Web & Frontend

smirnovalex-qa Skill

Cross-browser and responsive compatibility check of a web interface — scope from a feature/screen/directory/branch, a requirements document, or a tracker issue; checking against a browser/device matrix and breakpoints (mobile/tablet/desktop) with a mandatory live run in the browser via emulation of different viewports and user-agents, analysis of support for the CSS features and JS APIs used (caniuse logic), touch vs mouse, native controls, dark theme, and zoom. Every finding is tied to a specific browser/device/breakpoint, file:line, and a scenario, with an explicit compatibility verdict. Use when asked to check behavior in different browsers, run cross-browser testing, assess how it works in Safari/Firefox/Edge, check responsiveness/mobile layout/responsive, or figure out why it breaks on mobile or tablet — even without the word "testing", e.g. "will this work in safari", "won't the layout fall apart on a phone", "is this CSS supported everywhere", "is it fine on a tablet", "why doesn't the button tap on iO

smirnovalex-qa Skill

Аудит доступности (a11y) веб-интерфейса по WCAG 2.1/2.2 (уровни A и AA) — периметр из фичи/экрана/директории/ветки, документа-требований или issue в трекере; проверка по принципам POUR (Perceivable/Operable/Understandable/Robust) с обязательным ЖИВЫМ прогоном в браузере (клавиатура, фокус, aria, контраст, скринридер), а не только чтением кода. Каждая находка привязана к WCAG success criterion, затронутой группе пользователей, file:line и конкретному сценарию, с явным вердиктом соответствия. Используй когда просят проверить доступность страницы/компонента, сделать a11y аудит, оценить соответствие WCAG, проверить доступность для скринридеров или с клавиатуры, разобраться с контрастом/фокусом/aria/семантикой/alt-текстами/landmarks/модалками — даже без слова "аудит", например "доступно ли это для незрячих", "работает ли это без мыши", "почему скринридер не читает эту кнопку", "проходит ли это по WCAG AA", "нормальный ли тут контраст". Скилл только анализирует и сохраняет отчёт-файл, код проекта не меняет.

smirnovalex-qa Skill

Полный аудит безопасности ВСЕГО репозитория the-platform (все backend-сервисы, the-frontend, встраиваемые виджеты/расширения, общие библиотеки libs/*, инфраструктурные конфиги helm/k8s/docker) — три независимых среза (автоматизированное сканирование SCA/SAST/secret-scan/IaC, построчный код-ревью по зонам, архитектурный обзор), детальный чек-лист по 14 категориям (auth/authz, мультитенантность, websocket, internal API, инъекции, SSRF, XSS, секреты/PII, файлы, зависимости, docker, k8s/helm, обработка ошибок, CI/CD), находки с file:line и сценарием эксплуатации, и итоговым отчётом для руководства. Используй когда просят провести полный аудит безопасности всей кодовой базы/репозитория/платформы целиком, найти уязвимости по всему проекту, перепроверить статус находок из предыдущего security-аудита, или оценить общую готовность платформы к обработке персональных данных клиентов с точки зрения безопасности — даже если пользователь не произносит слово "аудит" буквально, а говорит "давай проверим весь проект на дыры в

smirnovalex-qa Skill

Full performance and resource-cost audit of the entire the-platform repository (FastAPI/asyncpg/PostgreSQL/Redis/RabbitMQ backend services, the-frontend, shared libraries libs/*, Docker/Kubernetes/Helm infrastructure, k6 load testing in load-testing/) — three independent passes (instrumental profiling, line-by-line code review, architectural review), findings only with measurement (EXPLAIN ANALYZE, py-spy, bundle size, k6 runs), severity, file:line, and a final verdict. Use when asked to run a performance/resource-cost audit of the whole codebase or infrastructure, to check CPU/RAM/network-traffic/infrastructure-cost consumption, to find bottlenecks across the whole repository, to assess the economy of the architecture as load grows, or to re-verify the status of findings from a previous audit/load-testing reports — even if the user doesn't say the word "audit" literally, but says "why does the service eat so much CPU/memory", "let's look at the performance of the whole project", etc.

smirnovalex-qa Skill

Проверка кросс-браузерной и адаптивной (responsive) совместимости веб-интерфейса — периметр из фичи/экрана/директории/ветки, документа-требований или issue в трекере; проверка по матрице браузеров/устройств и брейкпоинтам (mobile/tablet/desktop) с обязательным живым прогоном в браузере через эмуляцию разных вьюпортов и user-agent, анализ поддержки используемых CSS-фич и JS-API (caniuse-логика), touch vs mouse, нативных контролов, тёмной темы и зума. Каждая находка привязана к конкретному браузеру/устройству/брейкпоинту, file:line и сценарию, с явным вердиктом совместимости. Используй когда просят проверить работу в разных браузерах, провести кросс-браузерное тестирование, оценить работу в Safari/Firefox/Edge, проверить адаптивность/мобильную вёрстку/responsive, разобраться почему ломается на мобильном или планшете — даже без слова "тестирование", например "заработает ли это в сафари", "не поедет ли вёрстка на телефоне", "поддерживается ли этот CSS везде", "нормально ли на планшете", "почему на iOS кнопка не н

