formacao_ia

Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific cy- skills instead.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Leia o relatório de bugs de uma feature, analise e corrija cada defeito na causa raiz, crie testes de regressão, valide bugs visuais com Playwright MCP e gere o relatório final de correções. Use sempre que o usuário pedir para corrigir bugs, executar bugfix, tratar defeitos do bugs.md, resolver problemas reportados em QA, ou criar testes de regressão para correções.

Valide a implementação de uma feature contra o PRD, TechSpec e Tasks, executando testes de unidade, integração e E2E com Playwright MCP, verificando acessibilidade e responsividade, e gerando um relatório final de QA. Use sempre que o usuário pedir para executar QA, validar/testar uma funcionalidade, rodar testes E2E, verificar acessibilidade, levantar evidências de funcionamento ou gerar um relatório de QA.

Analise o código produzido, verifique conformidade com as rules e padrões do projeto, valide se os testes passam, confirme aderência à TechSpec e às Tasks, identifique code smells e gere o relatório final de code review. Use sempre que o usuário pedir para executar code review, revisar o código de uma feature, validar conformidade com padrões/rules, conferir se a implementação segue a TechSpec, ou gerar um relatório de code review.

Identifique e implemente a próxima task técnica de uma feature a partir do PRD, TechSpec e tasks.md. Use sempre que o usuário pedir para executar, implementar ou começar uma task/subtarefa, dar continuidade à implementação de uma funcionalidade, ou seguir a lista de tarefas em tasks.md.

Defines testing standards for the example_6_cursor full-stack project using Vitest and Playwright. Use when implementing features, fixing bugs, changing behavior, writing unit, integration, or E2E tests, or when the user asks about test coverage, AAA structure, stubbing dependencies, or Playwright.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Applies code standards for the example_6_cursor full-stack project (Express + TypeScript backend, React + TypeScript frontend). Use when writing or reviewing code in backend/ and frontend/, implementing features, refactoring, or when the user asks about coding conventions, naming, function size, or project structure.

Crie um PRD para um novo produto ou serviço. O PRD deve seguir um formato padrão e ser detalhado o suficiente para que o desenvolvedor possa implementar o produto ou serviço.

Usando um PRD e um TechSpec, crie uma lista de tasks para a implementação da feature. Você deve seguir o padrão de templates fornecido e o workflow listado abaixo.

Crie um TechSpec para um novo produto ou serviço. O TechSpec deve seguir um formato padrão e ser detalhado o suficiente para que o desenvolvedor possa implementar o produto ou serviço.

Finaliza implementações com commit conventional, screenshots Playwright, checklist de qualidade e abertura de pull request via gh CLI usando o template da empresa. Use quando o usuário pedir para finalizar, commitar, abrir PR, capturar screenshots, encerrar implementação, ou mencionar "finalize", "commit final", "pull request", "gh" ou "conventional commits".

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Applies React standards for the example_6_cursor frontend (React + TypeScript + Vite). Use when writing or reviewing components, pages, and hooks in frontend/, implementing UI features, or when the user asks about React conventions, props, hooks, or useMemo patterns.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.