Publish, review, organize, and share work with Artifact Server, or operate an installation when the user explicitly requests administrator work. Use for Artifact Server links, files or sites to upload, project, artifact, version, tag, sharing, or comment work, connection help, and explicit install, deploy, upgrade, backup, restore, or repair requests. Do not use for unrelated package publishing or for building software that the user did not ask to store in Artifact Server.
1842mo agoReviewMountCreate a free account to mount
Review Model Context Protocol (MCP) servers and client configurations — server provenance and pinning, tool description poisoning, authorization (OAuth 2.1 per the MCP spec, no token passthrough), confused-deputy risks, local server sandboxing, secret handling, and tool-call logging. Use when installing or approving an MCP server, building one, or assessing MCP use in coding assistants and agents.
Use when a fleet service ships its own Spring AI MCP server - explains how to discover those servers from the spring-fleet config and federate them alongside the spring-fleet MCP tools so the agent has one unified tool surface across the fleet.
Stand up a Guile project with a socket REPL an agent can drive - guile3 --debug --listen on a per-project port, with a logging proxy on PORT+1. Use when starting or resuming work on a Guile/Scheme project, when you need to evaluate code rather than only read it, or when a claim about Guile behaviour needs checking against a running interpreter.
Ktor server architecture for Kotlin backends - project structure, routing, plugins, request/response handling, serialization, error handling, service layer, repository pattern, database access with Exposed, configuration, and testing. Use this skill whenever creating a Ktor server, adding a route, configuring a plugin, setting up Exposed ORM, handling errors, writing service or repository classes, or testing Ktor endpoints. Trigger on phrases like "Ktor server", "Ktor route", "routing { }", "install plugin", "Exposed", "testApplication", "ApplicationCall", "call.respond", "call.receive", "StatusPages", "embeddedServer", or "Ktor backend".
Search, analyze, and author Elastic documentation using the remote MCP server. Use this when the user asks about Elastic product documentation, features, or APIs; wants to find, read, or verify existing docs pages; is writing or editing documentation; mentions cross-links between repos; asks about documentation structure, coherence, or consistency; wants to generate templates following Elastic content type guidelines; or references elastic.co/docs URLs or Elastic product names.
2612d agoReviewMountCreate a free account to mount
Help with using the ServerBox app itself — adding a server over SSH or through the ServerBox Monitor, why a button or feature is missing for a server, installing and configuring the Monitor on a server (password, TLS, alert rules), home-screen widgets, push alerts and the watch app, backups, the terminal, and the Agent's own settings (providers, tools, MCP servers, skills). Use it whenever the user asks how to do something in ServerBox, why something in the app is unavailable or failing, or wants the Monitor set up — including questions that never name the app, such as "why is there no terminal button", "how do I get alerts when CPU is high", or "can I see this on my watch".
Use when building Model Context Protocol (MCP) servers in .NET, configuring tools, transports (SSE/stdio), JSON serialization for AOT, or testing MCP endpoints
1999d agoReviewMountCreate a free account to mount
Architecture and craft doctrine for @delorenj/mcp-server-trello — how the server should be BUILT, as distinct from what it should do. Use when judging a PR or change for architecture/craft (not product value); deciding whether to extract an engine, collapse a duplication, or earn a design pattern; auditing for cross-cutting-concern gaps (authorization, retry, error-mapping, response shaping), silent-wrong bugs, dead quality gates, or resource leaks. Encodes the maintainer's taste — layered abstraction, Gang-of-Four patterns, hierarchical modular components, thoughtful reuse, regression-resistance, high observability — as enforceable gates, so good engineering is the path of least resistance ("passive habit injection"). Triggers: "is this well-architected", "should I extract this", "refactor", "DRY", "design pattern", "separation of concerns", "cross-cutting concern", "observability", "this keeps breaking", "craft review". Do NOT use for: what tools should exist / the moat (mcp-server-trello-product-doctrine); the release/publish procedure (mcp-server-trello-release); growth or distribution (mcp-server-trello-growth).
