When should I run /llm-chat?

Use when adding AI sidebars, chat widgets, or prompt completion panels.

Is /llm-chat a Cursor skill?

No. /llm-chat is a slash command you type. Skills are playbooks the agent may load. Use both: the command runs the workflow, the skills constrain how it writes.

← Cursor Slash Commands · ENGINEERING

/llm-chat

Streaming AI Chat Assistant Interface

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

/llm-chat Create streaming AI chat sidebar component with Markdown rendering and copy buttons

Where it installs

# .cursor/commands/llm-chat.md
# no frontmatter, the file opens with its H1 title

# .claude/commands/llm-chat.md
---
description: ...
argument-hint: [chat surface description]
allowed-tools: Read, Grep, Glob, Skill, TodoWrite, Task, ...
---

What it does

/llm-chat is a Cursor slash command. Type it in chat to run a saved workflow: Streaming AI Chat Assistant Interface.

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

Streaming conversational UI with message history, markdown, and code blocks. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /llm-chat for you.

Why it exists

Founders retype the same multi-step prompt until it rots. /llm-chat exists so the pipeline, all 4 steps of it, is a file in .cursor/commands, versioned with the repo.

It ships in the Engineering Kit. It is wired to the AI & Vector Engineer (ai-engineer) and React 19 & Next.js Specialist (react-specialist) agents. Required skills: LLM Integration & Streaming AI Workflows; System Prompt Engineering & Few-Shot Design.

When to use it

Use when adding AI sidebars, chat widgets, or prompt completion panels.
Use /llm-chat when you want that pipeline, not a freeform chat. If you only need one step, use a narrower command or a single agent.
Start a new chat. Do not run this command in a thread that just wrote marketing copy.

When not to use it

Do not run /llm-chat as a substitute for reading the diff. The command produces files; you still gate them.
Do not chain it into a 40-turn chat. Fresh context is part of the design.
Do not run it if you have not filled CURSOR.md. The pipeline will invent a stack.

Example workflow

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

Example usage

Type this in Cursor chat: /llm-chat Create streaming AI chat sidebar component with Markdown rendering and copy buttons

The command file tells the session which agents to adopt and which skills to read. You should see phase headers, not a single dump of code.

If a phase fails its gate, stop. Do not add 'just continue'.

Example output

Expected artifact: src/components/chat/ChatSidebar.tsx
Expected artifact: src/app/api/chat/route.ts

Best practices

Keep the prompt specific. /llm-chat Create streaming AI chat sidebar component with Markdown rendering and copy buttons is the shape: object, constraint, and outcome.
Let the listed agents work in order: ai-engineer → react-specialist.
Save outputs in the repo. Chat-only answers evaporate.
Engineering commands should leave tests or an audit note, not only implementation files.

Common mistakes

Typing /llm-chat with no object ('do the thing'). The pipeline will guess.
Re-running the command in the same chat after a failed gate instead of fixing the failing file.
Editing the command file to skip review so it 'goes faster'.
Skipping the LLM Integration & Streaming AI Workflows skill that the command depends on.

Frequently asked questions

What does /llm-chat do in Cursor?
Builds streaming conversational AI interfaces: message history persistence, markdown code formatting, token budgeting, and tool invocation status.
When should I run /llm-chat?
Use when adding AI sidebars, chat widgets, or prompt completion panels.
What is an example /llm-chat prompt?
/llm-chat Create streaming AI chat sidebar component with Markdown rendering and copy buttons
Which skills does /llm-chat load?
LLM Integration & Streaming AI Workflows; System Prompt Engineering & Few-Shot Design
Is /llm-chat a Cursor skill?
No. /llm-chat is a slash command you type. Skills are playbooks the agent may load. Use both: the command runs the workflow, the skills constrain how it writes.

Run /llm-chat from your own repo

AgenticKit installs 47 slash commands, 46 agents, and 61 skills. One command installation.

Get AgenticKit →All Commands