building-multi-connector-agent — for Claude Code building-multi-connector-agent, airbyte-agent-sdk, community, for Claude Code, ide skills, ai-agents, airbyte, anthropic, connectors, enterprise

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need building a multi-connector agent. 本地化技能摘要: 🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems. It covers ai, ai-agents, airbyte workflows.

功能特性

Building a Multi-Connector Agent
Use this when an agent needs two or more Airbyte connectors.
Going from Single to Multi
Build a single AirbyteAuthConfig(...) so credentials are shared across connectors.
Construct one typed connector per service (e.g. JiraConnector(auth config=auth)).

# 核心主题

airbytehq airbytehq
[117]
[8]
更新于: 4/21/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
65
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need building a multi-connector agent. 本地化技能摘要: 🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems. It covers ai, ai-agents, airbyte workflows.

核心价值

推荐说明: building-multi-connector-agent helps agents building a multi-connector agent. 🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

适用 Agent 类型

适用场景: Ideal for AI agents that need building a multi-connector agent.

赋予的主要能力 · building-multi-connector-agent

适用任务: Applying Building a Multi-Connector Agent
适用任务: Applying Use this when an agent needs two or more Airbyte connectors
适用任务: Applying Going from Single to Multi

! 使用限制与门槛

  • 限制说明: Use this when an agent needs two or more Airbyte connectors.
  • 限制说明: # Building a Multi-Connector Agent Use this when an agent needs two or more Airbyte connectors
  • 限制说明: One Tool Per Connector Each connector gets its own tool function — don't combine them into a mega-tool

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

building-multi-connector-agent 是什么?

适用场景: Ideal for AI agents that need building a multi-connector agent. 本地化技能摘要: 🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems. It covers ai, ai-agents, airbyte workflows.

如何安装 building-multi-connector-agent?

运行命令:npx killer-skills add airbytehq/airbyte-agent-sdk/building-multi-connector-agent。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

building-multi-connector-agent 适用于哪些场景?

典型场景包括:适用任务: Applying Building a Multi-Connector Agent、适用任务: Applying Use this when an agent needs two or more Airbyte connectors、适用任务: Applying Going from Single to Multi。

building-multi-connector-agent 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

building-multi-connector-agent 有哪些限制?

限制说明: Use this when an agent needs two or more Airbyte connectors.;限制说明: # Building a Multi-Connector Agent Use this when an agent needs two or more Airbyte connectors;限制说明: One Tool Per Connector Each connector gets its own tool function — don't combine them into a mega-tool。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add airbytehq/airbyte-agent-sdk/building-multi-connector-agent。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    building-multi-connector-agent 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

building-multi-connector-agent

安装 building-multi-connector-agent,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Building a Multi-Connector Agent

Use this when an agent needs two or more Airbyte connectors.

Going from Single to Multi

The bootstrapping-agent skill shows the single-connector pattern: direct class construction with AirbyteAuthConfig + @Connector.tool_utils decorator. Multi-connector agents use the same pattern, just repeated:

  1. Build a single AirbyteAuthConfig(...) so credentials are shared across connectors.
  2. Construct one typed connector per service (e.g. JiraConnector(auth_config=auth)).
  3. Define one tool function per connector, each with its own @Connector.tool_utils decorator.

There are no new APIs — same install, same constructor, same classmethod decorator.

Install the SDK

bash
1uv pip install airbyte-agent-sdk

The single airbyte-agent-sdk package bundles every typed connector, so tool_utils, list_entities(), and entity_schema() are available on each one without per-connector installs.

Core Pattern (PydanticAI)

python
1import os 2from pydantic_ai import Agent 3from airbyte_agent_sdk import AirbyteAuthConfig 4from airbyte_agent_sdk.connectors.jira import JiraConnector 5from airbyte_agent_sdk.connectors.slack import SlackConnector 6 7# Shared credentials — all connectors reuse the same AirbyteAuthConfig 8auth = AirbyteAuthConfig( 9 airbyte_client_id=os.getenv("AIRBYTE_CLIENT_ID"), 10 airbyte_client_secret=os.getenv("AIRBYTE_CLIENT_SECRET"), 11 workspace_name=os.getenv("AIRBYTE_WORKSPACE_NAME", "default"), 12) 13 14jira = JiraConnector(auth_config=auth) 15slack = SlackConnector(auth_config=auth)

If the workspace contains multiple connectors of the same type, pin one by passing connector_id=os.getenv("JIRA_CONNECTOR_ID") to the constructor.

One Tool Per Connector

Each connector gets its own tool function — don't combine them into a mega-tool. Separate tools give the LLM clear, independent tool descriptions.

tool_utils is a @classmethod — decorate with @JiraConnector.tool_utils, not @jira.tool_utils.

python
1agent = Agent( 2 "openai:gpt-4o", 3 system_prompt="You monitor Jira issues and post summaries to Slack.", 4) 5 6@agent.tool_plain 7@JiraConnector.tool_utils 8async def jira_execute(entity: str, action: str, params: dict | None = None): 9 return await jira.execute(entity, action, params or {}) 10 11@agent.tool_plain 12@SlackConnector.tool_utils 13async def slack_execute(entity: str, action: str, params: dict | None = None): 14 return await slack.execute(entity, action, params or {})

System Prompt

Describe the agent's purpose and what each connector does:

python
1agent = Agent( 2 "openai:gpt-4o", 3 system_prompt=( 4 "You are a customer support assistant. " 5 "Use the stripe tool to look up customer billing data. " 6 "Use the jira tool to create and track support tickets. " 7 "Use the slack tool to notify the support team." 8 ), 9)

Run Loop

PydanticAI

python
1import asyncio 2 3async def main(): 4 result = await agent.run("Find open P0 bugs and post a summary to #engineering") 5 print(result.output) 6 await jira.close() 7 await slack.close() 8 9asyncio.run(main())

Claude SDK (Anthropic Python)

See Claude SDK patterns for the full message loop with tool handling.

Project Structure

For a new agent project:

my-agent/
├── pyproject.toml       # dependencies: airbyte-agent-sdk, pydantic-ai or anthropic
├── .env                 # AIRBYTE_CLIENT_ID, AIRBYTE_CLIENT_SECRET, AIRBYTE_WORKSPACE_NAME
├── agent.py             # Entry point: auth config, connectors, agent + tools, run loop
└── README.md

pyproject.toml

toml
1[project] 2name = "my-agent" 3requires-python = ">=3.11" 4dependencies = [ 5 "airbyte-agent-sdk", 6 "pydantic-ai", 7 "python-dotenv", 8]

Environment Variables

AIRBYTE_CLIENT_ID=your_client_id
AIRBYTE_CLIENT_SECRET=your_client_secret
AIRBYTE_WORKSPACE_NAME=your_workspace_name

References

相关技能

寻找 building-multi-connector-agent 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具