Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow, 연구부터 논문까지, 연구 주제 설정부터 논문 완성까지, 논문 전체 워크플로, flujo de trabajo académico, investigación a artículo, flujo completo de artículo, pipeline de investigación completa, publicación de investigación, flujo de trabajo completo del artículo.
Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server. Use this skill when a user wants to connect their AI assistant (such as Gemini, Claude Code, or Cursor) to their Google Ads account to query campaigns or retrieve reporting metrics using natural language.
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.
Guide developers through creating and updating ChatGPT plugins. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting plugins to ChatGPT. Use when a user wants to create or update a ChatGPT plugin (formerly called a ChatGPT app) / MCP server for ChatGPT, or use the Skybridge framework.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. Don't use for standard infrastructure monitoring unrelated to AI agents, or when the agent is not instrumented with OpenTelemetry (for Reliability, Cost, Safety, Security alerts). NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (such as Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI deployments.
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "配置". Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.
Orderly Network onboarding: omnichain perps infra, MCP server, SDK and CLI quickstart. Also indexes executed Orderly fills into Starchild trade analytics. Use when starting on Orderly (e.g. install Orderly MCP, set up the DEX template, integrate the React SDK, use the orderly CLI), and after executing any Orderly trade — report the fill so it is indexed.
Answer questions about ECC by reading the live repo surface — agents, skills, commands, hooks, rules, install profiles, and docs — instead of memory. Use when the user asks what ECC includes, how to install or reset it, which skill or command fits a task, or how project onboarding works.
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.
Use this skill when the user asks to “create a plugin,” “scaffold a plugin,” “understand plugin structure,” “organize plugin components,” “set up plugin.json,” “use ${CLAUDE_PLUGIN_ROOT},” “add commands/agents/skills/hooks,” “configure auto-discovery,” or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Read a plan document, decompose it into steps, classify each step, and emit the ready-to-paste ECC slash command for that step, carrying the step identifier and scope in the command's own documented argument form. Generative only — never invokes commands itself and never claims to control what a command runs internally. Steps whose command cannot carry plan scope fail closed instead of being emitted. Use when the user has a multi-step plan and wants the right command for each step without picking it by hand.
Use when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like "help me write a skill", "make a skill that…", "turn this workflow into a skill", or improving an existing skill's triggering and discipline. Also use when capturing reusable agent guidance that should live as an installable skill rather than a one-off prompt. Covers choosing scope (project vs global), authoring inside a plugin or skills-distribution repo (write in the repo's own layout, never install), the SKILL.md frontmatter contract, progressive-disclosure structure, evaluating the skill, and installing it into the user's editors.
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.
Suggest relevant GitHub Copilot prompt files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing prompts in this repository, and identifying outdated prompts that need updates.
Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to OpenCode — phrasings like "have OpenCode do X", "delegate this to OpenCode", "run it through OpenCode", or "use OpenCode to implement/fix/refactor" — or wants to run a queue of coding tasks through OpenCode while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.
File-based persistent planning for multi-step AI agent tasks. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected planning context from the project. Automatic recovery reads only the project's planning files. When explicitly requested, session-catchup.py --metadata can inspect local session metadata from the same project; --replay can emit nonce-bounded, framed excerpts. The optional gated mode can only ask the host to continue if it supports that, and never runs commands declared in Markdown. The skill has no network load path. Use for research or work requiring 5 or more tool calls.
Persistent file-based planning for multi-step work with AI agents. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads only the project's planning files. Only an explicit call to session-catchup.py --metadata may inspect local session metadata of the same project; --replay may output limited, nonce-framed excerpts. The optional gate mode can only request continuation when supported by the host and never executes commands specified in Markdown. The skill has no network upload path. Use for research or work requiring more than 5 tool calls.
Persistent file-based planning for multi-step work with AI agents. Keeps task_plan.md, findings.md, and progress.md on disk, and lifecycle hooks inject selected project planning context. Automatic recovery reads only project planning files. An explicit session-catchup.py --metadata command can inspect local agent session metadata belonging to the same project, while --replay may output limited excerpts framed by nonce. The optional gate mode can only request continuation when supported by the host, and never executes commands stated in Markdown. The skill includes no network upload path. Use for research or work requiring 5 or more tool calls.
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit) development lifecycle.
This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.
Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary.
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps or the OS and must be installable without the user having Node/Python set up.
A step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating or demonstrating the pattern before committing to the protect-mcp runtime hooks. Covers Cedar policy, Ed25519 receipts, offline verification, tamper detection, CI/CD integration and SLSA composition.
Defines model-callable tools and renders their calls in assistant-ui. The authoring model: a "use generative" file whose default export is defineToolkit({...}), compiled by withAui from @assistant-ui/next, aui() from @assistant-ui/vite, or withAui from @assistant-ui/metro, mounted with AuiConfig({ tools: Tools({ toolkit }) }), and exposed to the model with new AISDKToolkit({ toolkit }).tools({ frontend }). Covers the tool kinds (backend, "use client" frontend, humanTool(), providerTool(), externalTool(), stubTool(), defineMcpToolkit()), render and display, ToolCallMessagePartProps, approval gates, MCP servers, MCP Apps, WebMCP, and sub-agent messages. Reach for it when a tool is never called, a tool UI does not render, a frontend result never reaches the model, humanTool() throws at runtime, or an approval gate cannot be answered. For model-composed UI use generative-ui, for MCP servers users add in the browser use react-mcp, and for the styled ToolFallback and ToolGroup use elements.
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
Delegate a coding task to a separate Claude Code CLI process or another Claude session as implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the `claude` CLI — for example, "have another Claude implement this", "delegate this to Claude Code", or "run this queue through a separate Claude session." Do not trigger merely because the current orchestrator is Claude, and do not use when the user asks the current Claude to implement directly without delegation.
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.