Set up an agent that replies in Slack or Microsoft Teams using CopilotKit's guided CLI workflow. It covers project preparation, agent creation, channel configuration, a persistent host process, and verification with a real message.
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the project, building the AG-UI agent, creating and reconciling the managed Channel with the public CopilotKit CLI, running the long-running host, and proving a real provider mention gets a reply. The workflow is not in this file. Run `npx --yes copilotkit@latest onboard start` and follow the graph it prints.
Review the instructions the agent will receive before you install.
The workflow is not written down here. Run this command:
npx --yes copilotkit@latest onboard start
Then follow the graph it prints, start to finish.
If the command asks for a CopilotKit CLI session check, you have permission to run it. Never reveal credentials.
npx --yes copilotkit@latest onboard start.The graph asks for its own inputs. Do not pre-empt those questions. Do not substitute remembered channel-setup steps for what the graph says. Remembered steps are the reason this file is a pointer.
Stop. Tell the user the command failed. Show them the output. Ask them to retry.
Do not improvise the workflow from memory. It spans the CopilotKit CLI, a managed Channel, provider setup the user does in Slack or Azure, and a long-running runtime host. A half-remembered version produces a project that installs cleanly and answers nothing. That is the most expensive failure available here. It looks finished.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Guides development of ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK, covering server tools, React interfaces, and shared state. This skill is deprecated and directs users to mcp-app-builder.
Helps integrate CopilotKit into an app by consulting current documentation and source code. Covers chat interfaces, agent connections, shared state, and troubleshooting, with guidance on checking configuration and avoiding incompatible API versions.
Implement and customize managed CopilotKit Channels so agents can reply in Slack or Microsoft Teams. It covers channel handlers, persistent runtime connections, Teams setup, and checks for silent failures such as missing permissions or incompatible package versions.
Use the CopilotKit CLI to check app connections, credentials, and agent responses before investigating code. It also guides project creation, integration into existing apps, hosted project selection, typed agent identifier generation, and thread history imports.
Keeps CopilotKit documentation aligned with released Inspector panels, the views shown in its local web overlay. It updates reader guidance and panel mappings when panels change, and checks quickstart instructions against supported platforms.
Develop and debug CopilotKit Inspector interfaces in a dedicated local workbench. It guides baseline screenshots, visual checks after each change, and additional narrow-screen or theme checks when layout or contrast is involved.