gguf-quantization
davila7GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
get-available-resources
davila7This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
llama-cpp
davila7Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
railway-metrics
davila7Query resource usage metrics for Railway services. Use when user asks about resource usage, CPU, memory, network, disk, or service performance like "how much memory is my service using" or "is my service slow".
pytorch-fsdp
davila7Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
nanogpt
davila7Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
rspack-perf-profiling
web-infra-devRun Rspack performance profiling on Linux using perf (with DWARF call stacks), generate perf.data, and analyze hotspots. Use when you need CPU-level bottlenecks, kernel symbol resolution, or repeatable profiling for rspack build/bench cases. Includes optional samply import with per-CPU threads for visualization, but primary analysis is perf-based.
get-available-resources
K-Dense-AIThis skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
swiftui-performance-audit
steipeteAudit 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.
swiftui-performance-audit
DimillianAudit 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.
system-info
UKGovernmentBEISGet detailed system information including OS, kernel, CPU, and memory details
mineru-pdf
openclawParse PDFs locally (CPU) into Markdown/JSON using MinerU. Assumes MinerU creates per‑doc output folders; supports table/image extraction.
parakeet-stt
openclawLocal speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, or processing voice recordings locally without cloud APIs.
mactop
openclawRetrieve real-time hardware metrics from Apple Silicon Macs using mactop's TOON format. Provides CPU, RAM, GPU, power, thermal, network, disk I/O, and Thunderbolt bus information. Use when the user wants system stats, hardware monitoring, or performance metrics on Apple Silicon Macs.
bonero-miner
openclawMine Bonero - private cryptocurrency for AI agents. RandomX CPU mining, Monero-based privacy.
process-watch
openclawMonitor system processes - CPU, memory, disk I/O, network, open files, ports. Find resource hogs, kill runaway processes, track what's consuming your machine.
system_monitor
openclawCheck the current CPU, RAM, and GPU status of the local server.
performance-testing
This skill enables Claude to design, execute, and analyze performance tests using the performance-test-suite plugin. It is activated when the user requests load testing, stress testing, spike testing, or endurance testing, and when discussing performance metrics such as response time, throughput, and error rates. It identifies performance bottlenecks related to CPU, memory, database, or network issues. The plugin provides comprehensive reporting, including percentiles, graphs, and recommendations.
cpu-profiler-config
Cpu Profiler Config - Auto-activating skill for Performance Testing. Triggers on: cpu profiler config, cpu profiler config Part of the Performance Testing skill category.
profiling-application-performance
jeremylongshoreThis skill enables Claude to profile application performance, analyzing CPU usage, memory consumption, and execution time. It is triggered when the user requests performance analysis, bottleneck identification, or optimization recommendations. The skill uses the application-profiler plugin to identify performance bottlenecks and suggest code-level optimizations. Use it when asked to "profile application", "analyze performance", or "find bottlenecks". It is also helpful when the user mentions specific performance metrics like "CPU usage", "memory leaks", or "execution time".
monitoring-cpu-usage
jeremylongshoreThis skill enables Claude to monitor and analyze CPU usage patterns within applications. It helps identify CPU hotspots, analyze algorithmic complexity, and detect blocking operations. Use this skill when the user asks to "monitor CPU usage", "optimize CPU performance", "analyze CPU load", or "find CPU bottlenecks". It assists in identifying inefficient loops, regex performance issues, and provides optimization recommendations. This skill is designed for improving application performance by addressing CPU-intensive operations.
single-cell-preprocessing-with-omicverse
StarlitnightlyWalk through omicverse's single-cell preprocessing tutorials to QC PBMC3k data, normalize counts, detect HVGs, and run PCA/embedding pipelines on CPU, CPU–GPU mixed, or GPU stacks.
parallel-processing
benchflow-aiParallel processing with joblib for grid search and batch computations. Use when speeding up computationally intensive tasks across multiple CPU cores.
python-parallelization
benchflow-aiTransform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and data-parallel (vectorization) scenarios.
axiom-energy
Use when app drains battery, device gets hot, users report energy issues, or auditing power consumption - systematic Power Profiler diagnosis, subsystem identification (CPU/GPU/Network/Location/Display), anti-pattern fixes for iOS/iPadOS
perf-profiler
agent-shUse when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
validate-binaries
Validate voxtype binaries for CPU instruction contamination. Use when checking release binaries for AVX-512 or GFNI instruction leaks that would crash on older CPUs.
debug-lldb
regenrekCapture and analyze thread backtraces with LLDB/GDB to debug hangs, deadlocks, UI freezes, IPC stalls, or high-CPU loops across any language or project. Use when an app becomes unresponsive, switching contexts stalls, or you need thread stacks to locate lock inversion or blocking calls.
performance-profiler
a5c-aiProfile application performance including CPU, memory, and flame graph generation
nodejs-profiling
a5c-aiExpert skill for Node.js-specific profiling and optimization. Use V8 CPU profiler, analyze heap snapshots, configure clinic.js tools (Doctor, Flame, Bubbleprof), debug event loop blocking, analyze async hooks performance, and optimize V8 JIT compilation.
surf
nicobailonControl Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok.
