frontend▌

Survey design framework grounded in product research best practices from nine leaders. \n \n Prioritize CSAT over NPS for better statistical properties and business outcome correlation; use 5-7 item scales \n Design single-variable questions only; avoid double-barreled phrasing that conflates multiple concepts \n Target customers 3-6 months post-signup when memory of the \"before\" state is fresh and relevant \n Use MaxDiff (Most/Least) methodology for feature prioritization rather than unlimite

Frameworks for designing organizational structures around speed versus coherence trade-offs. \n \n Contrasts centralized models (Apple: coherent user experience through central coordination) with decentralized models (Amazon: parallel execution through autonomous teams with minimal dependencies) \n Emphasizes functional structures over divisional ones to reduce management layers, restore startup speed, and keep leaders close to actual work \n Guides users through context discovery, trade-off ide

You are an expert full-stack web developer focused on producing clear, readable Next.js code. You always use the latest stable versions of Next.js 14, Supabase, TailwindCSS, and TypeScript, and you are familiar with the latest features and best practices. You carefully provide accurate, factual, thoughtful answers, and are a genius at reasoning.

Evaluate acquisition channels by unit economics, customer quality, and scalability to decide whether to scale, test, or kill. \n \n Assesses three core dimensions: unit economics (CAC, LTV, payback period, LTV:CAC ratio), customer quality (retention, churn, NRR by channel), and scalability (magic number, addressable volume, CAC trends) \n Delivers one of four recommendations: scale aggressively (LTV:CAC >3:1, payback <12mo), test and optimize (marginal economics with fixable problems), kill

Design methodology advisor combining Jobs-style product intuition with Rams-style functional minimalism. \n \n Diagnoses design problems through structured questioning before proposing solutions, uncovering true user needs beneath surface requests \n Delivers three solution tiers for every challenge: incremental optimization, structural redesign, and ideal long-term vision, with honest trade-off analysis \n Enforces pixel-level precision across spacing, typography, color, interaction states, and

Bridge design and engineering teams by clarifying roles, organizational placement, and hiring strategy. \n \n Defines design engineering as merging UX design with engineering to accelerate prototyping and production shipping, with scope varying from validation prototypes to production-ready code \n Emphasizes combining design sensibility with shipping ability rather than seeking unicorn-level expertise in both disciplines \n Guides organizational placement decisions, handoff friction diagnosis,

Team culture frameworks drawn from 138 product leaders at startups through Google and Airbnb. \n \n Focuses on articulating existing culture rather than inventing new values; helps identify behaviors in high performers and document what already works \n Emphasizes culture as a decentralized decision-making tool for remote and distributed teams, enabling sound choices when leadership isn't present \n Covers psychological safety, trust-building, and feedback loops as foundations for organizational

Structural design patterns and principles for reliable multi-step Claude Code workflow skills. \n \n Covers five workflow patterns (routing, sequential pipeline, linear progression, safety gate, task-driven) with numbered phases, entry/exit criteria, and decision trees for pattern selection \n Enforces progressive disclosure: SKILL.md stays under 500 lines with details split into references/ and workflows/ directories, one level deep \n Provides 20 anti-patterns with before/after fixes, covering

Practical guidance for building effective AI applications using techniques from 60 product leaders and practitioners. \n \n Covers core prompting patterns: few-shot examples, decomposition for complex tasks, self-criticism, and context placement for cache efficiency \n Emphasizes architecture decisions over prompt tuning: context engineering, RAG data preparation, layered model supervision, and specialized models for specific tasks \n Provides evaluation frameworks: mandatory evals with binary P

Next.js 16+ uses Turbopack by default for local development: an incremental bundler written in Rust that significantly speeds up dev startup and hot updates.