Explorar skills

Integração inicial: pergunta onde você está e o guia para o fluxo de trabalho correto, sem fazer suposições.

Habilidade especialista central para desenvolvimento em Python 3.10+. Foca em recursos modernos do Python como Structural Pattern Matching, Union Types, Async Task Groups, qualidade de código e design arquitetural.

Use Language Server Protocol operations directly for precise cross-file navigation. Find all references to a symbol, go to definition, get hover documentation, and rename symbols across the codebase. Only available when a language server is configured for the project language.

Orquestrar a equipe de design de níveis, composta por designers de níveis, diretores narrativos, construtores de mundo, diretores de arte, designers de sistemas e testadores de QA, para a criação completa de áreas e níveis.

Valida a completude e consistência da arquitetura do projeto em relação aos GDDs. Constrói uma matriz de rastreabilidade mapeando requisitos técnicos a ADRs, identifica lacunas, detecta conflitos e verifica a compatibilidade do motor, emitindo um veredito PASS/CONCERNS/FAIL. É o equivalente arquitetônico de /design-review.

Cut a new release: group Conventional Commits since the last tag, append a CHANGELOG section, create a release commit, and add an annotated git tag. TRIGGER when the user says "cut a release", "tag a release", "release v1.2.0", "ship version 1.2.0", "create a release for 1.2.0", "bump the version to 1.2.0", "make a release", "generate a changelog and tag", "what version should I release", "what's

Padrões de profiling no Unity, incluindo ProfilerMarkers, FrameTimingManager, profiling de memória e orçamentos de desempenho.

Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, is not grounded in real data, does not cite sources, makes unsupported claims, or you need to verify AI responses against source material. Also use when your LLM makes up facts, responses are disconnected from the input, or outputs are not grounded in source documents. Covers citation enforcement, faithfulness ver

Centralized team management SDK for Rune workflows. Provides ExecutionEngine interface (TeamEngine), shared lifecycle protocols (teamTransition, cleanup, session isolation), preset system, and monitoring utilities. Use when spawning agent teams, monitoring teammates, or cleaning up workflows. Loaded automatically by workflow skills (appraise, strive, devise, mend, etc). Keywords: team management,

Fetch the exact source code of a named symbol (function, class, method, type) from the codebase using the codemunch index. Reads only the lines for that symbol — not the whole file. Uses LSP for hover docs and type info when available. This is the core token-saving operation.

Use when you need to stream LM output tokens to a frontend in real time — progressive responses, typing indicators, server-sent events, or WebSocket feeds. Common scenarios - streaming DSPy responses to a React UI, FastAPI SSE endpoint with DSPy, showing AI typing in a chat interface, streaming multi-field outputs, streaming ReAct agent loop progress, or handling duplicate fields with predict_name

Use LangWatch for DSPy auto-tracing and real-time optimizer progress. Use when you want to set up LangWatch, langwatch.dspy.init, auto-tracing DSPy, real-time optimization dashboard, optimizer progress tracking, app.langwatch.ai, or DSPy optimizer dashboard. Also used for langwatch setup, pip install langwatch, langwatch trace, optimizer progress, real-time optimization, watch optimizer run, LangW