Guided Onboarding
This skill writes one file:
production/review-mode.txt
(review mode config set in Phase 3b).
This skill is the entry point for new users. It does NOT assume you have a game idea, an engine preference, or any prior experience. It asks first, then routes you to the right workflow.
Phase 1: Detect Project State
Before asking anything, silently gather context so you can tailor your guidance. Do NOT show these results unprompted — they inform your recommendations, not the conversation opener.
Check:
- Engine configured? Read
.claude/docs/technical-preferences.md
. If the Engine field contains , the engine is not set.
- Game concept exists? Check for
design/gdd/game-concept.md
.
- Source code exists? Glob for source files in (, , , , , , , ).
- Prototypes exist? Check for subdirectories in .
- Design docs exist? Count markdown files in .
- Production artifacts? Check for files in or .
Store these findings internally to validate the user's self-assessment and tailor recommendations.
Phase 2: Ask Where the User Is
This is the first thing the user sees. Use
with these exact options so the user can click rather than type:
- Prompt: "Welcome to Claude Code Game Studios! Before I suggest anything, I'd like to understand where you're starting from. Where are you at with your game idea right now?"
- Options:
- — I don't have a game concept at all. I want to explore and figure out what to make.
- — I have a rough theme, feeling, or genre in mind (e.g., "something with space" or "a cozy farming game") but nothing concrete.
- — I know the core idea — genre, basic mechanics, maybe a pitch sentence — but haven't formalized it into documents yet.
- — I already have design docs, prototypes, code, or significant planning done. I want to organize or continue the work.
Wait for the user's selection. Do not proceed until they respond.
Phase 3: Route Based on Answer
If A: No idea yet
The user needs creative exploration before anything else.
- Acknowledge that starting from zero is completely fine
- Briefly explain what does (guided ideation using professional frameworks — MDA, player psychology, verb-first design). Mention that it has two modes: for fully open exploration, or if they have even a vague theme (e.g., "space", "cozy", "horror").
- Recommend running as the next step, but invite them to use a hint if something comes to mind
- Show the recommended path:
Concept phase:
- — discover your game concept
- — configure the engine (brainstorm will recommend one)
- — throwaway concept build: validate the core idea is fun before designing (1–3 days)
- — define visual identity (uses the Visual Identity Anchor brainstorm produces)
- — decompose the concept into systems
- — author a GDD for each MVP system
- — cross-system consistency check
- — validate readiness before architecture work
Architecture phase:
- — produce the master architecture blueprint and Required ADR list
/architecture-decision (×N)
— record key technical decisions, following the Required ADR list
- — compile decisions into an actionable rules sheet
- — validate architecture coverage
Pre-Production phase:
- — author UX specs for key screens (main menu, HUD, core interactions)
- — production-quality end-to-end build to validate the full game loop
- — document each vertical slice playtest session
- — map systems to epics
- — break epics into implementable stories
- — plan the first sprint
Production phase: → pick up stories with
If B: Vague idea
- Ask them to share their vague idea — even a few words is enough
- Validate the idea as a starting point (don't judge or redirect)
- Recommend running to develop it
- Show the recommended path:
Concept phase:
- — develop the idea into a full concept
- — configure the engine
- — throwaway concept build: validate the core idea is fun before designing (1–3 days)
- — define visual identity (uses the Visual Identity Anchor brainstorm produces)
- — decompose the concept into systems
- — author a GDD for each MVP system
- — cross-system consistency check
- — validate readiness before architecture work
Architecture phase:
- — produce the master architecture blueprint and Required ADR list
/architecture-decision (×N)
— record key technical decisions, following the Required ADR list
- — compile decisions into an actionable rules sheet
- — validate architecture coverage
Pre-Production phase:
- — author UX specs for key screens (main menu, HUD, core interactions)
- — production-quality end-to-end build to validate the full game loop
- — document each vertical slice playtest session
- — map systems to epics
- — break epics into implementable stories
- — plan the first sprint
Production phase: → pick up stories with
If C: Clear concept
- Ask them to describe their concept in one sentence — genre and core mechanic. Use plain text, not AskUserQuestion (it's an open response).
- Acknowledge the concept, then use to offer two paths:
- Prompt: "How would you like to proceed?"