smirnovalex-qa Skill

Полный аудит производительности и ресурсоёмкости всего репозитория the-platform (backend-сервисы FastAPI/asyncpg/PostgreSQL/Redis/RabbitMQ, the-frontend, общие библиотеки libs/*, Docker/Kubernetes/Helm инфраструктура, нагрузочное тестирование k6 в load-testing/) — три независимых среза (инструментальное профилирование, построчный код-ревью, архитектурный обзор), находки только с измерением (EXPLAIN ANALYZE, py-spy, размер бандла, k6-прогоны), severity, file:line и итоговым вердиктом. Используй когда просят провести аудит производительности/ресурсоёмкости всей кодовой базы или инфраструктуры целиком, проверить расход CPU/RAM/сетевого трафика/стоимости инфраструктуры, найти узкие места по всему репозиторию, оценить экономичность архитектуры при росте нагрузки, или повторно перепроверить статус находок из предыдущего аудита/load-testing отчётов — даже если пользователь не произносит слово "аудит" буквально, а говорит "почему сервис жрёт столько CPU/памяти", "давай посмотрим на производительность всего проекта" и

lhh666-6 Bundle

any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report

lhh666-6 Bundle

Use when you need to generate a Reveal.js HTML presentation from Markdown.

h4vzz Skill

Create text-based wireframes at low, mid, and high fidelity with component inventories, interaction annotations, and responsive breakpoint specifications.

h4vzz Skill

Audit web interfaces against WCAG 2.1 AA/AAA standards, identify violations, and produce actionable remediation reports with code fixes.

ske-labs Skill

Plan scheduled macro-event risk from official calendars and point-in-time expectations. Use for FOMC, employment, inflation, GDP, or other releases requiring standardized surprise, component, revision, scenario, and execution analysis.

autonomous-ai Bundle

Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.

odjaramillo Skill

Next.js 14+ patterns with App Router, Server Components, and SSR. Trigger: When building Next.js applications with SSR/SSG.

odjaramillo Bundle

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

odjaramillo Bundle

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.

odjaramillo Skill

Expert integration of Supabase Auth with Next.js App Router Use when: supabase auth next, authentication next.js, login supabase, auth middleware, protected route.

odjaramillo Bundle

Suite of tools for creating elaborate, multi-component claude.ai 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.

odjaramillo Skill

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

buildpad-ai Bundle

Add internationalization to a Buildpad app the way the Next.js App Router guide prescribes — locale-prefixed routes (app/[lang]), Accept-Language negotiation inside the existing auth middleware, server-loaded dictionaries handed to client pages through an I18nProvider, a LanguageSwitcher built on SelectDropdown, DaaS field-label translations via VForm's locale prop, and Directus-style content translations (a languages collection plus <collection>_translations junctions with optional per-locale workflow). Use when the user says add i18n, internationalization, internationalisation, localization, translations, multilingual, multi-language, bilingual, locale, language switcher, RTL, or wants content or UI in more than one language.

buildpad-ai Skill

Perform a comprehensive code review checking for quality, security, performance, accessibility, and DaaS/Buildpad compliance. Generates actionable feedback with severity levels. Use when the user says review-code, review this, check code quality, or wants a PR review.

buildpad-ai Bundle

Split an app into a Main App plus domain-focused micro-apps that share one DaaS backend. Covers domain boundaries, collection ownership, shared RBAC, cross-domain contracts, and repo bootstrap. Load this skill FIRST to decide the split, then load add-microfrontend-zones (Multi-Zones, the default for Next.js micro-apps) or add-microfrontend (iframe composition and the auth bridge) to wire the composition. Use when the user says add-microapp, microapp, service boundary, or needs to split a large app into domain-focused micro-apps.

buildpad-ai Bundle

Core DaaS (Data-as-a-Service) platform knowledge including two-tier architecture, DaaS-compatible REST API, Supabase integration, Next.js App Router patterns, MCP tool usage, and environment configuration. Automatically loaded as background context for all DaaS development tasks.

buildpad-ai Bundle

Generate or update documentation for DaaS application code changes including API references, component docs, hook docs, schema files, and changelogs. Use when the user says generate-docs, update docs, document this, or needs documentation.

buildpad-ai Bundle

Initialize a new DaaS (Data-as-a-Service) application with Next.js, Supabase, and Buildpad UI. Creates the project foundation including scaffolding, authentication proxy, and test infrastructure, ready for spec-driven feature development. Use when the user wants to start a new project, create a new app, or bootstrap a DaaS application.

buildpad-ai Bundle

Generate a server-side Next.js API route for Supabase auth (login, logout, callback, session). These routes manage Supabase SSR cookies and run server-side. Do NOT use this skill to create proxy routes for DaaS data — the UI calls DaaS directly using Authorization Bearer tokens instead. Use when the user needs a new auth endpoint or server-side Supabase route.

