Kickoff logo

Kickoff

Community
koolamusic
kickoff

Initialize a new project with PROJECT.md + ROADMAP.md in .project/, set up jira and studio, and route to the first sprint. Use when starting a new project, onboarding a new codebase, or setting up workflow infrastructure for the first time.

Overview

Publisherkoolamusic
Repositoryclaudefiles
Skill namekickoff
Stars
121
Forks
14
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 koolamusic on GitHub. Read the source before you install it.

Installation

Install the Kickoff 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/koolamusic/claudefiles/tree/main/skills/kickoff
  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/koolamusic/claudefiles.git /tmp/claudefiles
mkdir -p .claude/skills
cp -r /tmp/claudefiles/skills/kickoff .claude/skills/kickoff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kickoff 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 Kickoff 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 Kickoff 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.

Kickoff

One command to go from empty repo (or unfamiliar codebase) to a working project with full workflow infrastructure. Produces .project/PROJECT.md + ROADMAP.md, initializes jira and studio, and points you at the first sprint.

Input

$ARGUMENTS:

  • Free text — a description of what this project is and what you're trying to build
  • Empty — start with adaptive questioning to understand the project

Process

1. Understand the project

If the user provided a description, use it as the seed. Either way, explore:

  • Codebase scan — ls, package.json, Cargo.toml, go.mod, README.md, CLAUDE.md, recent git history. What exists already?
  • Stack detection — language, framework, database, deployment target
  • Existing workflow state — .jira/, .project/, .planning/ (legacy), .workspacerc

Then ask focused questions via AskUserQuestion (max 4 questions, bundled):

  • What is this project? (one sentence)
  • Who uses it and what problem does it solve?
  • What are the hard constraints? (stack, timeline, compliance, team size)
  • What does "done" look like for the first milestone?

Skip questions the codebase already answers.

2. Set up infrastructure

Run these in sequence:

a. Studio — if no .workspacerc exists, invoke /studio:setup semantics (create workspace, symlinks, gitignore block, hook wiring). If .workspacerc already exists, skip.

b. Jira — if no .jira/ exists, invoke /jira:init semantics (bootstrap .jira/ with STATE.md, sprints/). If .jira/ already exists, skip.

c. Create .project/ — mkdir -p .project/. If studio is active, this will be a symlink into the workspace.

3. Write PROJECT.md

Write .project/PROJECT.md:

markdown
---
name: <project name>
created: <YYYY-MM-DD>
stack: <detected stack summary>
status: active
---

# <Project Name>

## Purpose
<2-3 sentences: what this project is and why it exists>

## Constraints
<bulleted list of hard constraints — technical, timeline, compliance, team>

## Success criteria
<what "done" looks like — measurable where possible>

## Stack
<language, framework, database, deployment, key dependencies>

## Team
<who's working on this — roles, not names if unknown>

## Decisions
<significant architectural or product decisions already made — reference CLAUDE.md, ADRs, or CONTEXT.md entries>

4. Write ROADMAP.md

Break the project into phases. Each phase is a milestone-level chunk that maps to one or more jira sprints.

markdown
---
project: <project name>
created: <YYYY-MM-DD>
phases: <count>
---

# Roadmap

## Phase 1: <name>
**Goal:** <one sentence>
**Sprints:** <estimated count>
**Depends on:** —
**Status:** not-started

### Deliverables
- <deliverable 1>
- <deliverable 2>

### Success criteria
- [ ] <criterion 1>
- [ ] <criterion 2>

## Phase 2: <name>
...

Scale the roadmap to the project. A weekend hack gets 2-3 phases. A production app gets 5-10. Don't over-plan — the roadmap is a compass, not a GPS route.

5. Present and iterate

Show the user:

  • PROJECT.md summary
  • ROADMAP.md phase breakdown
  • Infrastructure status (studio, jira)

Ask: "Does this capture the project? Should any phases merge, split, or reorder?"

Iterate until approved.

6. Commit and route

bash
git add .project/PROJECT.md .project/ROADMAP.md
git commit -m "kickoff: initialize project — <project name>"

Then suggest the next step:

  • If Phase 1 is clear enough to sprint on: "Ready for /jira:research <phase 1 goal>"
  • If Phase 1 needs shaping first: "Ready for /grill shape to refine Phase 1 before sprinting"
  • If the user wants to decompose Phase 1 into issues first: "Ready for /jira:to-issues after planning"

Legacy migration

If .planning/ exists (from GSD or older workflows):

  1. Note its contents to the user
  2. Offer to migrate relevant artifacts (PROJECT.md, ROADMAP.md equivalents) into .project/
  3. Don't delete .planning/ — that's a studio:migrate concern

Hard rules

  • Never skip the user conversation. Even if the codebase is obvious, confirm with the user. Kickoff is alignment, not automation.
  • Infrastructure is idempotent. Re-running kickoff on an initialized project updates PROJECT.md and ROADMAP.md but doesn't re-init jira or studio.
  • Roadmap phases are NOT jira sprints. A phase may require multiple sprints. The mapping is: phase = milestone, sprint = one research→plan→execute cycle within a phase.
  • Don't start a sprint. Kickoff ends at the roadmap. The user decides when to start the first sprint.
  • Never push. Commit locally only.

Frequently asked questions

What does the Kickoff AI skill do?

Initialize a new project with PROJECT.md + ROADMAP.md in .project/, set up jira and studio, and route to the first sprint. Use when starting a new project, onboarding a new codebase, or setting up workflow infrastructure for the first time.

Why use Kickoff on TypingMind?

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

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

Which AI models can use Kickoff?

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 Kickoff?

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

Is the Kickoff AI skill free?

Yes. It is published on GitHub by koolamusic 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 👇