Frontend

「Clarity / Deference / Depth」と、1プロダクト=1焦点の構成・大きいタイポ・余白・最小CTAを抽象化して、Web UI設計に適用する。

Write secure, performant database queries using parameterization, proper indexing, and optimization techniques. When creating or modifying database query logic, data access layers, or repository files. When working on files that interact with databases using SQL, ORMs, or query builders. When implementing SELECT queries, joins, transactions, or data fetching logic. When optimizing queries to prevent N+1 problems, using eager loading, or implementing query caching. When writing parameterized queries to prevent SQL injection vulnerabilities.

Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.

Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues. Use when /popkit:next detects research branches or when manually processing research from mobile sessions. Do NOT use for regular feature branches - only for branches matching claude/research-* or containing research documentation.

Expert Next.js - App Router, Server Components, Server Actions, data fetching, rendering strategies, optimization et déploiement

React/Next.js best practices for modern, performant applications.

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Work on Rust crates in packages/rust_viterbo. Use for crate layout, commands (fmt/clippy/test/bench), and coding conventions.

Forensic, high-fidelity context handover for seamless continuation in a new chat. Produces a single Markdown transfer artifact plus reusable templates, preserving decisions, requirements, non-negotiables, and open loops without truncation by judgment. Not for code continuation unless explicitly stated.

Use Open Props CSS custom properties for consistent design tokens. Use when setting up design systems, choosing spacing/color values, or wanting battle-tested CSS variables without heavy dependencies.

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns

Memory preservation for Claude Code sessions. Use when approaching token limits, needing to /reset or /compact, switching between complex tasks, or preserving critical session state before context loss. Creates comprehensive memory dumps at /tmp/total-recall containing current state, decisions, artifacts, and next steps for seamless context restoration.

TanStack Start specialist for file-based routing, SSR, and server functions with React

Evaluates Catz Android coding challenge submissions against SWORD Health requirements. Use when reviewing or assessing this coding challenge. Produces a structured markdown report with seniority level assessment (Junior/Mid/Senior/Staff) and confidence rating, covering requirements compliance, architecture, code quality, testing, and documentation.

Apply YAGNI (You Aren't Gonna Need It) principle when evaluating feature requests, reviewing speculative code, or preventing over-engineering. Use when assessing whether to build functionality now vs later.

Implements CSS-in-JS styling with styled-components using tagged template literals, theming, and dynamic props. Use when wanting component-scoped CSS-in-JS, dynamic styling based on props, or theming support.

Use when researching AI agents, LLMs, hosting solutions, OCR technologies, video generation models, or evaluating technology stacks. Apply when user asks to research, compare, evaluate, or investigate technologies, frameworks, models, or tools. Use proactively when technical decisions require research backing.

Use when implementing Weavr UI components for secure payment flows, authentication (password/passcode), KYC/KYB verification, or card display

Use PROACTIVELY when developing Claude Code hooks to implement content-based deduplication and prevent duplicate insight storage across sessions

Adds BetterAuth authentication to Apso backends. Handles entity setup, code generation, auto-fixes, and verification. Triggers when user needs to add authentication, setup auth, or integrate BetterAuth.