Software Development Skills

AI and ML expert including PyTorch, LangChain, LLM integration, and scientific…

Builds enterprise React applications with Ant Design's comprehensive component library. Use when creating admin dashboards, data tables, complex forms, or enterprise UIs with consistent design language.

Deploys and hosts full-stack web applications on AWS Amplify with SSR support, CI/CD, and backend services. Use when deploying Next.js apps to AWS, setting up Amplify hosting, or configuring Amplify backends.

Builds accessible React applications with Chakra UI v3 components, tokens, and recipes. Use when creating styled component systems, theming, or accessible form controls.

Systematic codebase exploration and architecture mapping.

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.

Docker orchestration and CI/CD for IntelliFill. Use when configuring containers, writing workflows, or setting up environments.

Configures esbuild for extremely fast JavaScript/TypeScript bundling with plugins, code splitting, and build optimization. Use when building libraries, rapid prototyping, or optimizing build performance.

Express.js middleware patterns, routing, error handling, security, and production best practices.

Enforces the use of full file paths when referencing, editing, or creating files in the project. This rule ensures consistency and accuracy in file operations across the entire project.

Generate a structured PR description from the diff. Fetches the diff, analyzes changes, and optionally applies the description.

Run local Go health checks (tests, coverage, lint) in Go repositories that contain go.mod/go.sum. Use when the user asks to run or interpret local Go test/coverage/lint workflows using tools like lazygotest, gocovsh, tparse, and golangci-lint. Do not use for Rust or non-Go projects.

Publish CLIs/TUIs to Homebrew via a personal tap. Use when asked to create or manage a Homebrew tap repo, generate or update formulae, compute sha256, test installs, or ship new releases for Go, Rust, Node/TypeScript, Python, or prebuilt binaries.

Write testable product hypotheses with clear success metrics, baselines, targets, and timeframes. Produces a structured hypothesis statement, supporting evidence, a validation plan with method and sample size, and a decision framework for what to do if validated or invalidated. Use when validating product assumptions, before running experiments, when proposing new features, or when shifting from opinion-based to evidence-based decision making.

Builds LLM-powered applications with LangChain.js for chat, agents, and RAG. Use when creating AI applications with chains, memory, tools, and retrieval-augmented generation in JavaScript.

LLVM IR and pass pipeline skill. Use when working directly with LLVM Intermediate Representation (IR), running opt passes, generating IR with llc, inspecting or writing LLVM IR for custom passes, or understanding how the LLVM backend lowers IR to assembly. Activates on queries about LLVM IR, opt, llc, llvm-dis, LLVM passes, IR transformations, or building LLVM-based tools.

Use when working with Apple's MLX or MLX-LM: fact-checking current behavior against upstream source/runtime, patching MLX-based repos, porting PyTorch/JAX code to MLX, validating lazy evaluation, indexing, compilation, streams, channels-last layouts, Metal kernels, quantization, caches, and local MLX model loading or generation on Apple silicon.

Use when the user asks about a specific project or all projects — e.g.

RESTful API design principles, versioning, pagination, HATEOAS, and documentation.