Web & Frontend

fluxonlab Skill

Use when you need to review dashboards, admin tools, density, scanning, filtering, and operational workflows.

fluxonlab Skill

Use when designing stable APIs, module boundaries, type contracts, public interfaces, REST or GraphQL endpoints, or frontend/backend contracts.

fluxonlab Skill

Master Next.js 14+ App Router with Server Components, streaming, parallel routes, and advanced data fetching. Use when building Next.js applications, implementing SSR/SSG, or optimizing React Server Components.

fluxonlab Skill

Use when adding, customising, or reviewing shadcn/ui components in a Next.js or React project — covering CLI installation, CSS variable theming, dark mode, react-hook-form + Zod form patterns, and Radix UI accessibility compliance.

fluxonlab Skill

Use when you need to audit mobile, tablet, desktop, overflow, container sizing, and text fit.

fluxonlab Skill

Use when you need to audit multi-language locale parity across TR/EN/DE locale files, detect missing translation keys, find hardcoded UI strings that bypass i18n, and validate next-intl App Router routing. This skill supports the "UI Language and Theme Parity" project behaviour rule.

fluxonlab Bundle

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

fluxonlab Skill

Use when you need to review a Next.js App Router codebase for React Server Component correctness, "use client"/"use server" boundary violations, server secret leakage into the client bundle, Server Action input validation, fetch cache strategy, and metadata/streaming patterns.

fluxonlab Bundle

Provides exact patterns for diagnosing and fixing automatic batching regressions in React 18 class components. Use this skill whenever a class component has multiple setState calls in an async method, inside setTimeout, inside a Promise .then() or .catch(), or in a native event handler. Use it before writing any flushSync call - the decision tree here prevents unnecessary flushSync overuse. Also use this skill when fixing test failures caused by intermediate state assertions that break after React 18 upgrade.

fluxonlab Skill

Use when designing or reviewing engine-agnostic web game architecture — covering the fixed-timestep game loop, Entity-Component-System (ECS) pattern, state machine, asset loading pipeline, and save/load via localStorage or IndexedDB.

fluxonlab Skill

Use when building 3D scenes in the browser with Three.js or React Three Fiber — covering Scene/Camera/Renderer setup, the render loop, GLTF loading, lighting, raycasting, and GPU-friendly instancing and frustum culling.

fluxonlab Skill

Use when you need to set and enforce frontend performance budgets — Core Web Vitals beyond the basics (LCP, INP, CLS attribution), JavaScript and asset size budgets, lazy loading, hydration cost, and Lighthouse CI gates in a pipeline.

fluxonlab Skill

Use when you need to review landing pages, first viewport signal, offer clarity, trust, and conversion friction.

fluxonlab Skill

Validates a UX spec, HUD design, or interaction pattern library for completeness, accessibility compliance, GDD alignment, and implementation readiness. Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict with specific gaps.

davidcastagnetoa Bundle

Desarrollo de aplicaciones móviles con Expo SDK, Expo Router (navegación file-based) y NativeWind (Tailwind CSS en React Native) para producción. Usar PROACTIVAMENTE cuando se trabaje con pantallas, navegación, layouts, deep links, notificaciones push en Expo, estilos con NativeWind/Tailwind en RN, o cualquier tarea del frontend móvil del proyecto. Activar siempre que aparezcan las palabras clave: Expo, expo-router, NativeWind, Expo Router, Stack, Tabs, app/(tabs), _layout.tsx, useRouter, useLocalSearchParams, usePathname, expo-notifications, deep link, notificaciones push Expo, tailwind en React Native, className en RN, useSafeAreaInsets, SplashScreen, o cualquier pantalla de la app móvil HADA.

davidcastagnetoa Bundle

Integración completa de Firebase Cloud Messaging (FCM) en backend NestJS y frontend Expo React Native. Usar PROACTIVAMENTE cuando se trabaje con notificaciones push, registro de tokens de dispositivo, envío de mensajes desde el servidor, manejo de tokens expirados o inválidos, notificaciones en foreground/background, deep links desde notificaciones, o configuración de credenciales FCM. Activar siempre que aparezcan las palabras clave: FCM, Firebase Cloud Messaging, push notification, getDevicePushTokenAsync, firebase-admin, sendEachForMulticast, fcmTokens, google-services.json, GoogleService-Info.plist, expo-notifications, notificación de cumpleaños, recordatorio push, o token de dispositivo.

