“performance optimization”

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction.

Generates performance-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Performance Optimization pillar of…

提供性能优化方法论、设计原则和具体优化规则。在编写代码、优化性能瓶颈、进行 code review 时使用，涵盖 CPU、内存、I/O、并发等维度。

Produce a prioritized performance-optimization roadmap across frontend, backend, and infrastructure.

Use when investigating N+1s, slow queries, caching, or query plans in Rails.

Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.

Use when an isometric Canvas game drops frames, to cut draw calls and allocations and hold a steady 60fps.

Use when optimizing React Three Fiber scenes, experiencing frame drops, high draw calls, or implementing 3D performance features - ensures systematic…

Plan, implement, or review google cloud waf performance optimization work in an existing codebase with compatibility, security, and verification controls.

Performance engineer loop — speed, memory, scalability, extra rendering.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices.

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations.

Identifies bottlenecks and improves speed, efficiency, and resource utilization.

Specialized skill for profiling applications, specifically games or interactive UIs, addressing frame drops, memory leaks, and render bottlenecks.

PFW 철학 통합 자동화 시스템 (v4.0) - Point-Free Workshop 단순성 원칙 최우선 적용, 12개 서브에이전트 동시 실행, TCAFlow & WeaveDI 3.4.1 전문, 타입 안전한 상태 검증 자동 구현.

排查并优化 Ascend C 算子性能。当用户开发、审查或优化 Ascend C kernel 算子时使用，或当用户提及 Ascend C 性能优化、算子优化、tiling、流水、搬运、 内存优化、NPU/昇腾等关键词时触发。

指导 Catlass 算子性能调优。流程：阅读 catlass 优化指南、获取/更新 profiler 基线、按指南修改 tiling、重新编译、**强制产出并展示性能对比报告**、迭代对比。调优策略以 catlass 文档为准。条件不明则追问。

Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.

Universal SQL performance optimization guidance for query tuning, indexing, execution plans, pagination, batching, and database performance analysis.

Performance optimization mindset - knowing when to optimize, how to measure, where bottlenecks hide, and when "fast enough" is the right answerUse when "slow…

Keeping codebases healthy, performant, and maintainable - refactoring, performance optimization, and technical debt managementUse when "refactor, optimize…

Profile-driven performance optimization with behavior proofs.

Evidence-gated workflow for MoE performance optimization in Megatron Bridge.

Performance optimization patterns for Mandu applications.