Skills

Designs caching strategies across the stack to cut latency and load. Chooses cache layers (browser, CDN, application, database), picks patterns (cache-aside, read-through, write-through, write-behind), sets TTLs and eviction policies, and plans invalidation to avoid staleness and stampedes. Produces a layered plan with keys, TTLs, and invalidation rules.

Designs routing layers that dispatch requests across multiple LLMs based on task type, difficulty, latency, cost, and reliability. Covers classifier-based and heuristic routing, fallbacks and retries across providers, quality scoring, and A/B evaluation of routing policies. Helps teams get frontier quality where it matters and cheap models everywhere else.

Implements secure OAuth 2.0 and OpenID Connect flows including authorization code with PKCE, client credentials, and device code grants. Generates token exchange logic, refresh handling, state/nonce validation, and secure token storage. Flags common pitfalls like implicit flow usage, missing PKCE, and insecure redirect URI handling.

Analyzes LLM usage and reduces inference cost without sacrificing quality. Covers prompt compression, context trimming, caching (prompt and semantic), model routing by task difficulty, batching, structured output to cut retries, and token accounting. Produces a concrete plan with estimated savings and quality guardrails.

Modernizes legacy codebases incrementally and safely. Establishes characterization tests to lock in current behavior, then applies the strangler-fig pattern, dependency updates, and idiomatic refactors in small verifiable steps, producing a migration plan that avoids big-bang rewrites.

Designs and implements real-time services using WebSockets and Server-Sent Events. Covers connection lifecycle, heartbeats, reconnection with backoff, room/channel fan-out, backpressure, authentication on upgrade, and horizontal scaling with a pub/sub backplane. Produces production patterns for chat, live dashboards, collaborative editing, and streaming updates.

Designs multi-agent systems where a coordinator delegates sub-tasks to specialist agents, verifies intermediate results, and synthesizes a final answer. Covers agent role definition, routing and delegation strategy, shared memory and message passing, verification loops, cost and latency budgeting, and failure handling across frameworks like LangGraph, CrewAI, or a custom orchestrator.

Helps architect scalable distributed systems by analyzing requirements and producing high-level architecture diagrams, component breakdowns, data flow descriptions, and technology recommendations. Covers load balancing, caching strategies, database selection, message queues, and failure handling patterns.

Designs and scaffolds AI agent architectures including tool definitions, system prompts, memory strategies, and orchestration logic. Supports multi-agent workflows, ReAct patterns, function calling schemas, and MCP server configurations. Helps structure agents that are reliable, observable, and easy to debug.

Identifies and resolves performance bottlenecks in code and systems. Covers algorithmic complexity analysis, memory optimization, caching strategies, database query tuning, and frontend performance (Core Web Vitals). Follows a measure-first approach.

Translates code between programming languages while preserving logic, idioms, and best practices of the target language. Handles differences in type systems, error handling, concurrency models, and standard library APIs. Produces idiomatic target code, not line-by-line transliteration.

Guides systematic code refactoring while preserving exact behavior. Identifies code smells, suggests appropriate refactoring patterns, and executes transformations incrementally with verification at each step. Follows Chesterton's Fence principle — understands why code exists before changing it.

Designs, optimizes, and iterates on prompts for LLM applications. Covers system prompt design, few-shot examples, chain-of-thought reasoning, output formatting, and prompt testing strategies. Helps build reliable AI-powered features.

Designs RESTful and GraphQL APIs following contract-first principles. Covers endpoint structure, request/response schemas, error handling, versioning, pagination, authentication, and rate limiting. Produces OpenAPI/Swagger specifications and implementation scaffolding.