Journey Templates logo

Journey Templates

Organization
butterbase-ai
journey-templates

Use as the optional template-publishing stage of the Butterbase journey, after deploy (and substrate, if used). Walks the user through authoring a clone-ready README, bundling agent spec files, dry-running and pushing the repo snapshot, flipping visibility to public + listed, and self-clone-testing. Delegates the mechanics to the `templates` skill. Skipped by default in hackathon mode.

Overview

Publisherbutterbase-ai
Repositorybutterbase-skills
Skill namejourney-templates
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 Templates 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-templates
  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-templates .claude/skills/journey-templates
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Journey Templates 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 Templates 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 Templates 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: Publish-as-template (optional)

Turn the deployed app into a public, forkable template. This stage is only for apps the user explicitly wants to share — most journeys end at deploy (or submit in hackathon mode).

When to use

  • Dispatched by journey when current_stage: templates.
  • Directly via /butterbase-skills:journey-templates.
  • The row is optional in the checklist; skip silently if the user declines.

Inputs

  • A deployed, working app (post-journey-deploy).
  • docs/butterbase/02-plan.md — to know what features the app uses (agents, MCP servers, OAuth providers, function env vars).
  • docs/butterbase/04-build-log.md — to confirm deploy smoke passed.

Preflight

  • 00-state.md must have current_stage: templates or later AND deploy ticked.
  • The @butterbase/cli must be installed locally (butterbase --version works). If not, invoke journey-preflight to fix.
  • The repo must be bound: .butterbase/config.json exists with the right currentApp. If not, run butterbase repo init <app_id>.

Procedure

  1. Refresh docs. Call butterbase_docs with topic: "templates" (and topic: "repo" if the cache doesn't already cover snapshot push). Skip if 03b-docs-cache.md is fresh.

  2. Confirm intent. Ask:

    "Publish '<app_name>' as a public template? Public + listed makes it appear in the gallery; public + unlisted is forkable by anyone with the app_id but hidden from search. Or skip. (listed / unlisted / skip)"

    Default: skip (especially in hackathon mode unless the user explicitly chose to publish their submission).

  3. On skip: mark the row - [x] templates (skipped — not publishing) in 00-state.md. Write docs/butterbase/06-template.md with one line: Skipped on <date>. Return to orchestrator.

  4. On listed / unlisted: delegate to butterbase-skills:templates. The wrapped skill walks the user through: a. Author / review README.md. This is the most important step — clone replay does not carry OAuth secrets, agent records, MCP server registrations, function secrets, or user data. The README must explain every manual step a cloner will need. The templates skill has the full checklist; do not let it write a short README and move on. b. Bundle agent specs. If the app has agents, ensure agents/<name>.json exist (export with butterbase agents get <name> if missing) and are tracked. c. Inspect drift. butterbase repo status. Walk the modified / untracked / deleted lists with the user. This is the chance to catch a stray secret file or an unwanted directory before it ends up in the snapshot. d. Dry-run. butterbase repo push --dry-run. Confirm the final upload manifest matches what repo status showed. e. Push. butterbase repo push -m "publish v1". Capture the snapshot id. f. Flip visibility. butterbase visibility public --listed (or --unlisted). g. Self-clone test. butterbase clone <app_id> /tmp/clone-test-<ts> into a scratch directory — this also exercises the cloner-side repo pull that butterbase clone runs internally. The wrapped skill walks the README from a cold cloner's perspective and reports any gap. Loop back to (a) if gaps exist.

  5. Write artifact. docs/butterbase/06-template.md:

    markdown
    ---
    published_at: <ISO>
    app_id: <id>
    visibility: public
    listed: <true|false>
    snapshot_id: <id>
    selfclone_test: <pass | gaps fixed in round N>
    ---
    
    # Template publication
    
    - Visibility: public (<listed | unlisted>)
    - Latest snapshot: <id>
    - README covers: env vars, OAuth, agent re-import, MCP servers, seed data, first-run smoke
    - Self-clone test directory: /tmp/clone-test-<ts>
    - Gallery URL: https://butterbase.ai/templates/<app_id>  (or wherever discovery lives)
  6. Update state. Tick - [x] templates in 00-state.md.

  7. Return to orchestrator (or end the journey, since this is the last optional stage).

Anti-patterns

  • ❌ Pushing the repo after flipping visibility. Order matters: snapshot first, public second. Otherwise the gallery briefly advertises an empty template.
  • ❌ Skipping the README. The clone preflight tells the cloner which env vars exist but not what they're for or what manual setup remains. A bare-bones README publishes a broken-on-clone experience.
  • ❌ Skipping the self-clone test. The author always knows too much; only a cold walk-through catches missing instructions.
  • ❌ Forgetting agent specs. The agents DB table doesn't replay. Without agents/*.json in the repo, cloners can see your agent code paths but cannot recreate the agents themselves.
  • ❌ Publishing in hackathon mode by default. Hackathon submissions are usually private; only publish if the user explicitly asks.
  • ❌ Pushing files containing secrets. Always dry-run first and scan the file list.

Frequently asked questions

What does the Journey Templates AI skill do?

Use as the optional template-publishing stage of the Butterbase journey, after deploy (and substrate, if used). Walks the user through authoring a clone-ready README, bundling agent spec files, dry-running and pushing the repo snapshot, flipping visibility to public + listed, and self-clone-testing. Delegates the mechanics to the `templates` skill. Skipped by default in hackathon mode.

Why use Journey Templates on TypingMind?

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

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

Which AI models can use Journey Templates?

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 Templates?

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

Is the Journey Templates 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 👇