221 skills · sorted by relevance
Reduce Google Kubernetes Engine costs by adjusting CPU and memory requests, setting resource quotas, and choosing Spot VMs or committed use discounts. Match spending decisions to steady usage, variable demand, and workloads that tolerate interruptions.
Review past dsh agent sessions to identify recurring tasks and test proposed skill or memory improvements. This skill guides preview runs, validation on reserved tasks, staged proposals, adoption with backups, and scheduled nightly cycles.
Guide language model training with SimPO using pairs of preferred and rejected answers. Covers configuration, learning rate tuning, and memory troubleshooting for preference alignment, which adjusts model responses toward human preferences without a separate reference model.
Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.
Develop microcontroller firmware for STM32 or ESP32, including peripheral drivers and FreeRTOS tasks. The skill guides interrupt handling, memory and power optimization, and checks that time-sensitive operations meet their deadlines.
Audit C/C++ and Rust code for secrets left in memory. It checks missing or incomplete wipes, examines compiler output for removed cleanup operations, and produces reports with evidence and suggested fixes.
Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.
The English summary is being prepared. Showing the original description.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
The English summary is being prepared. Showing the original description.
Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, and hot-path optimization. Use when profiling or benchmarks have identified a bottleneck and you need the right optimization pattern to fix it. Also use when performing performance code review to suggest improvements or benchmarks that could help identify quick performance gains. Not for measurement methodology (→ See `samber/cc-skills-golang@golang-benchmark` skill) or debugging workflow (→ See `samber/cc-skills-golang@golang-troubleshooting` skill).
The English summary is being prepared. Showing the original description.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
The English summary is being prepared. Showing the original description.
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
The English summary is being prepared. Showing the original description.
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
The English summary is being prepared. Showing the original description.
Profiles Python code for performance bottlenecks and memory issues. Use when Python code is slow or when profiling for optimization before a release.
The English summary is being prepared. Showing the original description.
Performance profiling and optimization for web apps — Core Web Vitals (LCP, INP, CLS), Lighthouse audits, bundle analysis, backend profiling (CPU, memory, DB queries), N+1 detection, caching strategies (Redis, CDN, HTTP), and performance budgets. Use when user asks to improve performance, run Lighthouse audit, profile a Node.js app, optimize Core Web Vitals, reduce bundle size, or investigate slow response times. Do NOT use for database schema optimization (use db-sculptor), Docker image optimization (use docker), or CDN configuration.
The English summary is being prepared. Showing the original description.
Audits and scores Claude Projects using a six-dimension Scorecard with anchored 1-5 rubrics and detects seven structural anti-patterns. When global layer info is provided, adds cross-layer alignment findings. Use when user says "audit my project," "review my custom instructions," "score my project," "evaluate my Claude project," "improve my system prompt," "what's wrong with my project," "why is my project underperforming." Also trigger on symptom-phrased: "my project doesn't work right," "Claude is inconsistent in my project," "my Project used to work and now doesn't." Also use when the user pastes Custom Instructions asking why output is poor or generic. Do NOT use when the user's primary request is a global-layer audit (use rootnode-global-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or Memory-only optimization (use rootnode-memory-optimization if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.
The English summary is being prepared. Showing the original description.
Spark, pandas, polars, DuckDB optimization for batch data processing. Activate on: batch processing, Spark optimization, polars, DuckDB, pandas performance, data frame, shuffle, partition, memory optimization. NOT for: streaming pipelines (use streaming-pipeline-architect), warehouse queries (use data-warehouse-optimizer).
The English summary is being prepared. Showing the original description.
Systematically find and fix performance problems in applications, frontend and backend, by measuring first. Use this skill whenever the user reports slow endpoints, high latency, poor throughput, memory leaks, large bundles, or slow page loads; wants to profile with cProfile, py-spy, Chrome DevTools, Node --cpu-prof, or perf; run load tests with locust or k6; set performance budgets or SLOs; optimize database queries (EXPLAIN, indexes, N+1); add caching (Redis); improve frontend performance (code splitting, lazy loading, image optimization, memoization, virtualization); or tune the network (CDNs, gzip/br, HTTP/2/3). Also trigger for p50/p95/p99 latency, throughput, error rate, connection pooling, async vs threads, GIL, and memory leak investigations.
The English summary is being prepared. Showing the original description.
Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
The English summary is being prepared. Showing the original description.
Spark, pandas, polars, DuckDB optimization for batch data processing. Activate on: batch processing, Spark optimization, polars, DuckDB, pandas performance, data frame, shuffle, partition, memory optimization. NOT for: streaming pipelines (use streaming-pipeline-architect), warehouse queries (use data-warehouse-optimizer).
The English summary is being prepared. Showing the original description.
Systematic performance profiling and optimization methodology. Covers CPU profiling, memory profiling, heap analysis, goroutine/thread analysis, FlameGraph generation, latency profiling, database query profiling, network I/O profiling, and continuous performance regression detection. USE WHEN: investigating performance issues, optimizing slow code, reducing memory usage, diagnosing GC/CPU bottlenecks, finding N+1 queries, analyzing pprof/flamegraph output, or establishing a performance baseline. Triggers on "profiling", "performance analysis", "slow code", "flame graph", "pprof", "heap dump", "memory leak", "CPU spike", "bottleneck".
The English summary is being prepared. Showing the original description.
Analyze performance in Claude Flow swarms, groups of agents working together. Identify delays in communication, processing, memory, and networking, then generate reports and prioritized recommendations. Compare previous runs or apply available automatic optimizations.
Configure images and videos as surface textures in Three.js, and use environment images for backgrounds and reflections. Adjust placement, color settings, repetition, and filtering, then manage texture memory through compression, reuse, and disposal.