* Add /vertical-slice skill, prototype overhaul, and workflow integration - Add /vertical-slice skill for pre-production validation (Phase 4 gate) - Overhaul /prototype skill with two-mode design: concept prototype (Phase 1) vs vertical slice (Phase 4), with clearer differentiation and higher standards for VS - Update prototyper agent to own both prototype and vertical-slice workflows - Add prototype-report.md and vertical-slice-report.md output templates - Update WORKFLOW-GUIDE, quick-start, skills-reference, agent-coordination-map, and skill-flow-diagrams to fully integrate both skills into the 7-phase pipeline - Remove orphaned empty quick-prototype/ directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * sync v1 counts + polish Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add entity inventory flow, relax vertical-slice gate, improve UX authoring prompts - /asset-spec: new Phase 0b entity & screen inventory when no argument and no existing inventory — reads GDDs/art-bible, proposes categorized list, writes design/assets/entity-inventory.md collaboratively - /asset-spec: entity/character target falls back to inline user description when no source doc exists, rather than failing - /gate-check: vertical slice changed from blocking to CONCERNS-only when absent; built-but-broken slice still fails; adds entity inventory as gate artifact - /ux-design: convert inline approval prompts to AskUserQuestion for structured option capture at key authoring decision points - workflow-catalog.yaml: entity-inventory step added to pre-production; UX spec min_count raised to 3; vertical-slice and prototype marked required: false with updated descriptions - .gitignore: exclude marrow/ eval tooling directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Add missing AskUserQuestion widgets to 7 skills Audit found 11 decision points across 7 skills where structured option prompts were missing — using plain text, auto-selection, or no gate at all. Skills patched: - create-epics: per-epic approval + producer CONCERNS verdict - sprint-plan: producer CONCERNS verdict with scope/timeline options - milestone-review: AT RISK / OFF TRACK producer verdicts require acknowledgement - retrospective: existing-retro handling converted from plain text [A]/[B] - quick-design: classification confirmation + draft approve/revise/redirect - tech-debt add mode: category (6 options) + effort (S/M/L/XL) structured capture - regression-suite: no-arg mode selection instead of silent auto-detect - hotfix: severity confirmation gate before workflow begins Also added AskUserQuestion to allowed-tools headers for retrospective, quick-design, tech-debt, regression-suite, and hotfix. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Prep v1 stable: fix WORKFLOW-GUIDE counts, stale agent names, and skill model fields - WORKFLOW-GUIDE.md: correct agent count (48→49), skill count (66/68→73), add 6 missing skills to Appendix B, fix Creative category count (2→4), replace 3 non-existent agent names with correct ue-*/unity-* specialists, add missing godot-csharp/gdextension specialists to hierarchy, fix production/stories/ paths → production/epics/ - coordination-rules.md: replace "not yet used" with opt-in env var note - quick-start.md: rename duplicate "Validate the concept" label → "Prototype the mechanic" - skill-flow-diagrams.md: remove duplicate legacy UX pipeline section - All 62 skills missing model: field now have explicit model: sonnet Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: comprehensive skill audit — consistency, UX, and flow gaps Two-pass audit fixing ~35 bugs across 41 files. Pre-production flow: - Brainstorm next-steps split into Path A (design-first) and Path B (prototype-first) — eliminates "prototype after architecture" confusion - /architecture-review added to pre-production flow in brainstorm and create-architecture handoffs - gate-check traceability check corrected to requirements-traceability.md - dev-story TR registry error now points to /architecture-review (not /create-epics) - start now writes production/stage.txt on first onboarding AskUserQuestion gaps filled: - balance-check, code-review, hotfix, day-one-patch, consistency-check all gain closing widgets and/or missing allowed-tools declarations - hotfix git branch creation now requires user confirmation - sprint-plan review-mode setup moved to Phase 0 (before gates run) - team-combat gains architecture→implementation approval gate - design-review APPROVED path consolidated from 3 widgets to 1 multiSelect All 9 team-* skills: - Phase 0 review-mode resolution added (solo/lean/full now respected) - team-audio output path fixed (design/gdd/ → design/audio/) - team-level final doc compilation delegated to level-designer subagent - team-narrative localization-lead added to composition list - team-qa sprint path fixed (flat files, not directories) - team-release NO-GO override captures written justification - team-live-ops Cancel verdict now explicitly BLOCKED Other fixes: - Art bible path standardized to design/art/art-bible.md (3 wrong refs) - AD-PHASE-GATE added to lean-mode skip list in director-gates.md - design-system duplicate 5d heading fixed; skeleton decline path added; mandatory agent spawns now respect review mode - story-readiness acceptance criteria thresholds now type-aware - create-stories gains multi-ADR and no-ADR handling guidance - consistency-check creates docs/consistency-failures.md on first run - retrospective frontmatter bash injection replaced with explicit Bash call - smoke-check ls -t gains PowerShell fallback - Conventional Commits format documented in coding-standards.md - gate-check: ADR acceptance gate, QA plan check, chain-of-verification tool-action requirement all added Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: expose --review flag in argument-hints for all team-* skills All 9 team-* skills already implement Phase 0 review-mode resolution internally (full/lean/solo), but none advertised [--review full|lean|solo] in their argument-hint. Users had no way to discover the per-run override. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add SECURITY.md with coordinated disclosure policy Defines scope, reporting process (GitHub private vulnerability reporting), contributor security guidelines for hooks/skills/agents, and 90-day coordinated disclosure timeline. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add CONTRIBUTING.md with framework contribution guidelines Covers what PRs are welcome, skill/hook/agent technical requirements, the collaborative principle, testing expectations, commit format, and platform compatibility requirements. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add v1.0.0-beta → v1.0 upgrade section to UPGRADING.md Documents the 17 commits since the beta tag: new /vertical-slice gate, entity inventory flow in /map-systems, AskUserQuestion widgets across 7 skills, --review flag exposure on team-* skills, bug fixes (#21, #36, #42, #43, #45), and the new CONTRIBUTING.md and SECURITY.md. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
12 KiB
Game Concept: [Working Title]
Created: [Date] Status: [Draft / Under Review / Approved]
Elevator Pitch
[1-2 sentences that capture the entire game. Should be compelling enough to make someone want to hear more. Format: "It's a [genre] where you [core action] in a [setting] to [goal]."