4463mo agoReviewMountCreate a free account to mount
This skill should be used when the user wants to "Model Context Protocol", "MCP server", "MCP client", "standardized tool integration", "JSON-RPC agent tools", "LLM tool protocol", "connect agents to external tools", "MCP primitives", "FastMCP", "ADK MCPToolset", "plug-and-play agent tools", "MCP integration", "tool server for agents", "MCP tools", "agent plugin system", "MCP setup", "model context protocol integration", or build agents that use the standardized MCP protocol for tool and resource integration. Also responds to Korean: "모델 컨텍스트 프로토콜", "MCP 서버", "MCP 클라이언트", "표준화된 도구 통합", "플러그 앤 플레이 에이전트 도구", "ADK MCP 툴셋", "MCP 구성", "MCP 설정", "MCP 써보고 싶어", "MCP 툴 연결", "MCP 서버 만들어줘", "도구 표준화해줘", "플러그인 에이전트". Also responds to Japanese: "モデルコンテキストプロトコル", "MCPサーバー", "MCPクライアント", "標準化ツール統合", "MCPの設定", "MCPを使いたい", "MCP構成", "エージェントのプラグインシステム", "ツールサーバー", "MCPツール連携" Also responds to Chinese: "模型上下文协议", "MCP服务器", "MCP客户端", "标准化工具集成", "MCP配置", "想用MCP", "MCP构建", "智能体插件系统", "工具服务器", "MCP工具集成".. Apply this skill to design or implement the Model Context Protocol (MCP) agentic design pattern.
Assess whether a web application and its build and runtime plan fit a low-cost Linux VPS or Alibaba Cloud ECS before purchase, implementation, or deployment. Use when choosing an OS image, Python, Node.js, or Java versions, build location, worker count, swap strategy, or minimum CPU, RAM, and disk for a repository. Produce evidence-backed FIT, FIT WITH CHANGES, NOT FIT, or NOT MEASURED decisions; do not recommend purchasing from guessed capacity.
1082mo agoReviewMountCreate a free account to mount
Review multiplayer authority, RPCs, sessions, authorization, replication, inventory, economy, purchases, retries, and replay. Use when server or backend state is the security boundary.
3.7k51d agoReviewMountCreate a free account to mount
Set up and verify the jupyterlab-collab-mcp MCP server so an agent can read/edit/execute Jupyter notebooks with real-time collaboration. Use when the user says 'connect to the jupyter MCP server', 'check the jupyterlab collab mcp', 'jlabx extensions aren't working', 'verify the MCP server is installed', the agent has no jupyter MCP tools despite expecting them, or notebook edits via MCP fail or return connection errors. THREE-LAYER architecture (opencode <-stdio-> MCP server <-y-websocket-> JupyterLab), three independent break points: (1) jlabx is a LAUNCHER, not the MCP server; (2) jupyter-collaboration must be installed in the SAME env JupyterLab runs from; (3) the MCP server must be registered in opencode.json mcp config (no auto-discovery; restart after changes). Verification: (a) 'jupyter server extension list' shows jupyter_server_ydoc enabled, (b) opencode.json has the jupyter entry, (c) the session actually has jupyter MCP tools. Full gotchas and the confirmed-working config in the body.
4250d agoReviewMountCreate a free account to mount
Use when the agent needs access to the outside world and it is unclear what is connected - "подключи mcp", "настрой доступы", "почему ты не видишь логи", "не видишь мою базу", "подключи vercel", "подключи supabase", "подключи stitch", "подключи drawio", "нарисуй схему", "нарисуй макет", "сделай дизайн экрана", "connect mcp", "set up mcp servers". Also use before deploying, before touching a database, before generating UI or screen mockups, and whenever a tool call fails with an authentication error rather than a code error.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.