Desenvolvimento

Use when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math, or complex classification where direct prediction fails. Common scenarios - classification tasks where the model needs to reason about edge cases, math word problems, multi-step analysis, complex question answering, legal or medical reasoning, any task where thinking before answeri

Gera um plano de teste de QA para um sprint ou funcionalidade. Lê GDDs e histórias para classificar testes (Lógica/Integração/Visual/UI), produzindo um plano estruturado com testes automatizados, manuais, escopo de smoke test e requisitos de playtest, ideal para antes do sprint ou de uma nova funcionalidade.

Summarize what nyann currently sees in this repo: stack detection, active profile, branching strategy, hook status, CLAUDE.md, and recent commits. TRIGGER when the user says "what does nyann think is set up here", "show nyann state", "explain the setup", "what's the current config", "what's the active profile", "describe this repo's nyann setup", "what's wired up", "show me the repo state", "/nyan

Orquestra a equipe de combate, coordenando designers de jogo, programadores de gameplay, programadores de IA, artistas técnicos, designers de som e testadores de QA para projetar, implementar e validar funcionalidades de combate de ponta a ponta.

Use when you need to give DSPy agents tool-calling abilities — wrapping Python functions as tools, building tool-using pipelines, or setting up code execution environments. Common scenarios - wrapping a Python function as a tool for DSPy agents, building tool-using pipelines, setting up a calculator or search tool, giving agents access to databases or APIs, or configuring code execution environmen

Use vLLM for high-throughput production serving of self-hosted models with DSPy. Use when you want production LLM serving, tensor parallelism, multi-GPU inference, batch processing, or high-concurrency self-hosted models. Also used for vllm, vLLM, production serving, high throughput LLM, tensor parallelism, self-hosted production, PagedAttention, local production server, GPU serving, batch inferen

Estruture um agente de IA Solana usando o Agent Kit v2 da SendAI e o MCP do Desenvolvedor Solana.

Reverse a bootstrap or retrofit run by walking its BootRecord manifest: restore pre-state files, drop branches that were created, surface anything that couldn't be safely undone. TRIGGER when the user says "undo the bootstrap", "undo nyann setup", "revert nyann setup", "uninstall nyann from this repo", "back out the bootstrap", "undo the retrofit", "I regret running bootstrap", "rip out nyann", "/

Analisa a pilha de tecnologia de um projeto e gera arquivos de configuração abrangentes do Claude Code (diretório .claude/ com CLAUDE.md, skills, agents, rules e commands). Use ao configurar o Claude Code para um repositório novo ou existente.

Esta skill gera testes NUnit EditMode e PlayMode a partir de cenários Gherkin GDD. Utilize-a para escrever testes, validar funcionalidades, garantir a qualidade do código ou verificar o comportamento após alterações.

Padrões do Behavior Designer para árvores de comportamento de IA, incluindo criação de tarefas, variáveis compartilhadas, condicionais e depuração.

First-run onboarding for nyann. Creates the user config directory, collects preferences through AskUserQuestion interactive pickers, and writes ~/.claude/nyann/preferences.json. TRIGGER when the user says "set up nyann", "configure nyann", "nyann setup", "onboard me", "first time using nyann", "initialize nyann", "nyann first run", "get nyann ready", "/nyann:setup". ALSO trigger when: the user run