buildpad-ai Skill

Generate a React component following DaaS platform patterns. Performs mandatory Buildpad-first check before creating any custom component. Use when the user needs a new React component, page section, or UI element for a DaaS application.

buildpad-ai Bundle

DaaS runtime extensions (hooks) and utilities API reference. Covers filter hooks (validation, transformation before save), action hooks (audit logging, notifications after save), and utility endpoints. Use DaaS extensions instead of implementing backend logic in Next.js API routes. Automatically loaded as background context.

buildpad-ai Skill

Offload long-running work from a Next.js/Amplify app to a Buildpad runtime worker over RabbitMQ, and chain job → worker → worker. Covers the standard topic-exchange convention (a single `jobs` exchange, routing key = job type, a message envelope, dead-lettering), the producer side (publish a job, fire-and-forget) and the consumer side (a worker that consumes and may hand off to another worker), and how to fetch the live RabbitMQ connection from the Buildpad Platform MCP (`get_project_detail` → `messaging`). Use when a request is too slow for request/response, needs background processing, or when one worker must pass work to another. Because the producer (Next.js repo) and the consumer (Node.js worker repo) are SEPARATE repositories worked on by separate agents, this skill also generates a cross-repo handoff doc that carries the topic/routing key, the payload schema and how to read it, the user's intent, and everything the other repo's agent needs to implement the matching side.

buildpad-ai Bundle

Compose independent Next.js micro-apps into one Main App with sandboxed iframes and a postMessage bridge. Covers the host component, the message contract, auth token bridging, URL and scope syncing, sandbox flags, and CSP. Load add-microapp first to decide domain boundaries and bootstrap the repos, then load this skill to wire the composition. Use when the user says add-microfrontend, micro-frontend, iframe composition, or needs to embed an independent app in another app.

buildpad-ai Bundle

Add external OAuth/OIDC identity provider integration where Next.js acts as the OAuth client. Creates OAuth proxy flow with PKCE, user provisioning via Supabase Admin API with default DaaS role assignment, and session management. Required for self-hosted Supabase without deployment access.

buildpad-ai Bundle

Buildpad UI component catalog and Buildpad-First rule reference. Lists all 40+ available components, hooks, services, and types. Enforces that raw Mantine form/input components must not be used when Buildpad provides equivalents. Automatically loaded as background context.

buildpad-ai Bundle

Grant application-level capability flags to users via DaaS Module-Level Access Keys. Keys such as `workflow:approve` or `system:logs` are registered in `daas_module_access_keys`, toggled on policies, and checked in React with `usePermissions().hasModuleAccess(key)` or in API routes with the OR-merge logic already built into the platform. Use when an application needs to gate a feature, page, or workflow command that is not tied to a collection CRUD operation.

buildpad-ai Bundle

Authentication proxy pattern reference. All browser-to-backend communication MUST go through Next.js API proxy routes. Never call Supabase auth or DaaS backend directly from client components. Automatically loaded as background context.

paulingram Skill

CT6's multi-agent wrapper around the external cartographer plugin call. One cartographer run produces CODEBASE_MAP.md; 3× codebase-map-reviewer agents independently audit the result and confirm 100% coverage in parallel; targeted re-mapping iterates until all 3 reviewers return ok. Wrapped in a ralph-loop with completion-promise "CODEBASE MAP COMPLETE". Caller-configurable output path so frontend-read-only mode (Phase 0b) can route output to .architect-team/frontend-reference/<codebase-slug>/ instead of <codebase>/docs/. v3.4.0.

paulingram Skill

A 3-researcher domain analysis skill with MANDATORY outside research. Reads provided inputs (a frontend codebase, documentation, or both — any combination is valid), extracts personas + objectives, and AUGMENTS with industry / market / competitor research that every researcher performs independently regardless of input completeness. Round-robin convergence + master-synthesizer produces the final map. Caller-configurable output path so the skill is reusable from intake-and-mapping (INTEGRATION_MAP.md output), visual-to-api-design Stages 1+2 (PERSONA_MAP.md output), the new Phase 0b backend dispatch (PERSONA_MAP.md output to .architect-team/frontend-reference/ when frontend_read_only). v3.4.0.

paulingram Skill

Use when authoring or running Playwright tests for any feature with a frontend component, especially during Phase 5 integration. Mandates a workflow that first establishes who the users are and what they are trying to achieve (escalating to the user via structured questions when intent cannot be derived from product docs/requirements), then exhaustively enumerates every link, button, form input, modal trigger, keyboard shortcut, drag target, and conditional render gate plus the API contracts each touches, then authors tests organized around user journeys (page.goto / click / fill / waitFor) that assert visible state. Rejects endpoint-only testing as a substitute for user-flow testing. Coverage verification proves every user objective, every interactive element, and every error response is exercised.