building
Use when building knowhere from source, configuring build options (CPU/GPU/DISKANN/ASAN), or troubleshooting compilation errors
performance-engineering
ancolemanWhen validating system performance under load, identifying bottlenecks through profiling, or optimizing application responsiveness. Covers load testing (k6, Locust), profiling (CPU, memory, I/O), and optimization strategies (caching, query optimization, Core Web Vitals). Use for capacity planning, regression detection, and establishing performance SLOs.
golang-performance
MadAppGangUse when profiling Go applications (pprof), running benchmarks, optimizing memory/CPU usage, or debugging performance bottlenecks in production Go code.
go-performance
caarlos0Analyze and optimize Go program performance. Use when asked to profile Go code, find performance bottlenecks, analyze memory allocations, detect memory leaks, write benchmarks, or optimize CPU/memory usage.
metrics
railwayappThis skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance. Covers questions like "how much memory is my service using" or "is my service slow".
perf-prof
OpenCloudOSAnalyze Linux system issues with perf-prof. perf-prof is a system-level analysis tool built on perf_event; events are processed in memory in real time and it can run for long periods with low overhead. Typical trigger scenarios: (1) high CPU usage and hotspot analysis (2) abnormal process states (many D/S states) (3) latency jitter or slow responses (4) memory leaks or abnormal growth (5) slow block device I/O (6) virtual machine performance issues (7) event aggregation and statistics (8) custom script analysis. Core analyzers: profile (CPU sampling), task-state (process state analysis), multi-trace (latency analysis), kmemleak (memory leak detection), blktrace (I/O latency), top/sql (aggregation/statistics), kvm-exit (virtualization exits), rundelay (scheduling delay), syscalls (system call timing), python (custom script analysis). Suitable for performance debugging, kernel/application development and debugging, and learning or understanding Linux kernel mechanisms (scheduling, memory, I/O, interrupts, etc.).
performance-profiling
conorluddyInstruments integration and performance analysis workflows for iOS apps. Use when profiling CPU usage, memory allocation, network activity, or energy consumption. Covers Time Profiler, Allocations, Leaks, Network instruments, and performance optimization strategies.
cc-performance-tuning
ryanthedevEnforce measure-first discipline for code optimization using a 7-step gated decision tree and 40-item checklist. Use when code is too slow, has performance issues, timeouts, OOM errors, high CPU/memory, or doesn't scale. Triggers on: profiler hot spots, latency complaints, unresponsive UI, memory allocation slow, needs optimization. Produce violation/warning/pass table with evidence.
aposd-optimizing-critical-paths
ryanthedevOptimize performance through mandatory measure-first workflow with 3 stages: MEASURE (gate) -> FUNDAMENTAL FIX -> CRITICAL PATH REDESIGN. Use when code is too slow, laggy, hangs, doesn't scale, has timeouts, OOM errors, or high CPU/memory. Emphasize that simpler code usually runs faster. Triggers on: performance issues, optimization needed, takes forever, profiling. Produces profiling-backed optimization with verified improvement.
cpu-profiling
aj-geddesProfile CPU usage to identify hot spots and bottlenecks. Optimize code paths consuming most CPU time for better performance and resource efficiency.
profiling-optimization
aj-geddesProfile application performance, identify bottlenecks, and optimize hot paths using CPU profiling, flame graphs, and benchmarking. Use when investigating performance issues or optimizing critical code paths.
workers-performance
secondskyCloudflare Workers performance optimization with CPU, memory, caching, bundle size. Use for slow workers, high latency, cold starts, or encountering CPU limits, memory issues, timeout errors.
pytorch-model-recovery
letta-aiThis skill should be used when reconstructing PyTorch models from weight files (state dictionaries), checkpoint files, or partial model artifacts. It applies when the agent needs to infer model architecture from saved weights, rebuild models without original source code, or recover models from corrupted/incomplete saves. Use this skill for tasks involving torch.load, state_dict reconstruction, architecture inference, or model recovery in CPU-constrained environments.
make-mips-interpreter
letta-aiGuide for implementing MIPS CPU interpreters/emulators, particularly for running compiled MIPS ELF binaries. This skill applies when building virtual machines to execute MIPS32 code, creating emulators for retro game ports (like Doom), or implementing CPU simulators. Use for tasks involving ELF parsing, instruction decoding, syscall emulation, and memory management for MIPS architecture.
party
cazalaProgrammatic guide for the @cazala/party library: engine setup, modules, particles, and performance across CPU + WebGPU.
metal-shader-expert
curiositech20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Metal shader', 'MSL', 'compute shader', 'vertex shader', 'fragment shader', 'PBR', 'ray tracing', 'tile shader', 'GPU profiling', 'Apple GPU'. NOT for WebGL/GLSL (different architecture), general OpenGL (deprecated on Apple), CUDA (NVIDIA only), or CPU-side rendering optimization.
Resource Analysis
openshift-engAnalyze system resource usage data from sosreport archives, extracting memory statistics, CPU load averages, disk space utilization, and process information from the sosreport directory structure to diagnose resource exhaustion, performance bottlenecks, and capacity issues