Skills by assistant-ui

Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.

Guide for assistant-stream package and streaming protocols. Use when implementing streaming backends, custom protocols, or debugging stream issues.

This skill documents `assistant-ui` runtime APIs for thread, message, and runtime integration. It includes examples that call `openai.chat.completions.create`, fetch `/api/chat`, and reference the env var `process.env.NEXT_PUBLIC_OPENAI_API_KEY`.

This skill documents `assistant-ui` frontend primitives for building chat UIs. Examples include runtime code that calls `https://assistant-ui.com/llms.txt`, `/api/chat`, and `/api/feedback`; network usage is purpose-aligned and no file/env credential access or shell execution is present.

Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.

Guide for multi-thread management in assistant-ui. Use when implementing thread lists, switching threads, or managing conversation history.

Setup and configure assistant-ui in a project. Use when installing packages, configuring runtimes, setting up chat UI, or troubleshooting setup issues.

High-risk skill: contains explicit shell commands such as `npx @ai-sdk/codemod upgrade`, `pnpm add @assistant-ui/react@latest`, and `git clean -fd` that the agent is instructed to run. It also instructs network/package fetches (e.g., `npm install`, `https://ai-sdk.dev/docs/migration-guides/migration-guide-6-0`) and references `"/api/chat"`.

Guide for assistant-cloud persistence and authorization. Use when setting up thread persistence, file uploads, or authentication.