Gat Milestone logo

Gat Milestone

Community
Yuki001
gat-milestone

Plan ordered GAT milestone handoff slices from overview and narrative documents, create the milestone roadmap and per-milestone brief skeletons, and stop before technical design or implementation. Use after foundational GAT documents are ready and before per-system design.

Overview

PublisherYuki001
Repositorygame-dev-skills
Skill namegat-milestone
Stars
104
Forks
13
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Yuki001 on GitHub. Read the source before you install it.

Installation

Install the Gat Milestone 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/Yuki001/game-dev-skills/tree/main/gat/.agents/skills/gat-milestone
  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/Yuki001/game-dev-skills.git /tmp/game-dev-skills
mkdir -p .claude/skills
cp -r /tmp/game-dev-skills/gat/.agents/skills/gat-milestone .claude/skills/gat-milestone
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gat Milestone 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 Gat Milestone 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 Gat Milestone 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.

Milestone

Codex Runtime

This skill is fully contained in the installed .agents directory. Resolve all linked resources relative to this SKILL.md; do not read workflow resources outside this packaged directory.

Before acting, read GAT Workflow. Read Directory Structure or Workflow Catalog only when their structure or ownership details are needed.

Use these packaged role profiles for every role-specific pass:

When the workflow says to spawn one of these roles, create a Codex subagent with that exact task name when collaboration is available. Give it the complete role profile, relevant source documents, confirmed decisions, template, and exact target paths; wait for it and review its result before continuing. This skill explicitly authorizes those named workflow subagents. If subagents are unavailable, perform the same pass yourself using the packaged role profile.

Treat the directory containing .agents as the repository root. All GAT project documents live under that root's gat/ directory. Use Codex filesystem tools and the environment's supported patch editor while preserving unrelated user changes.

Interpret AskUserQuestion in the procedure as a single concise user question. Use a structured choice UI only for a genuine 2-3 option decision; otherwise ask in ordinary dialogue and wait. Command examples use Codex skill syntax ($gat-*).

This skill plans milestone slices BEFORE per-system design and creates:

  • gat/milestone/milestone.md — the ordered milestone roadmap with status
  • gat/milestone/m{N}-<name>/ — per-milestone directory skeletons
  • gat/milestone/m{N}-<name>/m{N}-brief.md — milestone brief skeletons (all systems Pending, status planned)

It does NOT require any system GDD to exist. It does not create task lists, technical designs, prompt packs, or implementation files. Those belong to the downstream engineering workflow.

Phase 1: Validate Inputs

Fail if any of these are missing:

  • gat/overview/game.md
  • gat/overview/systems-index.md
  • gat/overview/art-direction.md

Do NOT fail when no system GDDs exist. Planning runs before design; the systems index's priorities and dependencies are sufficient input for slicing.

Read:

  • gat/overview/game.md
  • gat/overview/systems-index.md
  • gat/overview/art-direction.md
  • all existing gat/narrative/*.md (used to inform milestone boundaries)
  • ../../assets/templates/plan/milestone.md
  • ../../assets/templates/plan/m-brief.md
  • gat/milestone/milestone.md if it already exists
  • existing gat/milestone/m{N}-<name>/m{N}-brief.md files if any milestones are already planned

Phase 2: Hand Off To The Planner

Spawn gat-planner agent with all read content plus:

  • instruction to write or update gat/milestone/milestone.md as an ordered set of milestone slices (M01, M02, ...) with a status column (planned -> designing -> designed)
  • instruction to create a directory gat/milestone/m{N}-<name>/ for each planned milestone
  • instruction to author an m{N}-brief.md skeleton (template: ../../assets/templates/plan/m-brief.md) for each milestone, listing every in-scope system with status Pending and the milestone status planned
  • instruction to add an internal iteration plan to each brief using the template's repeated subsections;
  • instruction NOT to write system GDDs, content-data docs, art docs, task lists, technical designs, prompt packs, or code
  • planning focus from argument if provided

The planner should:

  • choose a small set of meaningful milestones that can be handed off one stage at a time
  • give each milestone a clear goal, player-facing outcome, and named system set
  • define what is in scope and explicitly out of scope for each milestone
  • use the systems index priorities + dependencies + narrative structure to slice; it does not need per-system rule detail
  • include overview, narrative (scoped range), and content context needed by a downstream engineering workflow
  • avoid technical architecture, file plans, coding tasks, and implementation sequencing
  • set each new milestone's status to planned

Phase 3: Review

Summarize how many milestones were planned, which comes first, and which directories/briefs were created.

Use AskUserQuestion:

  • Start designing the first milestone (Recommended) → Tell the user to run $gat-design <first-milestone> <system> or $gat-design <first-milestone> (continue)
  • Stop here

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gat Milestone AI skill do?

Plan ordered GAT milestone handoff slices from overview and narrative documents, create the milestone roadmap and per-milestone brief skeletons, and stop before technical design or implementation. Use after foundational GAT documents are ready and before per-system design.

Why use Gat Milestone on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Yuki001/game-dev-skills/tree/main/gat/.agents/skills/gat-milestone. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gat Milestone?

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 Gat Milestone?

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

Is the Gat Milestone AI skill free?

It is published on GitHub by Yuki001. Check the repository for licensing terms. 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 👇