Conversation Launcher logo

Conversation Launcher

OrganizationPopular
vellum-ai
conversation-launcher

Offer the user several spin-off conversations as clickable buttons on a single persistent card. Each click spawns a fresh seeded conversation in the sidebar; the user keeps their place in the current conversation. Use when you want to branch into N focused threads (research directions, draft choices, pending replies, triage of N items) without losing the current context. Not for single-destination pivots — just reply inline.

Overview

Publishervellum-ai
Repositoryvellum-assistant
Skill nameconversation-launcher
Stars
1.3K
Forks
186
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vellum-ai on GitHub. Read the source before you install it.

Installation

Install the Conversation Launcher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git /tmp/vellum-assistant
mkdir -p .claude/skills
cp -r /tmp/vellum-assistant/skills/conversation-launcher .claude/skills/conversation-launcher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Conversation Launcher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Conversation Launcher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Conversation Launcher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use this skill when you want to offer the user several spin-off conversations from the current one. You render one persistent card. Each button on the card spawns its own seeded conversation in the sidebar. The user can click multiple buttons without losing their place — the origin conversation (this one) keeps focus.

When this fits

  • Research branches — "here are three angles to pursue"
  • Draft choices — "here are the reply drafts I could write"
  • Triaging N items — "here are the five threads with pending replies"
  • Pending-reply fan-out — each sender gets their own drafting conversation

When this does NOT fit

  • Single-destination pivots — if there's one obvious next conversation, just reply inline or navigate there directly. One button is not a menu.
  • Options that share context and should stay in one thread — keep them here.
  • Inline Q&A the user can skim in place — answer; don't fan out.

How to render

Emit exactly one ui_show call with a card shaped like this, then end your turn:

json
{
  "surface_type": "card",
  "display": "inline",
  "persistent": true,
  "await_action": false,
  "data": {
    "title": "<framing headline>",
    "body": "<one short sentence framing the choice>"
  },
  "actions": [
    {
      "id": "opt-1",
      "label": "<short button label>",
      "style": "primary",
      "data": {
        "_action": "launch_conversation",
        "title": "<short conversation title>",
        "seedPrompt": "<full first-user-message seed>",
        "anchorMessageId": "<optional anchor message id from this conversation>"
      }
    },
    {
      "id": "opt-2",
      "label": "<short button label>",
      "style": "secondary",
      "data": {
        "_action": "launch_conversation",
        "title": "<short conversation title>",
        "seedPrompt": "<full first-user-message seed>"
      }
    }
  ]
}

Field notes:

  • persistent: true keeps the card visible after a click so the user can fire more buttons.
  • await_action: false lets the turn end without reserving the interactive-surface slot — the launcher dispatches its action directly, so blocking other surfaces is unnecessary.
  • Each action's data must contain _action: "launch_conversation", title, and seedPrompt. anchorMessageId is optional — include it when the spawned conversation should thread off a specific message in this one.
  • label is the button text (short, ≤ 4 words, ≤ 30 chars). title is the new conversation's sidebar name (3–5 words, specific not generic). seedPrompt is the first user message of the new conversation — written in first-person as if the user typed it, with enough context that the new conversation can pick up without re-asking.
  • Use style: "primary" for the recommended option (at most one), style: "secondary" for the rest.

Do nothing else

After rendering the card, end your turn. The click pipeline handles everything:

  • Do NOT run a follow-up step, issue any HTTP request, or write any file.
  • Do NOT send a chat message after the card. The card is the response.
  • Do NOT re-render the card on each click — it stays visible.

UX contract the client enforces

  • The card stays open and clickable for the lifetime of the live conversation — multiple buttons can be fired in succession without losing the user's place. If the conversation is closed and reopened later from history, the restored card reverts to single-click behavior (history rehydration drops the persistent flag — out of scope for this skill).
  • Each action.id fires at most once per card lifetime; sibling actions remain clickable.
  • Each spawned conversation inherits this conversation's guardian / trust context automatically.
  • Sidebar focus stays on this conversation. The user sees new entries appear and can navigate in at their pace.

Authoring tips

  • Don't invent options. Only surface branches the user has actually discussed or implied.
  • 2–5 buttons is the sweet spot. One option? Just reply inline. More than five? Trim or group.
  • Keep the card body to one sentence. The buttons carry the payload; the body just frames the choice.
  • Conversation titles should be highly concise, context-specific, and 3–5 words.

Frequently asked questions

What does the Conversation Launcher AI skill do?

Offer the user several spin-off conversations as clickable buttons on a single persistent card. Each click spawns a fresh seeded conversation in the sidebar; the user keeps their place in the current conversation. Use when you want to branch into N focused threads (research directions, draft choices, pending replies, triage of N items) without losing the current context. Not for single-destination pivots — just reply inline.

Why use Conversation Launcher on TypingMind?

Because you install it once and use it with any model. Conversation Launcher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Conversation Launcher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vellum-ai/vellum-assistant/tree/main/skills/conversation-launcher. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Conversation Launcher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Conversation Launcher?

As many as you like. As long as a model supports skills, you can use Conversation Launcher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Conversation Launcher AI skill free?

Yes. It is published on GitHub by vellum-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