11 skills · sorted by relevance
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".
The English summary is being prepared. Showing the original description.
Assess Google Cloud workloads for environmental sustainability using the Well-Architected Framework. Get recommendations on lower-carbon regions, efficient computing and storage, AI energy use, and ongoing emissions measurement with Carbon Footprint.
Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.
Optimize Claude API performance with prompt caching, model selection, streaming, and latency reduction techniques. Use when experiencing slow responses, optimizing token usage, or reducing time-to-first-token in production. Trigger with phrases like "anthropic performance", "claude speed", "optimize claude latency", "anthropic caching", "faster claude responses".
The English summary is being prepared. Showing the original description.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
Plan how an AI agent uses limited input space through reusable prompt prefixes, shorter tool outputs, summaries, and task splitting. Measure token use, response quality, and latency to choose optimizations that provide a net benefit.
Use when you need to refactor Java code for high performance — including memory/allocation reduction, CPU hot-path optimization, and syntax/API/control-flow improvements. This should trigger for requests such as Review Java code for high performance; Optimize Java hot path; Reduce Java allocations; Improve Java latency/throughput. Part of Plinth Toolkit
The English summary is being prepared. Showing the original description.
Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.
The English summary is being prepared. Showing the original description.
Audit over-engineered codebases by factoring layers into live obligations, quotienting redundant distinctions, ablating unearned surface, and normalizing survivors while preserving required behavior. Use when change latency or agent difficulty comes from frameworks, plugins, DI, codegen, task runners, config indirection, ORMs, GraphQL, monorepo/infra tooling, or web stacks, or when asked to remove layers. Produces an evidence-backed Reduction Certificate, cuts, migration phases, proof signals, and rollback. Not for one local readability cleanup (use tw-complexity-mitigator).
The English summary is being prepared. Showing the original description.