Design e Frontend

Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

Full content production pipeline — takes a topic from blank page to published-ready piece. Use when you need to execute content: write a blog post, article, or guide end-to-end. Triggers: 'write a post about', 'draft an article', 'create content for', 'help me write', 'I need a blog post'. NOT for content strategy or calendar planning (use content-strategy). NOT for repurposing existing content (u

Write a cross-topic synthesis note under vault/wiki/_synthesis/. Trigger when the user asks to "compare X and Y", "find themes across these pages", "identify contradictions", "do a gap analysis", "build a timeline of Z", or invokes /llm-wiki-stack:llm-wiki-synthesize directly. Also used as the follow-up when /llm-wiki-stack:llm-wiki-query offers to file an answer as a synthesis.

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

/cs:onboard — Founder interview that populates ~/.claude/company-context.md. The first command to run when starting with c-level-agents.

Generate modern UI components — cards, forms, navigation, modals, tables, hero sections, footers, and pricing tables. 2026 glassmorphism design with Tailwind CSS. Copy-paste ready.

Use when the user asks to design multi-agent systems, create agent architectures, define agent communication patterns, or build autonomous agent workflows.

Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript support, schema validation, safe evolution. Use when exposing an existing API as an MCP server, building tool integrations for Claude or Codex or Cursor, or scaffolding an MCP project from scratch.

在現有 domain stack 中新增單一 skill。不是重建整個 repo，是加一個新的。 Trigger: 用戶說「加一個 skill」、「我需要一個做 X 的 skill」、「新增」。 Do NOT use when: 要建整個 domain stack（用 /domain-build）。 Do NOT use when: 要改現有 skill（用 /skill-edit）。 Do NOT use when: 要建工具型 skill（用 /tool-builder）。 上游：用戶需求 + 現有 skill map。 下游：/skill-check design。 產出：新的 SKILL.md + references/（如需要）。

Build realistic trade show budgets and ROI projections with industry cost benchmarks.

Designer de Sistemas de Agentes de IA para 0xagentprivacy. Especialista em arquitetura TEE de agente duplo, aplicação de matriz de separação, design de ciclo de vida de agentes, arquitetura Oracle, implantação multi-chain (NEAR/Zcash/Ethereum) e orientação tetraédrica. Oferece a visão especialista mais ampla para a construção de sistemas, com 20 habilidades.

Este é um estúdio de design frontend que segue rigorosamente um contrato visual DESIGN.md existente ou, se não houver e for solicitado, guia o usuário por um processo de definição de estilo, culminando em um novo DESIGN.md. Todas as tarefas de frontend envolvem pré-visualizações interativas no navegador para confirmação do usuário, evitando a exposição direta do código.