Loading...
Loading...
Found 221 Skills
Multi-cycle performance optimization with profiling and bottleneck analysis. Use when optimizing application performance.
Detect performance anti-patterns and apply optimization techniques in Go. Covers allocations, string handling, slice/map preallocation, sync.Pool, benchmarking, and profiling with pprof. Use when checking performance, finding slow code, reducing allocations, profiling, or reviewing hot paths. Trigger examples: "check performance", "find slow code", "reduce allocations", "benchmark this", "profile", "optimize Go code". Do NOT use for concurrency correctness (use go-concurrency-review) or general code style (use go-coding-standards).
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.
Workflow for learning CuTe Python DSL by reading, importing, profiling, and extracting reusable patterns from CUTLASS Blackwell example kernels. Use when: (1) studying CUTLASS CuTe DSL reference implementations, (2) importing CUTLASS examples into the project runtime infrastructure, (3) building CuTe DSL knowledge base entries from profiling experiments, (4) understanding CuTe DSL API patterns, TMA pipelining, warpgroup scheduling, or persistent kernel structure.
Full Sentry SDK setup for Node.js, Bun, and Deno. Use when asked to "add Sentry to Node.js", "add Sentry to Bun", "add Sentry to Deno", "install @sentry/node", "@sentry/bun", or "@sentry/deno", or configure error monitoring, tracing, logging, profiling, metrics, crons, or AI monitoring for server-side JavaScript/TypeScript runtimes.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
Spatial indexing and world streaming for Three.js building games with thousands of pieces. Use when optimizing building games, implementing spatial queries, chunk loading, or profiling performance. Includes spatial hash grids, octrees, chunk managers, and benchmarking tools.
Automatically discover debugging and profiling skills when working with GDB, LLDB, breakpoints, profiling, stack traces, memory leaks, core dumps, or performance profiling. Activates for debugging development tasks.
Guide for Grafana Pyroscope continuous profiling. Use for Kubernetes Helm deployment, Go/Java/Python/.NET/Ruby/Node.js profiling, storage backends, trace-to-profile linking, and troubleshooting.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.