Development

Authoritative reference for the Claude API and Anthropic SDKs: model IDs, pricing, thinking/effort params, streaming, tool use, caching, managed agents, and model migration.

Read, edit, create, and fix Excel/CSV files — formulas, formatting, charts, and clean financial models with zero formula errors.

Generate distinctive, production-grade frontend UI that avoids generic AI aesthetics — pages, components, dashboards, and landing pages.

Build high-quality MCP (Model Context Protocol) servers in Python (FastMCP) or Node/TypeScript that let LLMs use external services through well-designed tools.

End-to-end workflow for authoring, testing, benchmarking, and optimizing agent skills, including eval runs, a review viewer, and a description-triggering optimizer.

Review UI code against Vercel's Web Interface Guidelines — accessibility, UX, and design best practices — with terse file:line findings.

Vercel Engineering's 70 React/Next.js performance rules across 8 priority categories—waterfalls, bundle size, server-side, re-renders—for writing, reviewing, and refactoring code.

Scaffolds and bundles elaborate React + TypeScript + Tailwind + shadcn/ui artifacts into one self-contained HTML file for claude.ai, with state, routing, and prebuilt components.

Deploys apps to Vercel, defaulting to preview, by detecting project/git/CLI state and choosing git-push, vercel deploy, link-first, or a no-auth sandbox fallback.

Domain knowledge for building videos in React with Remotion—frame-based animation via useCurrentFrame/interpolate, sequencing, assets, audio, captions, and rendering.

Produces a production-ready AKS cluster configuration, separating hard-to-change Day-0 choices (networking, API server) from Day-1 features across security, scaling, and cost.

Systematically triages Azure production incidents across App Service, Container Apps, Functions, AKS, and messaging using resource health, logs, and AppLens.

Tests and debugs local web apps with native Python Playwright scripts and a server-lifecycle helper, using a reconnaissance-then-action pattern and headless Chromium.

A fast Rust browser-automation CLI for AI agents using Chrome via CDP with accessibility-tree snapshots; a discovery stub that loads live workflows from the CLI itself.

Prepares apps for Azure deployment by writing a mandatory deployment plan, then generating Bicep/Terraform, azure.yaml, and Dockerfiles before handing off to validate and deploy.

Assesses existing AKS clusters or local manifests against AKS Automatic safeguards, classifying incompatibilities and generating fix diffs without ever mutating the cluster.

React Native and Expo best practices across list performance, Reanimated animations, navigation, UI patterns, and monorepo config, organized by priority and impact.

Runs an observability-first Vercel cost and performance audit, collecting production metrics before investigating metric-backed candidates and producing ranked, file-grounded recommendations.

Assesses reliability of Azure Functions and App Service apps for zone redundancy, ZRS storage, health probes, and multi-region failover, then drives staged CLI or IaC remediation.

Turns a workload description into an enterprise Azure topology (landing zone, hub-spoke, DR) and generates validated Bicep or Terraform aligned to the Well-Architected Framework.

Implements native-feeling animations with React's View Transition API—shared elements, Suspense reveals, list reorder, directional navigation—without third-party animation libraries.

A framework-agnostic write-path discipline: the cancel-snapshot-patch-rollback-invalidate optimistic lifecycle, once-per-intent idempotency keys, and multi-cache coherence.

A framework-agnostic field-side observability system: one typed event taxonomy, best-effort non-blocking provider fan-out, real-user Web Vitals, error reporting, and consent gating.

A portable Lighthouse CI performance gate that blocks PRs unless the production build meets Core Web Vitals budgets and category score floors, with median-of-N runs.