Journey Submit logo

Journey Submit

Organization
butterbase-ai
journey-submit

Use as the final stage of the Butterbase journey when hackathon_mode is true and journey-deploy has passed. Resolves which hackathon to submit to (asking the user when multiple are open), walks every field in the hackathon's returned field_schema with the user one at a time, then calls prep_and_submit_hackathon_entry. Writes the receipt to docs/butterbase/05-submission.md.

Overview

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

Use it in TypingMind

Enable Journey Submit 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 Submit 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 Submit 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: Hackathon submission

Stage 5 (final) of the guided journey. Resolve the active hackathon, confirm fields, submit.

When to use

  • Dispatched by journey when current_stage: submit and hackathon_mode: true.
  • Directly via /butterbase-skills:submit.
  • No-op (returns with "submit is disabled outside hackathon mode") if hackathon_mode: false.

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.

Additionally: refuse to run unless deploy is ticked in 00-state.md. If it is not, tell the user to run /butterbase-skills:journey-deploy first.

Inputs

  • docs/butterbase/01-idea.md — title / tagline candidates.
  • docs/butterbase/02-plan.md — feature list.
  • docs/butterbase/04-build-log.md — what actually shipped.
  • docs/butterbase/00-state.md — app_id, deployed_url.

Procedure

Step 1 — Prep (resolve which hackathon)

Always start with action: "prep". Do not assume there is exactly one hackathon, and do not invent a field schema from prior context — the platform owns the schema and it varies per hackathon.

jsonc
// First, ask the user: "Do you have a submission code from the organizer? (paste it, or 'no')"
// If yes, pass it. If no, omit it.
{
  "tool": "prep_and_submit_hackathon_entry",
  "arguments": {
    "action": "prep",
    "submission_code": "<optional, from user>"
  }
}

The response shape is:

jsonc
{
  "matched": null | { "slug", "name", "submission_deadline", "ends_at", "field_schema": { "fields": [...] } },
  "match_reason": null | "submission_code" | "already_bound" | "single_open",
  "open_hackathons": [{ "slug", "name", "starts_at", "ends_at", "submission_deadline" }, ...],
  "next_call": { ... }   // present only when matched is non-null
}

Branch on the result:

matchedopen_hackathons.lengthAction
non-nullanyResolved — continue to Step 2 with matched.field_schema. Mention match_reason to the user ("Resolved via your submission code", "You're already a participant in X", "Only one hackathon is open: X").
null0No hackathon is currently open for submissions. Tell the user, stop, and do not tick submit.
null1One hackathon is open but the user isn't bound and didn't supply a code. Ask: "The only open hackathon is '<name>' (deadline <submission_deadline>). Submit to this one? If so, paste the submission_code the organizer gave you." Re-run prep with the code.
null≥ 2Multiple open hackathons — ask the user which one. Present the list (name, slug, deadline) and ask: "Which hackathon are you submitting to? Paste its submission_code." Re-run prep with the code. Never guess.

Anti-pattern: do not re-run prep in a loop hoping it resolves — it won't until the user provides a submission_code. One question, then re-prep.

Step 2 — Walk the returned field_schema with the user

matched.field_schema.fields is the authoritative list of fields for this hackathon. Walk every field in order. For each:

  1. Show the user the field's label (not key) and description.
  2. Propose a value drawn from journey artifacts where obvious:
    • URL-typed fields (is_url: true or type: "url") for the deployed app → deployed_url from 00-state.md.
    • Project name / title field → top candidate from 01-idea.md.
    • Description / summary field → one-liner from 01-idea.md + must-haves.
    • Repo URL → ask, no default.
    • Team info → ask, no default.
    • Demo video → ask, allow skip if required: false.
    • Anything else → ask.
  3. Confirm one at a time. Do not batch. Required fields must have a non-empty value before moving on.
  4. For options-typed fields, present the allowed choices verbatim.

Use next_call.arguments.data from the prep response as the literal template — it has one key per field with a placeholder string. Replace each placeholder with the confirmed value.

Step 3 — Submit

Show the assembled data object back to the user verbatim and ask: "Submit now? (yes/no)". On yes:

jsonc
{
  "tool": "prep_and_submit_hackathon_entry",
  "arguments": {
    "action": "submit",
    "hackathon_slug": "<matched.slug from prep — REQUIRED when multiple are open>",
    "app_id": "<app_id from 00-state.md — strongly recommended, unlocks +50 scoring points>",
    "submission_code": "<same code passed to prep, if any — required on first submission>",
    "data": { /* user-confirmed values keyed by field.key */ }
  }
}

Always pass hackathon_slug = matched.slug from prep. Without it, submit re-resolves and may target a different hackathon if more than one is open. Always pass app_id — scoring awards up to 50 points for Butterbase usage on that specific app.

Step 4 — Receipt

Capture the response (submission.id, submission.version, submission.updated_at, participant_created) and write docs/butterbase/05-submission.md:

markdown
# Submission

- submitted_at: <submission.updated_at>
- submission_id: <submission.id>
- version: <submission.version>
- hackathon_slug: <submission.hackathon_slug>
- hackathon_name: <matched.name>
- app_id: <submission.app_id>
- participant_created: <true|false>

## Fields submitted
<one bullet per field: label → value>

Tick - [x] submit in 00-state.md, set current_stage: done. Print a one-line success to the user including the hackathon name and submission id.

Outputs

  • Hackathon submission via prep_and_submit_hackathon_entry (action: "prep" then "submit").
  • docs/butterbase/05-submission.md.

Anti-patterns

  • ❌ Skipping action: "prep" and calling submit directly with a hardcoded field list.
  • ❌ Assuming there is exactly one open hackathon. Always check open_hackathons on the prep response.
  • ❌ Picking a hackathon for the user when prep returns multiple — always ask.
  • ❌ Inventing field keys or labels — only use what's in matched.field_schema.fields.
  • ❌ Submitting without hackathon_slug from prep (can re-resolve to the wrong hackathon).
  • ❌ Submitting without app_id when one exists (forfeits up to 50 scoring points).
  • ❌ Calling submit without explicit yes from the user on the assembled payload.

Frequently asked questions

What does the Journey Submit AI skill do?

Use as the final stage of the Butterbase journey when hackathon_mode is true and journey-deploy has passed. Resolves which hackathon to submit to (asking the user when multiple are open), walks every field in the hackathon's returned field_schema with the user one at a time, then calls prep_and_submit_hackathon_entry. Writes the receipt to docs/butterbase/05-submission.md.

Why use Journey Submit on TypingMind?

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

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

Which AI models can use Journey Submit?

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 Submit?

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

Is the Journey Submit 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 👇