Design e Frontend

Review Jules (Google AI agent) pull requests using AI council. Supports -quick flag for lightweight reviews via parallel triage.

Review changed code for reuse, quality, and efficiency, then fix any issues found.

Generates a complete, shoot-specific packing and equipment checklist organized by category, crew role, and travel constraints.

Generate speech, podcasts, voiceovers, and multi-speaker dialogue with Google AI Studio's Gemini Flash TTS by driving the live web app in Chrome via the claude-in-chrome MCP server. Use whenever the user asks to (1) create a podcast, audiobook chapter, narration, audio drama, or voiceover with Gemini / Google AI Studio TTS; (2) turn a script into multi-speaker audio (e.g. "two-host podcast", "Spea

Error handling patterns across languages and layers — operational vs programmer errors, retry strategies, circuit breakers, error boundaries, HTTP responses, graceful degradation, and structured logging. Use when designing error strategies, building resilient APIs, or reviewing error management.

Produces a structured checklist of verification steps and questions a journalist should work through to confirm that a source's claimed professional credentials are genuine before quoting them.

Search for how other games solve a specific design problem — game loops, mechanics, systems, progression, economy. Returns a comparison of 2-4 reference games with what to borrow. Use when designing a new feature, exploring game mechanics, or looking for design inspiration before writing a design doc.

Transforma relatórios de ajuste multiview em uma fila de reparo sequencial ou paralela para alinhar produtos Blender a templates de referência. Utilize após a validação mostrar desalinhamento, quando o agente deve corrigir iterativamente incompatibilidades de wireframe, textura, iluminação ou projeção, e quando lacunas de habilidade devem acionar o autoaperfeiçoamento antes de outra reconstrução.

Um ciclo de autoaperfeiçoamento é executado quando um resultado do Blender é insatisfatório, expectativas do usuário não são atendidas, validação falha ou problemas recorrentes indicam falta de profundidade na skill. Este ciclo diagnostica a falha, decide entre reparar o artefato ou aprimorar uma skill genérica, prepara lições para publicação, atualiza documentação, valida e prepara para implantação quando solicitado.

Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html

Use when managing the pynchy service on the server — deploying changes, observing logs, checking service status, restarting the service, setting up GitHub auth, rebuilding the agent container, or running any commands on pynchy-server via SSH. Also use when interacting with the LiteLLM proxy — investigating failed requests, model routing errors, spend tracking, health checks, API gateway diagnostic