ag-ui
You are an expert in AG-UI (Agent-User Interaction Protocol), the open standard by CopilotKit for connecting AI agents to frontend UIs. You help developers stream agent actions, tool calls, state updates, and text generation to React components in real-time — enabling rich agent UIs where users see what the agent is thinking, doing, and can intervene at any step.
What this skill does
# AG-UI — Agent-User Interaction Protocol
You are an expert in AG-UI (Agent-User Interaction Protocol), the open standard by CopilotKit for connecting AI agents to frontend UIs. You help developers stream agent actions, tool calls, state updates, and text generation to React components in real-time — enabling rich agent UIs where users see what the agent is thinking, doing, and can intervene at any step.
## Core Capabilities
### AG-UI Server (Agent Events)
```typescript
// server/agent.ts — Stream agent events to UI
import { AgentServer, EventStream } from "@ag-ui/server";
const server = new AgentServer();
server.onRequest(async (request, stream: EventStream) => {
const { messages, context } = request;
// Emit thinking state
stream.emitStateUpdate({ status: "thinking", progress: 0 });
// Stream text generation
stream.emitTextStart();
for (const word of "I'll analyze your data now.".split(" ")) {
stream.emitTextDelta(word + " ");
await sleep(50);
}
stream.emitTextEnd();
// Emit tool call
stream.emitToolCallStart("search_database", { query: context.userQuery });
const results = await searchDatabase(context.userQuery);
stream.emitToolCallEnd("search_database", results);
stream.emitStateUpdate({ status: "analyzing", progress: 50 });
// Stream analysis
stream.emitTextStart();
const analysis = await generateAnalysis(results);
for await (const chunk of analysis) {
stream.emitTextDelta(chunk);
}
stream.emitTextEnd();
// Custom state for UI rendering
stream.emitStateUpdate({
status: "complete",
progress: 100,
charts: [{ type: "bar", data: results.chartData }],
suggestions: ["Run deeper analysis", "Export to CSV", "Schedule report"],
});
stream.end();
});
```
### AG-UI React Client
```tsx
import { useAgent, AgentProvider } from "@ag-ui/react";
function App() {
return (
<AgentProvider url="https://api.example.com/agent">
<AgentChat />
</AgentProvider>
);
}
function AgentChat() {
const { messages, state, sendMessage, isStreaming, toolCalls } = useAgent();
return (
<div className="flex flex-col h-screen">
{/* Agent state visualization */}
{state.status === "thinking" && (
<div className="bg-blue-50 p-3 rounded-lg animate-pulse">
🤔 Agent is thinking... ({state.progress}%)
<progress value={state.progress} max={100} />
</div>
)}
{/* Tool calls (show what agent is doing) */}
{toolCalls.map((tc) => (
<div key={tc.id} className="bg-gray-50 p-2 rounded text-sm">
🔧 <strong>{tc.name}</strong>: {tc.status === "running" ? "Working..." : "Done"}
{tc.result && <pre className="mt-1">{JSON.stringify(tc.result, null, 2)}</pre>}
</div>
))}
{/* Messages */}
{messages.map((msg) => (
<div key={msg.id} className={msg.role === "user" ? "text-right" : "text-left"}>
<p>{msg.content}</p>
</div>
))}
{/* Dynamic UI from agent state */}
{state.charts?.map((chart, i) => (
<Chart key={i} type={chart.type} data={chart.data} />
))}
{state.suggestions && (
<div className="flex gap-2">
{state.suggestions.map((s) => (
<button key={s} onClick={() => sendMessage(s)} className="px-3 py-1 bg-blue-100 rounded">
{s}
</button>
))}
</div>
)}
{/* Input */}
<form onSubmit={(e) => { e.preventDefault(); sendMessage(input); }}>
<input placeholder="Ask anything..." disabled={isStreaming} />
</form>
</div>
);
}
```
## Installation
```bash
npm install @ag-ui/react @ag-ui/server
```
## Best Practices
1. **State streaming** — Emit state updates for progress, status, UI components; users see agent's thought process
2. **Tool call transparency** — Show tool calls in real-time; builds trust, helps debugging
3. **Suggestions** — Emit suggestion buttons after responses; guide users to next actions
4. **Custom UI** — Use state updates to render charts, tables, forms; richer than plain text
5. **Human-in-the-loop** — Emit confirmation requests before destructive actions; users approve or reject
6. **Progress tracking** — Emit progress percentages for long tasks; prevent user anxiety
7. **Framework agnostic** — AG-UI protocol works with any agent backend (LangGraph, CrewAI, custom)
8. **CopilotKit integration** — AG-UI powers CopilotKit; use CopilotKit for higher-level React components
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.