agents-sdk

作者: openai

從 Codex 建置、執行、部署及評估 OpenAI Agents SDK 應用程式。當使用者要求建立或調整 Agents SDK 應用程式、從提示或 Codex 建置時使用…

npx skills add https://github.com/openai/plugins --skill agents-sdk

Cloudflare Agents SDK

Your knowledge of the Agents SDK may be outdated. Prefer retrieval over pre-training for any Agents SDK task.

Retrieval Sources

Fetch current docs from https://github.com/cloudflare/agents/tree/main/docs before implementing.

TopicDocUse for
Getting starteddocs/getting-started.mdFirst agent, project setup
Statedocs/state.mdsetState, validateStateChange, persistence
Routingdocs/routing.mdURL patterns, routeAgentRequest, basePath
Callable methodsdocs/callable-methods.md@callable, RPC, streaming, timeouts
Schedulingdocs/scheduling.mdschedule(), scheduleEvery(), cron
Workflowsdocs/workflows.mdAgentWorkflow, durable multi-step tasks
HTTP/WebSocketsdocs/http-websockets.mdLifecycle hooks, hibernation
Emaildocs/email.mdEmail routing, secure reply resolver
MCP clientdocs/mcp-client.mdConnecting to MCP servers
MCP serverdocs/mcp-servers.mdBuilding MCP servers with McpAgent
Client SDKdocs/client-sdk.mduseAgent, useAgentChat, React hooks
Human-in-the-loopdocs/human-in-the-loop.mdApproval flows, pausing workflows
Resumable streamingdocs/resumable-streaming.mdStream recovery on disconnect

Cloudflare docs: https://developers.cloudflare.com/agents/

Capabilities

The Agents SDK provides:

  • Persistent state - SQLite-backed, auto-synced to clients
  • Callable RPC - @callable() methods invoked over WebSocket
  • Scheduling - One-time, recurring (scheduleEvery), and cron tasks
  • Workflows - Durable multi-step background processing via AgentWorkflow
  • MCP integration - Connect to MCP servers or build your own with McpAgent
  • Email handling - Receive and reply to emails with secure routing
  • Streaming chat - AIChatAgent with resumable streams
  • React hooks - useAgent, useAgentChat for client apps

FIRST: Verify Installation

npm ls agents  # Should show agents package

If not installed:

npm install agents

Wrangler Configuration

{
  "durable_objects": {
    "bindings": [{ "name": "MyAgent", "class_name": "MyAgent" }]
  },
  "migrations": [{ "tag": "v1", "new_sqlite_classes": ["MyAgent"] }]
}

Agent Class

import { Agent, routeAgentRequest, callable } from "agents";

type State = { count: number };

export class Counter extends Agent<Env, State> {
  initialState = { count: 0 };

  // Validation hook - runs before state persists (sync, throwing rejects the update)
  validateStateChange(nextState: State, source: Connection | "server") {
    if (nextState.count < 0) throw new Error("Count cannot be negative");
  }

  // Notification hook - runs after state persists (async, non-blocking)
  onStateUpdate(state: State, source: Connection | "server") {
    console.log("State updated:", state);
  }

  @callable()
  increment() {
    this.setState({ count: this.state.count + 1 });
    return this.state.count;
  }
}

export default {
  fetch: (req, env) => routeAgentRequest(req, env) ?? new Response("Not found", { status: 404 })
};

Routing

Requests route to /agents/{agent-name}/{instance-name}:

ClassURL
Counter/agents/counter/user-123
ChatRoom/agents/chat-room/lobby

Client: useAgent({ agent: "Counter", name: "user-123" })

Core APIs

TaskAPI
Read statethis.state.count
Write statethis.setState({ count: 1 })
SQL querythis.sql`SELECT * FROM users WHERE id = ${id}`
Schedule (delay)await this.schedule(60, "task", payload)
Schedule (cron)await this.schedule("0 * * * *", "task", payload)
Schedule (interval)await this.scheduleEvery(30, "poll")
RPC method@callable() myMethod() { ... }
Streaming RPC@callable({ streaming: true }) stream(res) { ... }
Start workflowawait this.runWorkflow("ProcessingWorkflow", params)

React Client

import { useAgent } from "agents/react";

function App() {
  const [state, setLocalState] = useState({ count: 0 });

  const agent = useAgent({
    agent: "Counter",
    name: "my-instance",
    onStateUpdate: (newState) => setLocalState(newState),
    onIdentity: (name, agentType) => console.log(`Connected to ${name}`)
  });

  return (
    <button onClick={() => agent.setState({ count: state.count + 1 })}>
      Count: {state.count}
    </button>
  );
}

References

來自 openai 的更多技能

user-context
openai
載入或管理資料分析插件的持久性來源路由偏好設定、入門邏輯、設定進度以及語義層註冊表。
official
notion-research-documentation
openai
研究Notion內容,並將其整合為結構化的簡報、報告或附有引用的比較分析。透過精準查詢搜尋並擷取Notion頁面,然後按主題組織發現,並附上內文來源引用及參考文獻章節。根據範圍與使用者目標,從四種輸出格式(快速簡報、研究摘要、比較分析、綜合報告)中選擇。使用內建範本建立與更新Notion頁面;直接連結來源,並在新資訊到來時追蹤變更。
official
rcsb-pdb-skill
openai
提交精簡的RCSB PDB請求以獲取核心元數據、Search API查詢及FASTA下載。當用戶需要簡潔的RCSB摘要時使用;保存原始JSON或…
official
pdf
openai
PDF 讀取、建立與驗證,支援視覺化渲染與程式化生成。使用 Poppler(pdftoppm)將 PDF 頁面渲染為 PNG,以便在交付前檢查版面、間距與排版。透過 reportlab 程式化生成 PDF,確保格式可靠;使用 pdfplumber 或 pypdf 提取文字與元資料。執行品質標準:無文字裁切、元素重疊、表格破損或渲染瑕疵;僅使用 ASCII 連字號,引用格式需具可讀性。使用...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
終端驅動的瀏覽器自動化,具備元素快照與互動式UI工作流程。透過playwright-cli包裝腳本運作(需npx),支援無頭模式與有頭模式以進行視覺化除錯。核心流程:開啟頁面、擷取快照以取得穩定元素參照、使用參照進行互動、在導航或DOM變更後重新擷取快照。包含表單填寫、點擊、輸入、多分頁管理、螢幕截圖/PDF擷取,以及流程除錯的軌跡記錄。元素參照(例如e3、e15)...
official
ukb-topmed-phewas-skill
openai
接受rsID、GRCh37或GRCh38輸入,解析為所需的GRCh38查詢,以獲取單一變異的簡潔UKB-TOPMed PheWAS摘要。當需要…時使用。
official
code-review-context
openai
模型可見上下文
official