Explorar skills

Squash-merge a worktree branch into the target branch with a structured commit message. Use after audit consensus and retrospective completion.

Review and optimize the MeMesh memory database. Analyzes health score, finds stale/conflicting/redundant memories, shows work patterns, and suggests cleanup actions. Use when asked to "review memories", "check memory health", "clean up knowledge", or "what's in my memory".

Use when designing, implementing, or reviewing TypeScript type contracts, advanced generics, discriminated unions, type guards, API DTOs, component props, public utility types, or type-level regressions in frontend projects. Prefer code review for broad PR review; Chinese triggers include TypeScript 类型安全, 类型建模, 泛型, 判别联合, 类型收窄.

Use when optimizing or reviewing large lists, virtual scrolling, windowing, react-window, TanStack Virtual, variable-height rows, dynamic measurement, infinite scroll, grid virtualization, or scroll performance; Chinese triggers include 虚拟列表, 大列表优化, 滚动性能.

Guide for writing evidence packages for the consensus-loop watch file. Use when preparing code review submissions, structuring feedback evidence, or addressing audit rejections.

Use this skill when building Model Context Protocol (MCP) servers on Cloudflare Workers. This skill should be used when deploying remote MCP servers with TypeScript, implementing OAuth authentication (GitHub, Google, Azure, etc.), using Durable Objects for stateful MCP servers, implementing WebSocket hibernation for cost optimization, or configuring dual transport methods (SSE + Streamable HTTP).

Use this skill when building MCP (Model Context Protocol) servers with FastMCP in Python. FastMCP is a framework for creating servers that expose tools, resources, and prompts to LLMs like Claude. The skill covers server creation, tool/resource definitions, storage backends (memory/disk/Redis/DynamoDB), server lifespans, middleware system (8 built-in types), server composition (import/mount), OAut

Run all done-criteria checks (CQ/T/CC/CL/S/I/FV/CV) and produce a pass/fail verification report. Use after implementing code, before submitting evidence to the quorum audit.

Search for code patterns in decompiled output using Weggli semantic matching. Use when finding vulnerable code constructs like unchecked memcpy, buffer operations, or specific function call patterns in pseudocode.

Use when implementing or reviewing TanStack Query/React Query server-state flows: typed queries, query keys, caching, invalidation, mutations, optimistic updates, infinite queries, prefetch, SSR hydration, or API-layer integration. Do not use for local UI state or Service Worker caching; Chinese triggers include 数据获取, 缓存, 乐观更新.

Use when adding or reviewing Progressive Web App capabilities such as installability, manifest metadata, Service Worker registration, Workbox caching, offline fallback, app update prompts, maskable icons, or iOS PWA compatibility. Do not use for general API caching or non-installable performance tuning; Chinese triggers include PWA, 离线, Service Worker.

Use when moving expensive browser work off the main thread with Web Workers, SharedWorker, worker pools, Comlink, transferable objects, Vite/Webpack worker integration, or UI responsiveness fixes. Do not use for lightweight synchronous work or DOM manipulation; Chinese triggers include Web Worker, 后台线程, 主线程阻塞.