Desenvolvimento

Padrões de correção do Novo Sistema de Input da Unity. Identifica erros comuns na leitura de ações (triggered vs IsPressed vs WasPressedThisFrame), troca de mapas de ação, persistência de remapeamento, tempo de vida de InputValue, PassThrough vs Value, atribuição de dispositivos em multiplayer local e troca automática de esquemas de controle. Formato do PADRÃO: QUANDO/ERRADO/CERTO/PEGADINHA. Baseado no Unity 6.3 LTS.

Controle o estado da aplicação Unity Editor, permitindo iniciar, parar ou pausar o 'playmode'. Use a ferramenta 'editor-application-get-state' para verificar o estado atual antes.

Use when you want higher accuracy by generating multiple reasoning chains and selecting the best answer — trading speed for quality on critical outputs. Common scenarios - high-stakes decisions where you want multiple reasoning paths compared, classification tasks where one chain of thought is not reliable enough, improving accuracy by generating several answers and selecting the best-reasoned one

Make your AI give the same answer every time. Use when AI gives different answers to the same question, outputs are unpredictable, responses vary between runs, you need deterministic AI behavior, or your AI is unreliable. Also used for same input gives different output every time, prompt sensitivity causes output changes with minor wording tweaks, reordering examples shifts accuracy dramatically,

LLM observability for DSPy with Langfuse -- auto-trace every LM call, attach scores and evaluations, run annotation queues for human review, and track experiments across prompt versions. Use when you want to set up Langfuse, langfuse.com, openinference-instrumentation-dspy, trace DSPy calls, LLM observability with scores, annotation queues, or experiment tracking. Also used for langfuse setup, pip

Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Also use when your prompt broke after a model update, prompts that work for GPT-4 do not work for Clau

Use when you want few-shot demos that are dynamically selected per input based on similarity — better than fixed demos when inputs vary widely. Common scenarios - inputs vary widely and fixed examples do not cover enough cases, dynamically selecting the most relevant demos per input, building a retrieval-augmented prompt with similar examples, or when static few-shot examples work for some inputs

Use when you want conservative, incremental optimization — making small targeted improvements rather than large changes, useful for already-working programs that need fine-tuning. Common scenarios - your program already works well and you want to improve it without breaking what works, conservative optimization that preserves existing quality, fine-tuning a production program incrementally, or whe

Desenvolve, refatora ou audita código Rust, abordando ownership, borrowing, lifetimes, tratamento de erros e padrões de design modernos. Esta skill é útil para escrever programas Rust, revisões de código, otimização de performance ou discussão de arquitetura de sistemas Rust, mesmo sem menção explícita de "Rust" se houver arquivos .rs ou Cargo.

Cria um módulo de recurso completo com estrutura de pastas, Assembly Definition (.asmdef), assembly de teste e namespace. Utilize ao adicionar uma nova funcionalidade, sistema ou módulo a um projeto Unity.

Use when encountering Swift 6 concurrency errors, Sendable conformance warnings, actor isolation issues, "global variable is not concurrency-safe" errors, or migrating codebases to Swift 6 language mode

Crie um título e uma descrição preliminar de PR após a conclusão de alterações substanciais no código. Acione ao finalizar uma mudança moderada ou maior (código, testes, configuração de build, docs com impacto) e precisar do bloco de resumo pronto para PR, com o sumário da mudança e o texto preliminar.