性能
性能分析与优化
async-expert
martinholovsky
"Expert in asynchronous programming patterns across languages (Python asyncio, JavaScript/TypeScript promises, C# async/await, Rust futures). Use for concurrent programming, event loops, async patterns, error handling, backpressure, cancellation, and performance optimization in async systems."
configure
designnotdrum
"Configure pattern-radar sources, weights, and domains."
javascript-developer
paulund
Use when building JavaScript applications with modern ES2023+ features, frameworks, and best practices.
system-check
dgriffin831
Check system health and performance
numpy
G1Joshi
NumPy numerical computing with arrays. Use for numerical operations.
deepseek
G1Joshi
DeepSeek AI models for coding. Use for code AI.
pytorch
G1Joshi
PyTorch deep learning framework with dynamic graphs. Use for neural networks.
lightgbm
G1Joshi
LightGBM gradient boosting framework. Use for fast ML.
mistral
G1Joshi
Mistral AI efficient open models. Use for efficient AI.
proactive-agent
wangyendt
"让 AI 助手从「等待任务」变成「主动预见」的架构设计。包含 WAL 协议、Working Buffer、自动定时任务等经过实战验证的模式。"
memory-manager
rangerrick337
"Manages the 3-tier memory system. Use when: (1) the user says 'remember this' or 'commit to memory', (2) a significant decision or fact is established, (3) the user runs /memory-save or /memory-review, (4) at session start to load memory context, or (5) at session end to flush important context to logs."
core-brain-mula
NachaFromMars
"CoreBrainMula-TieuTam V1.0 — Zero-Decay Neural Memory System. Cài đặt và vận hành NeuralMemory với zero decay (không bao giờ quên), conflict resolution thông minh (tự quyết/hỏi + thông báo), và token budget tối ưu. Use when: (1) Cài NeuralMemory lần đầu, (2) Import MEMORY.md vào neural brain, (3) Phát hiện conflict memory và cần resolve, (4) Query memory với associative recall, (5) Backup/restore brain, (6) Bất kỳ thao tác nào liên quan đến neural memory system."
tig-innovator
daydreamsai
AI-powered algorithm optimization agent for The Innovation Game protocol. Earns cryptocurrency by optimizing Rust algorithms. Use when optimizing TIG challenge algorithms or submitting solutions to the TIG network.
requirements-elicitation
DoubleslashSE
Requirements gathering and elicitation techniques for business analysis. Use when conducting stakeholder interviews, gathering functional/non-functional requirements, or identifying gaps in requirements.
dspy-miprov2-optimizer
OmidZamani
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization", mentions "state-of-the-art DSPy optimizer", "joint instruction tuning", or needs maximum performance from a DSPy program with substantial training data (200+ examples).
Performance Optimizer
daffy0208
Optimize application performance and scalability. Use when investigating slow applications, scaling bottlenecks, or improving response times. Covers profiling, caching, database optimization, and frontend performance.
superpowers-debug
anthonylee991
Systematic debugging: reproduce, isolate, form hypotheses, instrument, fix, and add regression tests. Use when troubleshooting errors, failing tests, or unexpected behavior.
performance-optimizer
armanzeroeight
Optimize React Native app performance including bridge optimization, list rendering, memory management, and profiling. Use when app is slow, laggy, or consuming excessive memory. Trigger words include "performance", "optimize", "slow", "lag", "memory", "FlatList", "rendering".
laravel-performance-select-columns
noartem
Select only required columns to reduce memory and transfer costs; apply to base queries and relations
dough-test-optimization
terryyin
Speeds up local test feedback through profiling and measured experiments across related tests. Use to optimize slow tests or test-suite performance. Preserves behavioral coverage and confidence while pursuing fewer redundant cases, less code, and cleaner design. With --resolve, triages recorded candidates without profiling or optimizing.
laravel-data-chunking-large-datasets
noartem
Process large datasets efficiently using chunk(), chunkById(), lazy(), and cursor() to reduce memory consumption and improve performance
improve-worker
chnlich
methodology for iterative improve loop workers.
decay-upkeep
Bbeierle12
Building decay and upkeep systems for survival games. Use when implementing timer-based decay, Tool Cupboard patterns (Rust-style protection radius), resource upkeep costs, or server performance management through automatic cleanup. Balances gameplay and server health.
building-mechanics
Bbeierle12
Three.js 3D building system with spatial indexing, structural physics, and multiplayer networking. Use when creating survival games, sandbox builders, or any game with player-constructed structures. Covers performance optimization (spatial hash grids, octrees, chunk loading), structural validation (arcade/heuristic/realistic physics modes), and multiplayer sync (delta compression, client prediction, conflict resolution).