Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill for all Alibaba Cloud 云效 (Yunxiao) DevOps operations on codeup.aliyun.com. Invoke IMMEDIATELY when the user wants to: create or manage Merge Requests (MR) on codeup, update work items/tasks in 云效, query MR lists or task status, create version tags via 云效 API, or push code to a codeup remote. Key triggers: 创建 MR, 提交评审, 云效, yunxiao, codeup, 更新任务, 查看任务, 发布版本, 打 tag. Handles both MCP tool mode and aliyun CLI fallback. Do NOT use for GitHub PRs (use git-workflow), Jira, GitLab, or non-Alibaba platforms.
FMC conventions for Zustand v5 in React: file naming, custom-hook-only exports, atomic selectors, actions namespace, small focused stores. Use when adding or reviewing client global state, or debugging unnecessary re-renders and SSR/persist hydration issues. Not for server/async data (TanStack Query) or URL state (router search params, or nuqs in Vite apps without TanStack Router). For API details, middleware, slices, and migration, use the official llms.txt index below.
Mount tRPC as a Fastify plugin with fastifyTRPCPlugin from @trpc/server/adapters/fastify. Configure prefix, trpcOptions (router, createContext, onError). Enable WebSocket subscriptions with useWSS and @fastify/websocket. Set routerOptions.maxParamLength for batch requests. Requires Fastify v5+. FastifyTRPCPluginOptions for type-safe onError. CreateFastifyContextOptions provides req, res.
Mount tRPC on Node.js built-in HTTP server with createHTTPServer() from @trpc/server/adapters/standalone, createHTTPHandler() for custom http.createServer, createHTTP2Handler() for HTTP/2 with TLS. Configure basePath to slice URL prefix, CORS via the cors npm package passed as middleware option. CreateHTTPContextOptions provides req and res for context creation.
Use when admin/CMS/back-office screens need to be built or specified after admin-ui-orchestrator defines roles, permissions, workflows, and safety gates. Covers tables, forms, editors, moderation queues, dashboards, CRUD surfaces, and state coverage without production destructive actions.
Intercept the AG2 agent loop with `BaseMiddleware` — wrap full turns (`on_turn`), each LLM call (`on_llm_call`), each tool execution (`on_tool_execution`), or each human-input request (`on_human_input`). Use for retry, logging, history trimming, request mutation, tool auditing, guardrails, or rate limiting. Built-ins: `LoggingMiddleware`, `RetryMiddleware`, `HistoryLimiter`, `TokenLimiter`, `TelemetryMiddleware` (see `ag2-telemetry`). For per-tool hooks see also `ag2-add-custom-tool` tool-middleware section.
Clarify, create, review or change product, service and office workflow requirements, PRDs and interactive prototypes. Use for vague goals, process improvements, spreadsheet/form rules, small UI edits and changes to existing systems, even without the word requirement. 中文:产品、服务及办公流程的需求判断、深挖澄清、PRD、原型、变更与验收;一句话想法、表单/表格规则和微小改动也适用。明确的纯翻译、排版、抄录或既定步骤执行由对应工具直接处理。
Use this skill for AI in WeChat Mini Programs via wx.cloud.extend.AI. Covers generateText and streamText with callbacks (onText, onEvent, onFinish); streamText needs a data wrapper, while generateText returns the raw response. Models are accessed via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed group), or custom-*; the model id goes in the data wrapper’s `model` field. MUST run the two-step preflight before coding — see body. NOT for browser/Web (use ai-model-web), Node.js backends (use ai-model-nodejs), or image generation (use ai-model-nodejs).
Use when building or modifying websites with AI Staff via Alibaba Cloud OpenAPI. Supports conversation creation, async chat with requirement collection, PRD generation, code generation, and incremental SSE event polling.
Analyze an unfamiliar repository and explain what it does, how it runs, what architectural choices define it, where the important code lives, and what deserves deeper inspection next. Use this whenever a user has just cloned a repo, wants onboarding help, asks for a repo walkthrough, or needs a reliable first-pass architecture analysis.
Recommended architecture reference for Android app development (Kotlin). Covers Jetpack, androidx, UI layer, Domain layer, Data layer, state holder, UDF, SSOT, offline-first, modularization, ViewModel, viewModelScope, SavedStateHandle, Lifecycle, repeatOnLifecycle, collectAsStateWithLifecycle, LiveData, dependency injection with Hilt, and pagination with Paging 3.
