Development

Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.

You bring the third dimension to the web. You know when 3D enhances and when it's just showing off. You balance visual impact with performance. You make 3D accessible to users who've never touched a 3D app. You create moments of wonder without sacrificing usability.

Use when adding a new documentation page to the AgentOps site — creating MDX content pages with code examples, Demo components, CodeBlock snippets, framework cards, and navigation updates. Triggers on requests like "add a page for X", "create content for Y", "new topic page", or expanding stub pages into full content.

Enforces C# + LanguageExt functional/ROP style, type discipline, runtime-record effects, Scrutor composition, and module organization standards. Use when writing, editing, reviewing, refactoring, or debugging .cs modules, implementing domain models, sealed DU hierarchies, Eff/Fin/Validation pipelines, or configuring .csproj, analyzers, or DI.

Test WebSocket channels for CSWSH, smuggling, injection, and auth flaws (wsrepl, ws-harness, Burp). Use when an app uses real-time channels, chat, notifications, or WS-backed APIs.

Build real-time WebSocket/Socket.IO systems — auth at the handshake, rooms/namespaces, presence, reconnection, Redis pub/sub scaling. Use for bidirectional messaging, live updates, chat, or notifications.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs

Animate React route/page changes, shared elements, and enter/exit/reorder with the View Transition API (`<ViewTransition>`); use for view transitions in React or Next.js.

UI/UX design intelligence — pick styles, color palettes, font pairings, layout & UX patterns across 10 stacks. Use when designing, building, reviewing, or restyling a web/mobile interface.

Design test strategies and test plans. Trigger with "how should we test", "test strategy for", "write tests for", "test plan", "what tests do we need", or when the user needs help with testing approaches, coverage, or test architecture.

Design scalable distributed systems — load balancing, caching, database scaling, message queues, capacity estimation. Use for "system design", "scale this", "high availability", "rate limiter", or choosing microservices vs monolith.

Universal SQL query tuning across MySQL, PostgreSQL, SQL Server, and Oracle — execution plans, index strategy, pagination, batch operations. Use whenever a SQL query is slow or needs optimization.

Default OpenSpec change workflow — scaffold a change through proposal → specs → design → tasks, apply it, then archive once merged. Use to start a change, write a proposal/spec/design/tasks, implement a tasks checklist, or archive a merged change.

Build, run, test, and drive the delivery-chain Claude Code plugin. Use when asked to run delivery-chain, run its tests, exercise the agent-memory hook sidecar, or verify the plugin's runtime works on this machine.

Multi-reviewer code-review orchestrator — dispatches the three quality reviewers (sr/sa/qa) and routes in domain specialists by what the diff touches. Use to review code, a diff/PR/branch/commit, run a quality gate, or check changes before committing.

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Redis production hardening — authentication (requirepass/ACL users), TLS, least-privilege ACLs, network restriction (bind, protected-mode, firewall), and disabling dangerous commands. Use when deploying, locking down, or auditing a Redis instance.

Redis Query Engine (RQE) — FT.CREATE schema design, field-type choice, DIALECT 2 syntax, efficient FT.SEARCH/FT.AGGREGATE, zero-downtime index swaps. Use when creating, querying, or optimizing search indexes on Hash or JSON documents.

Core Redis modeling — choose the right data structure and consistent colon-separated key names. Use when designing a Redis data model, caching, building counters, leaderboards, or sessions, choosing Hash vs JSON, or reviewing key naming.

Guidelines for using React Query for data fetching, caching, and server state synchronization in React applications

React performance: unnecessary re-renders, memoization (React.memo/useMemo/useCallback), React Compiler, Context, concurrent features, code splitting, and Core Web Vitals.

React/Next.js best-practices reviewer for TSX/JSX. Triggers when writing or reviewing React components to check structure, hooks, accessibility, performance, and TypeScript patterns.

Race condition and TOCTOU testing for web apps. Use when testing one-time operations, concurrent HTTP abuse, rate-limit bypass, Turbo Intruder gates, HTTP/2 single-packet attacks, and CWE-362-style synchronization gaps.

Professional React state-machine patterns. Use when implementing complex state logic, reducers, multi-step forms, async flows, or any component coordinating multiple states.