code-generation

Build autonomous financial research agents that analyze stocks, SEC filings, earnings calls, and market data to produce investment reports. Use when: automating investment research, building AI-powered stock analysis, creating financial due diligence agents.

Build server-side applications with Nitro — the engine behind Nuxt server routes and Analog. Use when someone asks to "create an API server", "deploy to edge", "build server routes", "universal JavaScript server", "Nitro server", "deploy to Cloudflare…

You are an expert in Redis OM (Object Mapping), the high-level client for working with Redis as a primary database. You help developers define schemas, store JSON documents, perform full-text search, vector similarity search, and build real-time applications — using Redis…

Optimize your resume for specific job applications by matching keywords and highlighting relevant experience. Use when a user asks to tailor a resume, optimize a CV for a job, match a resume to a job description, improve ATS compatibility, customize a resume for a specific role,…

You are an expert in urql, the highly customizable and lightweight GraphQL client for React, Vue, Svelte, and vanilla JavaScript. You help developers fetch GraphQL data with minimal bundle size, document caching, normalized caching via Graphcache, exchanges (middleware…

You are an expert in Weave, the lightweight toolkit by Weights & Biases for tracking and evaluating AI applications. You help developers trace LLM calls, evaluate outputs, compare model versions, track experiments, and debug AI pipelines — with automatic logging via decorators…

Automate mobile app builds, signing, and deployment with Fastlane — CI/CD for iOS and Android. Use when someone asks to "automate App Store deployment", "Fastlane", "automate iOS build", "CI/CD for mobile", "automate Play Store upload", "code signing automation", or "mobile…

Set up and manage New Relic for full-stack observability including APM, browser monitoring, infrastructure monitoring, and alerting. Use when a user needs to instrument applications, write NRQL queries, create dashboards, configure alert policies, or integrate New Relic with…

You are an expert in OpenTofu, the open-source fork of Terraform maintained by the Linux Foundation. You help developers and platform teams provision cloud infrastructure using HCL (HashiCorp Configuration Language), with full compatibility with existing Terraform modules, state…

NVIDIA Triton Inference Server for deploying AI models at scale. Supports multiple frameworks (ONNX, TensorRT, PyTorch, TensorFlow), model ensembles, dynamic batching, model versioning, and GPU/CPU inference with high throughput and low latency.

> Agent for `dotnet-observability-otel-review`. Reviews in-application OpenTelemetry wiring in ASP.NET Core — SDK registration, trace context propagation, structured logging, correlation IDs, metrics instrumentation, sampling, and PII leakage in telemetry. Static review of…

> Agent for `nvidia-ai-infrastructure-operations`. Review NVIDIA GPU infrastructure (DGX/HGX/MGX) per NCA-AIIO and NCP-AII — driver/firmware/CUDA alignment, BMC segmentation, ECC, persistence, and MIG host posture.

> Agent for `nvidia-ai-networking-fabric-review`. Review NVIDIA AI fabrics per NCP-AIN — Spectrum-X / InfiniBand topology, NCCL tuning, RoCEv2 lossless config, congestion control, tenant isolation.

> Agent for `nvidia-cuda-kernel-performance-review`. Static review of CUDA C/C++ kernels for memory coalescing, shared-memory bank conflicts, occupancy, register pressure, and stream concurrency against NVIDIA's official CUDA Programming and Best Practices Guides.

> Agent for `nvidia-maestro`. Classify the user's task across the NVIDIA stack (CUDA, TensorRT, Triton, NIM, NeMo, NGC, DCGM, GPU Operator, AI fabric), select the narrowest NVIDIA specialist or the right team of specialists from the catalog, and dispatch in parallel when the…

Use this skill when reviewing NVIDIA AI networking fabrics — Spectrum-X Ethernet or InfiniBand topology, NCCL collective tuning, RoCEv2 lossless DCQCN/PFC config, adaptive routing, congestion control, and east-west isolation between training jobs. Trigger when the user asks…

Use this skill when reviewing CUDA C/C++ kernel sources statically against NVIDIA's published performance guidance — global-memory coalescing, shared-memory bank conflicts, warp divergence, occupancy and register pressure, stream/event concurrency, kernel launch parameter…

Route NVIDIA tasks to the narrowest specialist or team of specialists from the NVIDIA agent catalog. Use when you do not already know the specialist. Not for direct NVIDIA answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks,…

Use this skill when reviewing NVIDIA NGC and NIM supply chain posture — NGC org and team boundaries, API key scope and rotation, NIM container cosign verification against NVIDIA's published identity, model card and weights provenance, AI Enterprise entitlement posture, and…

Use this skill when reviewing TensorRT or TensorRT-LLM deployment artifacts statically — ONNX/PyTorch export pipelines, precision selection (FP16/BF16/INT8/FP8/INT4), calibration cache integrity, dynamic shape profiles, custom plugin loading, engine cache and serialized engine…

Use this skill when reviewing Triton Inference Server deployments statically — `model_repository/` layout and `config.pbtxt` files, dynamic batching configuration, ensemble and BLS pipelines, custom backend (Python, C++, ONNX, OpenVINO, vLLM) trust posture, gRPC and HTTP…

> Agent for `dotnet-csharp-runtime-review`. Static review of C# language and runtime correctness — nullable reference types, async/await, cancellation, disposal, allocations on hot paths, LINQ misuse, and AOT/trimming hazards. Reads source only; never compiles or runs code.

> Agent for `dotnet-supply-chain-review`. Reviews .NET CI/CD and NuGet supply-chain integrity — SDK pinning, package version pinning and lock files, feed trust, fork-PR secret exposure, vulnerability scanning, and build reproducibility — by reading workflow and project…

> Agent for `nvidia-triton-inference-serving-review`. Static review of Triton Inference Server deployments against NVIDIA's Triton documentation — model repository layout, dynamic batching, ensemble pipelines, custom backend trust, gRPC/HTTP authentication, model encryption at…

.NET Maestro routing skill. Classify the user's .NET task, select the narrowest specialist agent or the right team of specialists from the .NET board, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Trigger when a user…