Comprehensive security auditing framework for LLM applications covering OWASP Top 10 for LLMs, threat modeling, penetration testing, and compliance with NIST AI RMF and ISO 42001Use when "security...
Don't die. Runway calculation, default alive vs. default dead, when to raise vs. cut, zero-based budgeting for startups. The math that keeps companies alive long enough to win. Burn rate is not...
Keeping codebases healthy, performant, and maintainable - refactoring, performance optimization, and technical debt managementUse when "refactor, optimize, performance, technical debt, cleanup,...
The YC meta-game distilled from 4000+ funded companies. Demo day prep, batch dynamics, investor updates, "launch now" mentality, talking to users obsessively. This is the playbook that turned...
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for...
Expert at building robust form experiences. Covers React Hook Form, Zod validation, server actions, progressive enhancement, error handling, and accessible form patterns. Use when "form,...
Acts as a Requirements Analyst to translate requests into specifications. Use when gathering user requirements, defining user stories, or creating technical specifications.
Paul Graham's founder mode. When to delegate vs. dive deep. Maintaining velocity as you scale. Avoiding "professional CEO" traps. The operating mode that built Apple, Tesla, and every YC unicorn. ...
Expert guidance on real-time communication patterns including WebSockets, Server-Sent Events (SSE), Socket.IO, and WebRTC. Covers connection management, reconnection strategies, scaling, and...
World-class Kubernetes operations - deployments, debugging, Helm charts, and the battle scars from managing clusters that serve millions of requestsUse when "kubernetes, k8s, kubectl, helm, pod,...
Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when "prompt engineering, system...
Acts as a Deployment & DevOps Agent for infrastructure and CI/CD. Use when managing Dockerfiles, K8s manifests, or GitHub Actions pipelines.
World-class DevOps engineering - cloud architecture, CI/CD pipelines, infrastructure as code, and the battle scars from keeping production running at 3amUse when "devops, infrastructure,...
Expert for codebase-wide code reviews. Use when auditing Pull Requests, refactoring complex logic, or enforcing architectural and security standards across the ecosystem.
Expert at designing clean, consistent, and developer-friendly APIs. Covers RESTful conventions, versioning strategies, error handling, pagination, rate limiting, and OpenAPI documentation. Designs...
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rotUse when "context window, token limit, context management, context engineering, long...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
World-class backend engineering - distributed systems, database architecture, API design, and the battle scars from scaling systems that handle millions of requestsUse when "backend, api,...
Security engineering that protects applications, data, and users from real-world threatsUse when "security, authentication, authorization, encryption, OWASP, vulnerability, XSS, SQL injection,...
Write high-quality technical blog posts with strong structure and clarity. Use when asked to write a blog post, technical article, tutorial, or guide about programming, software, APIs, tools, or...