- Options:
- — Run to structure it into a proper game concept document
- — Go to now and write the GDD manually afterward
- Show the recommended path:
Concept phase:
- or — (their pick from step 2)
- — throwaway concept build: validate the core idea is fun before designing (1–3 days)
- — define visual identity (after brainstorm if run, or after concept doc exists)
- — validate the concept doc
- — decompose the concept into individual systems
- — author a GDD for each MVP system
- — cross-system consistency check
- — validate readiness before architecture work
Architecture phase:
- — produce the master architecture blueprint and Required ADR list
/architecture-decision (×N)
— record key technical decisions, following the Required ADR list
- — compile decisions into an actionable rules sheet
- — validate architecture coverage
Pre-Production phase:
- — author UX specs for key screens (main menu, HUD, core interactions)
- — production-quality end-to-end build to validate the full game loop
- — document each vertical slice playtest session
- — map systems to epics
- — break epics into implementable stories
- — plan the first sprint
Production phase: → pick up stories with
If D: Existing work
-
Share what you found in Phase 1:
- "I can see you have [X source files / Y design docs / Z prototypes]..."
- "Your engine is [configured as X / not yet configured]..."
-
Sub-case D1 — Early stage (engine not configured or only a game concept exists):
- Recommend first if engine not configured
- Then for a gap inventory
Sub-case D2 — GDDs, ADRs, or stories already exist:
- Explain: "Having files isn't the same as the template's skills being able to use them. GDDs might be missing required sections. checks this specifically."
- Recommend:
- — understand what phase and what's missing entirely
- — audit whether existing artifacts are in the right internal format
-
Show the recommended path for D2:
- — phase detection + existence gaps
- — format compliance audit + migration plan
- — if engine not configured
/design-system retrofit [path]
— fill missing GDD sections
/architecture-decision retrofit [path]
— add missing ADR sections
- — bootstrap the TR requirement registry
- — validate readiness for next phase
Phase 3c: Write Initial Stage File
After confirming the starting path (and before asking about review mode), write the initial stage to
. Create the
directory if it does not exist.
Stage mapping:
- Path A, B, or C (starting from scratch): write
- Path D, existing project, engine not configured or only a game concept exists: write
- Path D, existing project with GDDs but no architecture documents: write
- Path D, existing project with full architecture (ADRs, architecture doc): write
Do this silently — no "May I write?" needed for this single-line file.
Say: "I've set
to
— this anchors your status line and stage detection."
Phase 3b: Set Review Mode
Check if
production/review-mode.txt
already exists.
If it exists: Read it and show the current mode — "Review mode is set to
." — then proceed to Phase 4. Do not ask again.
If it does not exist: Use
:
- Prompt: "One setup choice: how much design review would you want as you work through the workflow?"
- Options:
- — Director specialists review at each key workflow step. Best for teams, learning the workflow, or when you want thorough feedback on every decision.
- — Directors only at phase gate transitions (/gate-check). Skips per-skill reviews. Balanced approach for solo devs and small teams.
- — No director reviews at all. Maximum speed. Best for game jams, prototypes, or if the reviews feel like overhead.
Write the choice to
production/review-mode.txt
immediately after the user
selects — no separate "May I write?" needed, as the write is a direct
consequence of the selection:
Create the
directory if it does not exist.
Phase 4: Confirm Before Proceeding
After presenting the recommended path, use
to ask the user which step they'd like to take first. Never auto-run the next skill.
- Prompt: "Would you like to start with [recommended first step]?"
- Options:
Yes, let's start with [recommended first step]
I'd like to do something else first
Phase 5: Hand Off
When the user confirms their next step, respond with a single short line: "Type
to begin." Nothing else. Do not re-explain the skill or add encouragement. The
skill's job is done.
Verdict: COMPLETE — user oriented and handed off to next step.
Edge Cases
- User picks D but project is empty: Gently redirect — "It looks like the project is a fresh template with no artifacts yet. Would Path A or B be a better fit?"
- User picks A but project has code: Mention what you found — "I noticed there's already code in . Did you mean to pick D (existing work)?"
- User is returning (engine configured, concept exists): Skip onboarding entirely — "It looks like you're already set up! Your engine is [X] and you have a game concept at
design/gdd/game-concept.md
. Review mode: [read from production/review-mode.txt, or 'lean (default)' if missing]
. Want to pick up where you left off? Try or just tell me what you'd like to work on."
- User doesn't fit any option: Let them describe their situation in their own words and adapt.
Collaborative Protocol
- Ask first — never assume the user's state or intent
- Present options — give clear paths, not mandates
- User decides — they pick the direction
- No auto-execution — recommend the next skill, don't run it without asking
- Adapt — if the user's situation doesn't fit a template, listen and adjust