性能
性能分析与优化
backend-principle-eng-javascript-pro-max
PrakharMNNIT
"Principal backend engineering intelligence for JavaScript services. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, reliability, performance, security, observability, scalability, operability, cost."
ask-questions-if-underspecified
alemar11
Clarify requirements before implementing when a request is underspecified or the user asks for clarification.
monitoring-expert
dmonteroh
"Provides end-to-end observability across logs, metrics, traces, alerting, and performance testing. Use when instrumenting services, setting alert strategy, or designing an observability stack."
system-scenario-player
famaoai-creator
Global speed multiplier for delays.
debugging-methodology
webdevtodayjason
Scientific debugging methodology including hypothesis-driven debugging, bug reproduction, binary search debugging, stack trace analysis, logging strategies, and root cause analysis. Use when debugging errors, analyzing stack traces, investigating bugs, or troubleshooting performance issues.
networkx
eyadsibai
Use when "NetworkX", "graph analysis", "network analysis", "graph algorithms", "shortest path", "centrality", "PageRank", "community detection", "social network", "knowledge graph"
cost-optimization
dmonteroh
"Cloud FinOps cost governance for reducing cloud spend while maintaining reliability. Use when teams need tagging/chargeback, budgets/anomaly detection, rightsizing, commitment strategy (RIs/Savings Plans/CUDs), or unit-cost analysis. Produces a prioritized savings plan with verification gates."
llm-inference
eyadsibai
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
next-loading-skeleton
akashp1712
"⚡ Instant Loading UI for Next.js - Auto-generate beautiful loading.tsx with shadcn/ui Skeleton placeholders. Perfect for dashboards, data tables, and profile pages. Zero wait time, maximum user satisfaction."
mem-skill
Lilily58
Hybrid conversational memory management using SQLite and a vector database for retrieval-augmented user context. Use when building or updating assistants that need persistent user facts, lexical plus semantic retrieval, conflict arbitration, confidence scoring, temporal validity, and profile injection across turns.
memory-systems
eyadsibai
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"
ai-era-career-planner
mnetfairy
AI时代职业规划师技能。专为AI时代职场变化而设计，帮助用户应对AI带来的职业冲击与机遇。当用户询问职业规划、职业建议、选专业、职场转型、未来就业方向时触发。功能包括：收集用户基本信息、霍兰德职业兴趣测评、职业价值观分析、AI时代职业影响评估（高危/中危/低危分级），并输出完整的个性化职业规划报告。关键词：职业规划、选专业、工作建议、做什么工作好、职业转型、AI时代职业、AI替代、哪些工作会被AI取代。
vercel-react-only-best-practices
TianyiLi
React performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.
load-topology
nicholasf
Read the local system topology to discover available machines and models. Triggers on "load topology", "what models are available", "which machines are running", "start a model", "show me the topology", "sync topology", "refresh topology", "benchmark llm", "benchmark model", "test llm", "run benchmark", "help", "show help", "list subcommands".
ti-expert
macCesar
"Titanium SDK architecture and implementation expert. Use when designing, reviewing, analyzing, or examining Titanium project structure (Alloy or Classic), creating controllers/views/services, choosing models vs collections, implementing communication patterns, handling memory cleanup, testing, auditing code, or migrating legacy apps. Automatically identifies project type."
performance
dmonteroh
"End-to-end performance optimization workflow for baselining, profiling bottlenecks, proposing measurable fixes, and adding regression guardrails. Includes a safe-by-default scan/report script to capture repo signals and write a deterministic report. Use for latency/throughput/resource issues, scalability work, or performance gating."
ct-c-style
experiencenow-ai
C coding style for Tockchain/Valis firmware development. Use when writing, reviewing, or modifying C code for this project. Enforces compact Allman bracing, stdint types, zero-copy wire structs, dependency-ordered functions, unique negative error codes, and high-performance patterns. Triggers on any C code generation, editing, or review request.
backend-principle-eng-python-ml-pro-max
PrakharMNNIT
"Principal backend engineering intelligence for Python AI/ML systems. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale ML services and pipelines. Focus: data quality, reproducibility, reliability, performance, security, observability, model evaluation, MLOps."
llm-training
eyadsibai
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
backend-principle-eng-nodejs-pro-max
PrakharMNNIT
"Principal backend engineering intelligence for Node.js runtime systems. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale backend code and architectures. Focus: correctness, reliability, performance, security, observability, scalability, operability, cost."
agent-guard
astecka-m
Real-time prompt injection detection and sanitization for AI agents. Protects against Clinejection-style attacks, command injection, and malicious prompt manipulation. Works as both OpenClaw skill and Claude MCP server.
dask
eyadsibai
Use when "Dask", "parallel computing", "distributed computing", "larger than memory", or asking about "parallel pandas", "parallel numpy", "out-of-core", "multi-file processing", "cluster computing", "lazy evaluation dataframe"
ti-guides
macCesar
"Titanium SDK official fundamentals and configuration guide. Use when working with, reviewing, analyzing, or examining Titanium projects, Hyperloop native access, app distribution (App Store/Google Play), tiapp.xml configuration, CLI commands, memory management, bridge optimization, CommonJS modules, SQLite transactions, or coding standards. Applies to both Alloy and Classic projects."
engram
qwexs
Etalon memory architecture with Knowledge Graph (PARA), session isolation, memory decay, and QMD hybrid search