# /llm-chat - Streaming AI Chat Assistant Interface

> Streaming conversational UI with message history, markdown, and code blocks.

Canonical: https://www.agentickit.co/commands/llm-chat
Last updated: 2026-11-18

Builds streaming conversational AI interfaces: message history persistence, markdown code formatting, token budgeting, and tool invocation status.

**Usage:** `Use when adding AI sidebars, chat widgets, or prompt completion panels.`

## Pipeline
1. Set up streaming chat API endpoint using Vercel AI SDK and Anthropic/OpenAI
2. Build chat UI component with auto-scrolling message list and input textarea
3. Add code syntax highlighting, copy-to-clipboard buttons, and markdown support
4. Persist conversation history to database with session caching

## Output files
- `src/components/chat/ChatSidebar.tsx`
- `src/app/api/chat/route.ts`

**Claude Code frontmatter:** `argument-hint: [chat surface description]` · `model: inherit`

## Related
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [react-specialist](https://www.agentickit.co/agents/react-specialist)
- [llm-integration](https://www.agentickit.co/skills/llm-integration)
- [prompt-engineering](https://www.agentickit.co/skills/prompt-engineering)