**WORKFLOW SKILL** - Safely migrates eligible Aspire 13.6+ AppHosts from legacy ProjectResource APIs to experimental DotnetProjectResource APIs after a per-resource assessment and explicit approval of exact edits. USE FOR: assess or migrate existing AddProject, addProject, AddCSharpApp, addCSharpApp, or AddBlazorGateway resources to Project v2; migrate ProjectResource to DotnetProjectResource; clean up the resulting obsolete AppHost ProjectReference edges. DO NOT USE FOR: upgrading Aspire versions, creating/wiring a new AppHost, Azure Functions migration, generic source modernization, ordinary C# resource wiring or adding a new AddProject resource (use aspireify), publishing, or build/lifecycle diagnostics. INVOKES: Aspire docs/API lookup, aspire add/restore/start/wait, AppHost and package edits. FOR SINGLE OPERATIONS: Assess first; never edit from a generic migration request alone
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
Baidu Map Open Platform CLI. For anything involving Baidu Map development, HTML/demo, WebAPI/BMapGL, AK/personalized map styles/quota, trigger this skill first and complete the environment and AK flow before consulting docs or writing code. Covers: CLI installation, Skills/MCP configuration, account and AK, personalized map styles, place/route/address resolution, and more; it also supports Baidu Map Agent Plan (no developer account required, providing map tools that are LLM-friendly, with semantic AI search, semantic AI route planning, geocoding and reverse geocoding, and weather queries).
Build a layered, LLM-friendly documentation system for a project. For existing projects: scan the project structure → classify the architecture → generate the CLAUDE.md main index → base module documentation → business module API/data model/pitfall documentation → configuration documentation → git changelog (with risk assessment + rollback guide) → cross-validation. For new projects: parse the PRD → design the architecture according to scaffolding standards → break requirements down into development tasks → merge with code standards to generate the CLAUDE.md development guide → module-level API design + data models + development checklist. Use when the user needs to create AI programming documentation for a project, establish a project index, sort out code, plan a new project, or mentions llm.txt/CLAUDE.md.
Provides context and best practices for building Fintoc integrations. Use when working with the Fintoc API, CLI, SDKs, or MCP servers — including writing integration code, debugging API errors, implementing payments or transfers, setting up webhooks, or exploring Fintoc documentation.
Bun runtime, package manager, bundler, and test runner. Use when running scripts with bun, managing packages, serving HTTP with Bun.serve, querying databases with Bun.sql/bun:sqlite/Bun.redis, shell scripting with $, using S3/file I/O, writing tests with bun:test, bundling or compiling to executable, or using any Bun-specific API (spawn, glob, semver, FFI, workers, plugins, HTMLRewriter).
Automatic compliance audit against the Hexagone domain business rules (docs/domain/). Analyzes the code of a screen and the APIs it calls, matches them against documented invariants, transitions and validations, and produces a structured report with citations. Report-only mode — no automatic modification of business rules in a healthcare context. Use when the user wants to verify the business compliance of a screen, audit business rules, validate invariants/transitions/validations, or mentions « conformité métier » / « business compliance ».
Prepares CanAI-friendly static sites as one self-contained HTML file per page: semantic HTML5, Tailwind utility classes, vanilla JS or Alpine.js for interactivity, Lucide icon markup. Use when the user asks to prepare HTML for CanAI, single-html pages, image/mockup to HTML, screenshot to HTML, SPA or PWA to static pages, static site export, or "canai-prepare". Triggers on: "canai-prepare", "prepare html", "image to html", "mockup to html", "screenshot to html", "spa to html", "pwa to html", "static html", "single html", "per-page html", "convert design to html".
Integrate a new blockchain as a second-class citizen in ShapeShift Web. HDWallet packages live in the monorepo under packages/hdwallet-*. Covers everything from HDWallet native/Ledger support to Web chain adapter, asset generation, and feature flags. Activates when user wants to add basic support for a new blockchain.
Manage dotfiles with chezmoi — the source-state dotfile manager that uses filename attributes (`dot_`, `private_`, `encrypted_`, `run_once_`), Go templates, and password-manager integration to keep one set of dotfiles working across many machines. Use when the user says "set up dotfiles", "manage my dotfiles", "bootstrap a new machine", "chezmoi", "encrypt my SSH key in dotfiles", "template dotfiles per OS", "add secrets to dotfiles", "what should be in my .chezmoi.toml.tmpl", or asks how to share configs across macOS / Linux / servers. Also trigger when the user is staring at a fresh machine and wants the one-liner that gets them home, or when they're about to commit something sensitive into a dotfiles repo. Do NOT use for stow / yadm / rcm or other dotfile managers, generic git repo setup, or password-manager setup unrelated to dotfiles.
Decide where code lives and what each module hides—the directory tree, module and package boundaries, a module's entry point, and when to split or merge a file. Use when starting a project or directory tree, placing a new file, class or function, grouping code into modules or packages, splitting or merging a module or file, naming directories or files, or auditing a codebase's structure
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
