Search Skills
Find the perfect capability for your agent.
tailwind-css
Tailwind CSS configuration, custom plugins, design systems, theming, and component patterns for modern web applications.
supplier-scorecard-engine
Automated supplier performance scorecard generation with KPI tracking and trend analysis
supplier-onboarding-orchestrator
Supplier onboarding workflow orchestration with documentation collection and system setup
dynamics365-connector
Microsoft Dynamics 365 Sales integration with Power Platform support
brand-tracking
Brand health measurement and tracking platform integration
cross-dock-orchestrator
Flow-through logistics process coordination skill to minimize storage time and accelerate product movement
support-platform-integration
Integration with support and ticketing platforms
data-catalog-enricher
Enriches data catalog entries with automated metadata
nccl-communication
NVIDIA Collective Communications Library integration for multi-GPU operations. Initialize NCCL communicators, execute collective operations, configure communication topologies, profile collective performance, and support RCCL for AMD compatibility.
cutlass-triton
High-performance kernel template libraries and DSLs. Generate CUTLASS GEMM configurations, implement Triton kernel definitions, configure epilogue operations, tune tile sizes and warp arrangements, and benchmark against cuBLAS.
cuda-toolkit
Deep integration with NVIDIA CUDA toolkit for kernel development, compilation, and debugging. Execute nvcc compilation with optimization flags analysis, generate and validate CUDA kernel code, analyze PTX/SASS assembly output, and configure execution parameters.
opencl-runtime
Cross-vendor OpenCL runtime management and kernel development. Query platforms/devices, generate portable OpenCL C kernel code, handle vendor-specific extensions, manage contexts and command queues, compile and cache programs.
cuda-graphs
Expert skill for CUDA Graph capture and optimization for reduced launch overhead. Capture CUDA operations into graphs, instantiate and execute graph instances, update graph node parameters, profile graph vs stream execution, design graph-friendly kernel patterns, and optimize launch latency for inference.
cublas-cudnn
Expert integration with NVIDIA GPU-accelerated math libraries. Configure cuBLAS tensor core operations, generate cuBLAS GEMM calls, integrate cuDNN layers, handle algorithm selection, and support mixed-precision operations.
pwntools-exploitation-skill
Exploit development automation using pwntools framework