wgpsec Bundle

JavaScript 静态分析提取隐藏 API 端点。当目标是 SPA/前后端分离架构、页面使用 Vue/React/Angular、或常规目录扫描收效甚微时使用。通过分析 JS bundle 提取 API 路径、密钥、内部域名、WebSocket 端点。是 API 渗透的信息收集阶段。发现端点后 → api-fuzz 进行语义化 fuzz

wgpsec Skill

思维链 (Chain-of-Thought) 注入攻击方法论。当目标系统使用 ReAct/CoT 框架进行多步推理、 Agent 依赖中间推理结果做决策、或需要测试思维链完整性时触发。 覆盖: 思维链干扰注入(伪造中间 Agent 结果)、思维链操纵注入(跳过验证步骤直接调度敏感操作)、 查询注入(在数据查询 Agent 中注入恶意查询语句)。

wgpsec Bundle

CTF/靶场 Flag 强制验证流程。当通过**任何方式**发现疑似 flag 字符串（含 flag{、FLAG{、ctf{ 等格式）时**必须立即**使用此 skill 验证，不要直接提交。防止因字符截断、编码错误、HTML 实体、base64 不完整解码、hex 截断等原因导致提交错误 flag。即使 flag 看起来完整，也可能存在隐藏字符或编码问题。覆盖 SQL 注入分段提取、命令执行输出截断、文件读取编码、Web 页面解析等所有 flag 提取场景。任何时候看到 flag{ 字样都应触发此 skill

pavel-kravchenko Skill

TF-IDF normalize scATAC-seq peak matrices and run LSI/SVD, dropping depth-correlated component 1, via SnapATAC2 or Signac/Seurat. Use when clustering 10x fragments.tsv.gz, running LSI/UMAP on ATAC data, or linking peaks to genes.

pavel-kravchenko Skill

Choose Borzoi (RNA-seq coverage, 32bp) vs Epiformer (sequence+PhyloP, chromatin accessibility) vs AlphaGenome for epigenomic prediction. Use when picking a model for RNA-seq, ATAC/DNase, or variant-effect scoring.

zakirkun Bundle

Detects HTML injection that, even without script execution, can exfiltrate page content via dangling attributes and tags.

zakirkun Bundle

Detects the use of dangerous API methods in modern frontend frameworks (React, Vue, Angular) that can lead to Cross-Site Scripting (XSS).

zakirkun Bundle

Detects Server-Timing headers that expose internal component names and timing data to clients.

zakirkun Bundle

Detects user-controlled input reflected in HTML without proper encoding, enabling HTML injection that may not execute scripts but can redirect or spoof content.

zakirkun Bundle

Detects CSS-based browser history sniffing patterns and sensitive data in browser history.

zakirkun Bundle

Detects iOS Keychain items stored with insecure accessibility attributes that allow access when device is locked or without user authentication.

marktantongco Skill

Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.

marktantongco Skill

Chat UI building blocks for React/Next.js from ui.inference.sh. Components: container, messages, input, typing indicators, avatars. Capabilities: chat interfaces, message lists, input handling, streaming. Use for: building custom chat UIs, messaging interfaces, AI assistants. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks

marktantongco Skill

Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop

marktantongco Skill

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

marktantongco Skill

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

marktantongco Skill

Declarative UI widgets from JSON for React/Next.js from ui.inference.sh. Render rich interactive UIs from structured agent responses. Capabilities: forms, buttons, cards, layouts, inputs, selects, checkboxes. Use for: agent-generated UIs, dynamic forms, data display, interactive cards. Triggers: widgets, declarative ui, json ui, widget renderer, agent widgets, dynamic ui, form widgets, card widgets, shadcn widgets, structured output ui

marktantongco Skill

Meta-skill activating frontend-design, supabase, and deployment-manager

marktantongco Skill

Automates detection and prioritization of audit-related issues across the workspace. Scans for performance, accessibility, and monitoring signals. Use when analyzing audit errors or requesting actionable improvement patches.

marktantongco Skill

ElevenLabs text-to-speech with 22+ premium voices, multilingual support, and voice tuning via inference.sh CLI. Models: eleven_multilingual_v2 (highest quality), eleven_turbo_v2_5 (low latency), eleven_flash_v2_5 (ultra-fast). Capabilities: text-to-speech, voice selection, stability/style control, 32 languages. Use for: voiceovers, audiobooks, video narration, podcasts, accessibility, IVR. Triggers: elevenlabs, eleven labs, elevenlabs tts, premium tts, professional voice, ai voice, high quality tts, multilingual tts, eleven labs voice, voice generation, natural speech, realistic voice, voice over, speech synthesis