empty space, duplicated or garbage content, misalignment, inconsistent spacing, truncation, low contrast, leftover placeholders, broken states, and lag/jank — are caught BEFORE you claim completion. Triggers on "done", "looks good", "finished the UI", "here's the redesign", "screenshot", "ship it".

logicleap-labs Skill

Use before declaring a UI change done, fixed, working, ready, or shipped. Forces a real accessibility pass across keyboard flow, focus visibility, accessible names, contrast, reduced motion, and the platform's native semantics.

trycompai Bundle

Use when an app uses @pierre/diffs to render or edit code files, diffs, patches, merge conflicts, or CodeView review surfaces, including React, vanilla JavaScript, SSR, workers, annotations, selection, and custom Shiki languages or themes.

trycompai Bundle

Build end-to-end type-safe tRPC APIs inside NestJS using the nestjs-trpc adapter — @Router/@Query/@Mutation/@Subscription decorators, TRPCModule.forRoot, injectable middlewares and context, Zod input/output schemas, and the Rust CLI that generates the AppRouter type for clients. Use this skill whenever the user mentions nestjs-trpc, tRPC in a NestJS app, @Router or @Query decorators, TRPCModule, AppRouterHost, "typed API between my Nest backend and frontend", generating AppRouter types, or is migrating a NestJS GraphQL/REST API to tRPC — even if they don't name the library explicitly.

yurake Bundle

Suite of tools for creating elaborate, multi-component Codex CLI HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

azure-samples Skill

Diagnose and fix React render loops caused by unstable effect or callback dependencies

azure-samples Skill

Proper flex truncation for title+badge rows in Tailwind CSS

sahiltolani30 Skill

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

sahiltolani30 Skill

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

sahiltolani30 Skill

Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns

kong Skill

Use for Next.js on Volcano and for web apps, pages, dashboards, boards, galleries, full-stack UIs, public HTTP routes, redirects, webhook ingress, middleware, API routes, server actions, and client or server SDK separation.

kong Skill

Reusable error handling patterns for Volcano SDK apps: centralized error dispatcher with action enum, useApiCall React hook for loading/error/data state, retry with exponential backoff, retry with toast notifications, and cross-domain error message catalog.

danielnoamtuby Skill

Use when a built interface needs a structured visual, interaction, responsive, accessibility, or theme critique against its design brief.

danielnoamtuby Skill

Use when building a frontend interface that needs a deliberate, distinctive visual direction instead of generic styling.

esp1ngard4 Bundle

Maintains a TSP Register - the inventory of every Tool, System and Procedure you rely on - plus the recurring control activities that keep each one alive, and regenerates an HTML dashboard from it. Use whenever the user mentions a "tool register", "tool inventory", "process inventory", "TSP", or asks to add, retire or renumber a tool, record that a tool was reviewed, find which tools are obsolete or overdue for review, run a periodic controls check, or refresh the tool dashboard. Also use when a new tool or automation is created and needs registering.

esp1ngard4 Bundle

Manages a RAID register - Risks, Actions, Issues, Decisions and Ideas - stored as a JSON register, and generates an interactive HTML dashboard with analytics and a risk heat map. Use whenever the user mentions "RAID", "risk register", "issue log", "decision log", or asks to add, edit or close a risk, action, issue or decision, to log an update or progress note against one, or wants a view of project risks and how the project is tracking.

expert-vision-software Bundle

Use ONLY when working in an Aurelia v2 project — branch picks the right pillar skill for scaffold, resolve, assemble, slice, lift, package, or wire questions on Aurelia 2.x MVVM SPAs. Use when starting an Aurelia app, choosing between Aurelia skills, structuring a large SPA, dependency injection, routing, migration from v1, debugging, performance, building a component library, packaging a plugin, wiring first-party plugins (fetch-client, validation, dialog, state, i18n), forms, testing, SSR/prerendering, or AI-assisted Aurelia scaffolding. Front-loads the leading word "branch".

expert-vision-software Bundle

Package a distributable Aurelia v2 plugin — author the register(container) entry point, the .customize() options pattern with DI.createInterface tokens, global resource registration, AppTask lifecycle hooks, and the rendering-pipeline extensions (IRenderer, IRendering, registerHostNode). Use when creating a plugin from scratch, turning a component library, feature slice, or shared directory into a standalone npm package, wiring peerDependencies and dual ESM/CJS builds, or shipping templates/styles with explicit ?raw imports. Leading word — package.

expert-vision-software Bundle

Use when wiring an Aurelia v2 component — resolves dependency injection, routing, navigation, AppTasks, custom events, and cross-feature orchestration. Use when injecting services, configuring `@route`, navigating programmatically, sharing state between features, declaring AppTasks, or paginating components. Leading word — resolve.

expert-vision-software Bundle

Wire first-party Aurelia v2 plugins and ecosystem concerns into an app — picks the right reference for HTTP/fetch-client, validation, dialog, state, i18n, forms, testing, and SSR/prerendering. Use when adding @aurelia/fetch-client, @aurelia/validation, @aurelia/dialog, @aurelia/state, or @aurelia/i18n; writing Vitest + @aurelia/testing component tests; binding forms with model.bind/matcher.bind; or configuring server-side rendering, prerendering, hydration, sitemap/robots, and client takeover. Leading word — wire.

expert-vision-software Bundle

Scaffold an Aurelia v2 project from zero. Picks the right foundation step — philosophy, hello-world quickstart, component naming, lifecycle hooks, or AI-assisted scaffolding. Use when starting an Aurelia 2 app, asking "what is Aurelia", creating a custom element, wiring binding/attached/unbinding, or generating the first main.ts and pair.

neuralmedic-de Bundle

Audit and fix web accessibility to WCAG 2.2 AA, gated by automated checks that actually run — axe-core via Playwright for violations, scripted keyboard/focus and reflow audits, plus a mandatory manual + screen-reader checklist. Use when the user wants to make a site/app/page accessible, fix a11y or WCAG/ADA/Section 508 issues, add an accessibility CI gate, run an axe/Lighthouse-style audit, check keyboard navigation, color contrast, ARIA, screen-reader support, or remediate accessibility violations. Triggers: "accessibility", "a11y", "WCAG", "ADA compliance", "screen reader", "keyboard navigation", "axe audit".

neuralmedic-de Bundle

Convert a Webflow page or site into a pixel-perfect React implementation (Vite or Next.js) with Playwright visual-regression testing as the correctness gate. Use when the user wants to migrate, port, rebuild, clone, or recreate a Webflow design 1:1 in React, move off Webflow, or set up screenshot/visual-diff testing of a rebuilt page against the original. Triggers: "convert Webflow to React", "rebuild this Webflow site in Next.js", "pixel-perfect clone", "visual regression vs the original".