Loading...
Loading...
Found 301 Skills
Rust profiling skill for performance analysis. Use when generating flamegraphs from Rust binaries, measuring monomorphization bloat with cargo-llvm-lines, analysing binary size with cargo-bloat, microbenchmarking with Criterion, or interpreting inlined frames in profiles. Activates on queries about cargo flamegraph, cargo-bloat, cargo-llvm-lines, Criterion benchmarks, Rust performance profiling, or binary size analysis.
Performance profiling principles. Measurement, analysis, and optimization techniques.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Python performance profiling with cProfile, tracemalloc, and line_profiler. Use for identifying bottlenecks and memory issues. USE WHEN: user mentions "Python profiling", "cProfile", "memory profiling", asks about "Python performance", "tracemalloc", "line_profiler", "py-spy", "Python optimization", "Python memory leak" DO NOT USE FOR: Java/Node.js profiling - use respective skills instead
Use when you need to verify Java performance optimizations by comparing profiling results before and after refactoring — including baseline validation, post-refactoring report generation, quantitative before/after metrics comparison, side-by-side flamegraph analysis, regression detection, or creating profiling-comparison-analysis and profiling-final-results documentation. Part of the skills-for-java project
Use when you need to set up Java application profiling to detect and measure performance issues — including automated async-profiler v4.0 setup, problem-driven profiling (CPU, memory, threading, GC, I/O), interactive profiling scripts, JFR integration with Java 25 (JEP 518, JEP 520), or collecting profiling data with flamegraphs and JFR recordings. Part of the skills-for-java project
Application performance profiling and bottleneck identification — Node.js profiling, Chrome DevTools, flame graphs, memory leak detection, CPU profiling, React rendering performance. Activate on "profiling", "performance bottleneck", "flame graph", "memory leak", "slow app", "CPU profiling", "heap snapshot", "React re-renders", "EXPLAIN ANALYZE", "event loop lag", "clinic.js", "Core Web Vitals". NOT for infrastructure monitoring or observability (use logging-observability), load testing (use a load-testing skill), or database schema optimization.
Guide performance profiling with Instruments, diagnose hangs, memory issues, slow launches, and energy drain. Use when reviewing app performance or investigating specific bottlenecks.
Use when app feels slow, memory grows over time, battery drains fast, or you want to profile proactively - decision trees to choose the right Instruments tool, deep workflows for Time Profiler/Allocations/Core Data, and pressure scenarios for misinterpreting results
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while golang-performance provides the optimization patterns.