Loading...
Loading...
Found 298 Skills
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
Automatically discover software engineering practice skills when working with code review, documentation, pair programming, production debugging, performance profiling, deployment strategies, or software engineering practices. Activates for engineering development tasks.
Comprehensive immune repertoire analysis for T-cell and B-cell receptor sequencing data. Analyze TCR/BCR repertoires to assess clonality, diversity, V(D)J gene usage, CDR3 characteristics, convergence, and predict epitope specificity. Integrate with single-cell data for clonotype-phenotype associations. Use for adaptive immune response profiling, cancer immunotherapy research, vaccine response assessment, autoimmune disease studies, or repertoire diversity analysis in immunology research.
Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease/condition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis across 9 phases covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment (Low/Intermediate/High/Very High), treatment algorithm (1st/2nd/3rd line), pharmacogenomic guidance, clinical trial matches, and monitoring plan. Use when clinicians ask about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy across cancer, metabolic, cardiovascular, neurological, or rare diseases.
Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Given a cancer type, somatic mutations, and optional biomarkers (TMB, PD-L1, MSI status), performs systematic analysis across 11 phases covering TMB classification, neoantigen burden estimation, MSI/MMR assessment, PD-L1 evaluation, immune microenvironment profiling, mutation-based resistance/sensitivity prediction, clinical evidence retrieval, and multi-biomarker score integration. Generates a quantitative ICI Response Score (0-100), response likelihood tier, specific ICI drug recommendations with evidence, resistance risk factors, and a monitoring plan. Use when oncologists ask about immunotherapy eligibility, checkpoint inhibitor selection, or biomarker-guided ICI treatment decisions.
Full Sentry SDK setup for .NET. Use when asked to "add Sentry to .NET", "install Sentry for C#", or configure error monitoring, tracing, profiling, logging, or crons for ASP.NET Core, MAUI, WPF, WinForms, Blazor, Azure Functions, or any other .NET application.
Use this skill when implementing data validation, data quality monitoring, data lineage tracking, data contracts, or Great Expectations test suites. Triggers on schema validation, data profiling, freshness checks, row-count anomalies, column drift, expectation suites, contract testing between producers and consumers, lineage graphs, data observability, and any task requiring data integrity enforcement across pipelines.
Guides efficient Haskell aligned with GHC practice -- laziness and strictness, purity, fusion, newtypes, pragmas, Core reading, and space-leak avoidance. Use when writing or reviewing Haskell, optimizing or profiling, debugging strictness or memory, or when the user mentions GHC, thunks, foldl vs foldl', list fusion, SPECIALIZE, or UNPACK.
How to benchmark and analyze memory usage in Turso using the memory-benchmark crate and dhat heap profiler. Use this skill whenever the user mentions memory usage, memory profiling, allocation tracking, heap analysis, memory regression, memory benchmarking, dhat, or wants to understand where memory is being allocated during SQL workloads. Also use when investigating memory growth in WAL or MVCC mode. IMPORTANT - If you modify the perf/memory crate (add profiles, change CLI flags, change output format, etc.), update this skill document to reflect those changes so it stays accurate for future agents.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Guide for adding a new benchmark or training environment to NeMo-Gym. Use when the user asks to add, create, or integrate a benchmark, evaluation, training environment, or resources server into NeMo-Gym. Also use when wrapping an existing 3rd-party benchmark library. Covers the full workflow: data preparation, resources server implementation, agent wiring, YAML config, testing, and reward profiling (baselining). Triggered by: "add benchmark", "new resources server", "integrate benchmark", "wrap benchmark", "add training environment", "add eval".