性能
性能分析与优化
flutter-expert
Jeffallan
Use when building cross-platform applications with Flutter 3+ and Dart. Invoke for widget development, Riverpod/Bloc state management, GoRouter navigation, platform-specific implementations, performance optimization.
pandas-pro
Jeffallan
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
dma-attack-techniques
gmh5225
Guide for PCIe DMA threat modeling, FPGA-based memory access, and defensive implications in game security. Use this skill when researching pcileech, BAR and TLP behavior, page-table walking, IOMMU or VT-d, device impersonation, firmware mimicry, or DMA detection and mitigation in game security research.
openclaw-test-heap-leaks
openclaw
Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.
openclaw-ci-limits
openclaw
Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning .github/workflows/*, docs/ci.md, CI runner labels, matrix max-parallel, ClawSweeper/Blacksmith burst protection, CodeQL runner placement, or investigating slow/queued OpenClaw CI.
openclaw-test-performance
openclaw
Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
deep-review
coder
Sub-agent powered code reviews spanning correctness, tests, consistency, and fit
cpu-profile
ClickHouse
Profile a ClickHouse query using the sampling query profiler and system.trace_log. Use when the user wants to find CPU hotspots, analyze where time is spent in a query, or investigate performance bottlenecks.
nemo-evaluator-sdk
Orchestra-Research
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
gptq
Orchestra-Research
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
deepspeed
Orchestra-Research
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
quantizing-models-bitsandbytes
Orchestra-Research
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
cuda-index-width
pytorch
Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or AT_DISPATCH_INDEX_TYPES, and when considering binary-size or performance impact of index-type templating.
healthcheck
elizaOS
Host security hardening and risk-tolerance configuration for Otto deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, Otto cron scheduling for periodic checks, or version status checks on a machine running Otto (laptop, workstation, Pi, VPS).
web-perf
cloudflare
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.
vercel-react-best-practices
Significant-Gravitas
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
optimize-bundle-size
elastic
Reduce plugin page load bundle size and avoid unnecessary increases in packages/kbn-optimizer/limits.yml. Use when proactively optimizing bundles, investigating CI page-load overages, or reviewing PRs that change bundle limits.
py
crazyguitar
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC. Use for: Python questions, Python interview preparation, debugging, performance optimization, async patterns, library examples, code review, best practices, MLOps workflows, distributed computing, security implementations, and any Python development tasks.
gradle-expert
vitorpamplona
Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5) Desktop packaging (DMG/MSI/DEB), (6) Build performance optimization, (7) Proguard/R8 configuration, (8) Common KMP + Android Gradle issues (Compose conflicts, secp256k1 JNI variants, source set problems).
fastify-best-practices
mcollina
"Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify application — including defining routes, implementing plugins, setting up JSON Schema validation, handling errors, optimising performance, managing authentication, configuring CORS and security headers, integrating databases, working with WebSockets, and deploying to production. Covers the full Fastify request lifecycle (hooks, serialization, logging with Pino) and TypeScript integration via strip types. Trigger terms: Fastify, Node.js server, REST API, API routes, backend framework, fastify.config, server.ts, app.ts."
node
mcollina
Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error handling, streams, modules, testing, performance, caching, logging, and more. Use when setting up Node.js projects with native TypeScript support, configuring type stripping (--experimental-strip-types), writing Node 22+ TypeScript without a build step, or when the user mentions 'native TypeScript in Node', 'strip types', 'Node 22 TypeScript', '.ts files without compilation', 'ts-node alternative', or needs guidance on error handling, graceful shutdown, flaky tests, profiling, or environment configuration in Node.js. Helps configure tsconfig.json for type stripping, set up package.json scripts, handle module resolution and import extensions, and apply robust patterns across the full Node.js stack.
depth-estimation
SharpAI
"Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)"
react-component-performance
Dimillian
Analyze and optimize React component performance issues (slow renders, re-render thrash, laggy lists, expensive computations). Use when asked to profile or improve a React component, reduce re-renders, or speed up UI updates in React apps.
swiftui-performance-audit
Dimillian
Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.