Journey Functions logo

Journey Functions

Organization
butterbase-ai
journey-functions

Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.

Overview

Publisherbutterbase-ai
Repositorybutterbase-skills
Skill namejourney-functions
Stars
535
Forks
42
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 butterbase-ai on GitHub. Read the source before you install it.

Installation

Install the Journey Functions 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.
    https://github.com/butterbase-ai/butterbase-skills/tree/main/skills/journey-functions
  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/butterbase-ai/butterbase-skills.git /tmp/butterbase-skills
mkdir -p .claude/skills
cp -r /tmp/butterbase-skills/skills/journey-functions .claude/skills/journey-functions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Journey Functions 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 Journey Functions 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 Journey Functions 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.

Journey: Functions

Stage 3e of the guided journey. Implement and deploy each function in the plan.

When to use

  • Dispatched by journey when current_stage: functions.
  • Directly via /butterbase-skills:journey-functions.
  • Skipped (annotated (n/a)) if the plan lists no functions.

Preflight

If docs/butterbase/03-preflight.md is missing, older than 24 hours, or 00-state.md has app_id: null, invoke butterbase-skills:journey-preflight first. Wait for it to return successfully before proceeding.

Inputs

  • docs/butterbase/02-plan.md — the Functions section.
  • docs/butterbase/00-state.md — for app_id.

Procedure

  1. Refresh docs. Call butterbase_docs with topic: "functions". For trigger types and ctx shape, also WebFetch https://docs.butterbase.ai/functions. Skip if cache is fresh.

0.5. Check built-in integrations first. Before writing function code that calls an external SaaS for email / messaging / calendar / CRM / payments:

  • Email / Slack / etc. → invoke butterbase-skills:integrations. The function should call manage_integrations execute_action rather than installing a third-party SDK.
  • Payments → invoke butterbase-skills:payments. The function should use Stripe Connect via manage_billing unless the plan has explicitly chosen a regional gateway.

@butterbase/sdk works server-side too

Inside a function, prefer ctx.db / ctx.storage / ctx.user for the common cases — those are pre-wired and authenticated against the calling user. But for cross-app calls, scripts, or scheduled jobs that operate on multiple apps, instantiate @butterbase/sdk with a service key (bb_sk_) and use the same client surface as the frontend.

Example for a cron function that aggregates from another app:

ts
import { createClient } from '@butterbase/sdk';

export async function handler(_request: Request, ctx: { env: Record<string,string> }) {
  const other = createClient({
    apiUrl: ctx.env.OTHER_APP_API_URL,
    apiKey: ctx.env.OTHER_APP_SERVICE_KEY,
  });
  const { data } = await other.db.from('events').select('*').gte('created_at', ...);
  // ...
  return new Response('ok');
}

For server-side patterns, butterbase_docs topic: "sdk".

Build each function

For each function in the plan, in order:

  1. Print: "About to build function: <name> (trigger=<trigger>). Proceed?". Wait for yes.
  2. Invoke butterbase-skills:function-dev via the Skill tool with the function spec (name, trigger, behaviour, dependencies) and app_id. The wrapped skill scaffolds the handler, writes tests where appropriate, and calls deploy_function. Reminder it must enforce: handler signature (request, { db, env, user }) and must return new Response(...).
  3. Smoke: call invoke_function for HTTP/cron functions and confirm a 2xx + expected body. For WebSocket, defer the smoke to frontend integration.
  4. Append one line per function to docs/butterbase/04-build-log.md: <ISO timestamp> functions deploy_function <fn-name> ok
  5. After all functions are done, tick - [x] functions in 00-state.md, set current_stage: to the next unchecked stage.
  6. Return to journey orchestrator (or ask "Continue to the next stage? (yes/no)").

Outputs

  • Deployed functions in the Butterbase app.
  • One line per function in 04-build-log.md.

Anti-patterns

  • ❌ Letting a handler return a plain object — must be new Response(...).
  • ❌ Skipping the smoke invocation. Cron functions in particular are easy to deploy and forget.
  • ❌ Forgetting per-function env vars — use manage_function action: update_env.

Frequently asked questions

What does the Journey Functions AI skill do?

Use as the functions build stage of the Butterbase journey. Implements the Functions section of 02-plan.md by delegating to function-dev for each function. Calls deploy_function per function; smokes each with invoke_function. Skipped if the plan has no functions.

Why use Journey Functions on TypingMind?

Because you install it once and use it with any model. Journey Functions 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 Journey Functions in TypingMind?

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

Which AI models can use Journey Functions?

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 Journey Functions?

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

Is the Journey Functions AI skill free?

Yes. It is published on GitHub by butterbase-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 👇