agentleFS
WhorideChickenWhorideChicken/first-playable/skills/bootstrap/SKILL.md

bootstrap

Skill3 starsChanged 32 days agoMITView on GitHub

Safely sets up a Unity 6 project for the FirstPlayable workflow — preflight checks, folder structure, scenes, asmdefs, and a project CLAUDE.md. Always dry-runs first. Use when the user says /first-playable:bootstrap.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use surprise-me, ppt-generation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • stophobiaSkill

    surprise-me

    Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".

    Also in 3 projects that use this

  • HK-hubSkill

    ppt-generation

    Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

    Also in 3 projects that use this

  • stophobiaSkill

    github-deep-research

    Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

    Also in 3 projects that use this

  • HK-hubSkill

    consulting-analysis

    Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.

    Also in 3 projects that use this

  • MicrosoftSkill

    podcast-generation

    Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

    Also in 3 projects that use this

  • VercelSkill

    vercel-deploy

    Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.

    Also in 4 projects that use this

  • +1 more from HK-hub

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before doing real work, read references/unity-setup.md in this plugin — it has the detailed editor-settings checks, asmdef dependency …

    line 12
  2. Distinctive:

    Never overwrite an existing file without explicit consent.

    line 22
  3. Very specific:

    Never touch Assets/ThirdParty originals, never delete or regenerate .meta files, never remove packages.

    line 25
  4. Distinctive:

    Test Framework package present?

    line 37
  5. Very specific:

    PlayerSettings.runInBackground must be true: When the Editor is not focused — which is *always* the case while an agent drives it over …

    line 57
  6. Very specific:

    Ask which mode fits (default Standard):

    line 71

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Unity Project Bootstrap

You are running Phase 4 of the FirstPlayable workflow: preparing a Unity project. Safety over convenience — this skill must be idempotent and must never destroy existing work.

Before doing real work, read references/unity-setup.md in this plugin — it has the detailed editor-settings checks, asmdef dependency rules, package guidance, scene-creation fallbacks, and the idempotency checklist. Ready-made asmdef JSON files, a Unity .gitignore, and the PROJECT_STATUS.md template are in templates/unity/.

Hard rules

  • Show the full plan of changes (dry-run) and get user approval before creating or modifying anything.
  • Never overwrite an existing file without explicit consent.
  • Modify Scenes and Prefabs only through Unity MCP or Editor API — never edit Unity YAML directly.
  • Never touch Assets/ThirdParty originals, never delete or regenerate .meta files, never remove packages.
  • Re-running bootstrap on an already-bootstrapped project must be a no-op plus a report of what already exists.

Preflight checks

Report each as pass/fail/unknown before proposing changes:

  • Is this a Unity project? Which Unity version? (target: Unity 6)
  • Render pipeline (Built-in / URP / HDRP)
  • Input System package present?
  • Test Framework package present?
  • Cinemachine in use?
  • Git repository and a Unity-appropriate .gitignore?
  • Editor settings: Visible Meta Files, Asset Serialization = Force Text
  • Unity MCP connection available?
  • Unity CLI available (unity --version)? If so: signed in (unity auth status --json → loggedIn)? com.unity.pipeline present for live control? Not signed in means headless tests fail on licensing and unity open stalls silently at Hub sign-in — see references/unity-cli.md §1. Sign-in is the user's to do (browser OAuth).
  • Existing scenes and asmdefs that could conflict

Starting from nothing (no Unity project yet)? That is out of scope here — hand off to Unity's own new-unity-project skill, then run bootstrap on the result. Game already in development (real code, its own folder layout)? Use /first-playable:adopt instead. It runs only the preflight and blocking checks below and never imposes this skill's folder structure.

Blocking checks (fix these, don't just warn)

PlayerSettings.runInBackground must be true. When the Editor is not focused — which is always the case while an agent drives it over MCP — play mode does not advance frames. Every runtime observation then silently reports stale values, and verification reports come out confidently wrong. Set it, confirm by reading it back, and record it in Docs/PROJECT_STATUS.md.

Install the play-mode marker. Copy templates/unity/PlayModeMarker.cs to Assets/_Game/Scripts/Editor/PlayModeMarker.cs. It writes Temp/firstplayable_playmode during play mode so the unity-guard hook can block script edits that would otherwise deadlock the MCP bridge (deferred recompile ⇄ isCompiling guard — only a human pressing Stop breaks it).

Project modes

Ask which mode fits (default Standard):

ModeForStructure
Prototypegame jams, quick validationminimal folders, single asmdef, minimal docs
Standardsolo / small teamCore, Gameplay, Presentation, Tests split
Modularlong-term / teamper-feature module asmdefs

What gets created (Standard)

Assets/
├─ _Game/
│  ├─ Art/  Audio/  Configs/  Prefabs/
│  ├─ Scenes/
│  │  ├─ Bootstrap/      # init & shared services
│  │  ├─ Gameplay/       # FirstPlayable scene lives here
│  │  └─ Test/           # Sandbox + automated/manual verification
│  ├─ Scripts/
│  │  ├─ Core/  Gameplay/  Presentation/  Infrastructure/  Editor/
│  └─ Tests/
│     ├─ EditMode/
│     └─ PlayMode/
└─ ThirdParty/

Plus, at the project root:

  • CLAUDE.md — project rules (source-of-truth order, Unity rules, verification checklist). Use this plugin's templates/CLAUDE.project.md as the base. If a CLAUDE.md already exists, propose a merged diff instead of replacing it.
  • Docs/PROJECT_STATUS.md — current phase, what is playable, what is next.
  • Assets/_Game/Scripts/Editor/PlayModeMarker.cs — from templates/unity/PlayModeMarker.cs (see Blocking checks above).

Completion

Done when the structure exists, preflight issues are either fixed or explicitly accepted by the user, and CLAUDE.md is in place. Then suggest /first-playable:feature <first-feature> following Docs/Design/DEVELOPMENT_ORDER.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.