Multi-model AI command center: one Coordinator (Chrono — Claude) routes work to 5 Department Leads each running its own CLI (Codex/Claude/Gemini/Claude/Kimi) in dedicated tmux panes. Mailbox-mediated, subscription-billed (Max/ChatGPT/Gemini OAuth/Kimi), vibecoder-friendly.
npx skills add mtarcure/claude-vibe-squadMulti-model AI command center: one Coordinator (Chrono — Claude) routes work to 5 Department Leads each running its own CLI (Codex/Claude/Gemini/Claude/Kimi) in dedicated tmux panes. Mailbox-mediated, subscription-billed (Max/ChatGPT/Gemini OAuth/Kimi), vibecoder-friendly.
Lightweight owner-operated Linux EDR with AI agent skills — network, auth, process monitoring and defensive response
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Model software around the business domain using bounded contexts, aggregates, and ubiquitous language. Use when the user mentions "domain modeling", "bounded context", "aggregate root", "ubiquitous language", "anti-corruption layer", "context mapping", "domain events", or "strategic design". Also trigger when splitting a monolith into services, defining microservice boundaries, or aligning code structure with business processes. Covers entities vs value objects, domain events, and context mapping strategies. For architecture layers, see clean-architecture. For complexity, see software-design-philosophy.
An agent skill for incremental teaching, restatement, and quiz-based understanding checks.
Local Pokemon Red LLM-agent harness with live gameplay UI, structured traces, save states, replay, and turn-by-turn agent observability.
代码优化的子流程入口，处理"行为不变、结构变"的工作（结构 / 性能 / 可读性），按 scan → design → apply 分步执行每步人工放行。触发：用户说"优化一下 / 重构 / 重写 / 拆一下 / 性能不行 / 代码太长"且不夹带行为改动。不处理新需求 / bug / 跨模块架构重划。