Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-15, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn vs HeroUI legacy, folder placement, actions/adapters, shared types/hooks/lib).
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
Creates MCP tools for Prowler MCP Server. Covers BaseTool pattern, model design, and API client usage. Trigger: When working in mcp_server/ on tools (BaseTool), models (MinimalSerializerMixin/from_api_response), or API client patterns.
Reference OpenCode docs when implementing skills, plugins, MCPs, or config-driven behavior.
SolidJS reactivity + UI state patterns for OpenWork
Tauri 2.x + SolidJS stack for OpenWork native app
Core context and guardrails for OpenWork native app
Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.
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).
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
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".
Navigate and work with the react-native-navigation (RNN) codebase. Use when fixing bugs, adding features, tracing command flows, understanding options resolution, or working across JS/iOS/Android layers in this repo.
Navigate and work with the react-native-navigation (RNN) codebase. Use when fixing bugs, adding features, tracing command flows, understanding options resolution, or working across JS/iOS/Android layers in this repo.
Navigate and work with the react-native-navigation (RNN) codebase. Use when fixing bugs, adding features, tracing command flows, understanding options resolution, or working across JS/iOS/Android layers in this repo.
Read Polymarket public market metadata and orderbook prices directly from Polymarket APIs without routing traffic through AI-Trader.
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