Test: Can someone who has never heard of this game understand what they'd be doing in 10 seconds? If not, simplify.]
Core Identity
| Aspect | Detail |
|---|---|
| Genre | [Primary genre + subgenre(s)] |
| Platform | [PC / Console / Mobile / Cross-platform] |
| Target Audience | [See Player Profile section below] |
| Player Count | [Single-player / Co-op / Multiplayer / MMO] |
| Session Length | [Typical play session: 10 min / 30 min / 1 hr / 2+ hr] |
| Monetization | [Premium / F2P / Subscription / none yet] |
| Estimated Scope | [Small (1-3 months) / Medium (3-9 months) / Large (9+ months)] |
| Comparable Titles | [2-3 existing games in the same space] |
Core Fantasy
[What power, experience, or feeling does the player get from this game? What can they do here that they can't do anywhere else?
The core fantasy is the emotional promise. It's not a feature list — it's the answer to "why would someone choose THIS game over anything else they could be doing?"
Examples of strong core fantasies:
- "You are a lone survivor building a new life in a hostile wilderness" (survival)
- "You command a civilization across millennia" (strategy)
- "You explore a vast, beautiful world at your own pace" (open world)
- "You master intricate combat and overcome impossible odds" (soulslike)]
Unique Hook
[What makes this game different from everything else in its genre? This is the single most important differentiator.
A strong hook passes the "and also" test: "It's like [comparable game], AND ALSO [unique thing]." If the "and also" doesn't spark curiosity, the hook needs work.
The hook should be:
- Explainable in one sentence
- Genuinely novel (not just a combination of existing features)
- Connected to the core fantasy (not a gimmick bolted on)
- Something that affects gameplay, not just aesthetics]
Player Experience Analysis (MDA Framework)
The MDA (Mechanics-Dynamics-Aesthetics) framework ensures we design from the player's emotional experience backward to the systems that create it.
Target Aesthetics (What the player FEELS)
Rank the following aesthetic goals for this game (1 = primary, mark N/A if not relevant). These come from the MDA framework's 8 aesthetic categories:
| Aesthetic | Priority | How We Deliver It |
|---|---|---|
| Sensation (sensory pleasure) | [1-8 or N/A] | [Visual beauty, audio design, haptics] |
| Fantasy (make-believe, role-playing) | [Priority] | [World, characters, player identity] |
| Narrative (drama, story arc) | [Priority] | [Plot structure, player-driven stories] |
| Challenge (obstacle course, mastery) | [Priority] | [Difficulty curve, skill ceiling] |
| Fellowship (social connection) | [Priority] | [Co-op, guilds, shared experiences] |
| Discovery (exploration, secrets) | [Priority] | [Hidden areas, emergent systems, lore] |
| Expression (self-expression, creativity) | [Priority] | [Build variety, cosmetics, creation tools] |
| Submission (relaxation, comfort zone) | [Priority] | [Low-stress loops, ambient gameplay] |
Key Dynamics (Emergent player behaviors)
[What behaviors do we WANT to emerge from our mechanics? What should players naturally start doing without being told?
Example: "Players will experiment with ability combinations to find synergies" Example: "Players will share discoveries with the community"]
Core Mechanics (Systems we build)
[What are the 3-5 mechanical systems that generate the dynamics and aesthetics above? These are the rules, verbs, and systems we actually implement.]
- [Mechanic 1 — e.g., "Real-time combat with stamina management"]
- [Mechanic 2 — e.g., "Procedurally generated dungeons with hand-crafted rooms"]
- [Mechanic 3 — e.g., "Crafting system with discoverable recipes"]
Player Motivation Profile
Understanding WHY players play helps us make every design decision. Based on Self-Determination Theory (SDT) and the Player Experience of Need Satisfaction (PENS) model.
Primary Psychological Needs Served
| Need | How This Game Satisfies It | Strength |
|---|---|---|
| Autonomy (freedom, meaningful choice) | [How does the player feel in control?] | [Core / Supporting / Minimal] |
| Competence (mastery, skill growth) | [How does the player feel skilled?] | [Core / Supporting / Minimal] |
| Relatedness (connection, belonging) | [How does the player feel connected?] | [Core / Supporting / Minimal] |
Player Type Appeal (Bartle Taxonomy)
Which player types does this game primarily serve?
- Achievers (goal completion, collection, progression) — How: [...]
- Explorers (discovery, understanding systems, finding secrets) — How: [...]
- Socializers (relationships, cooperation, community) — How: [...]
- Killers/Competitors (domination, PvP, leaderboards) — How: [...]
Flow State Design
Flow occurs when challenge matches skill. How does this game maintain flow?
- Onboarding curve: [How do the first 10 minutes teach the player?]
- Difficulty scaling: [How does challenge grow with player skill?]
- Feedback clarity: [How does the player know they're improving?]
- Recovery from failure: [How quickly can they try again? Is failure punishing or educational?]
Core Loop
Moment-to-Moment (30 seconds)
[What is the player physically doing most of the time? The most basic, repeated action. This MUST be intrinsically satisfying — if the 30-second loop isn't fun in isolation, no amount of progression will save the game.]
Short-Term (5-15 minutes)
[What objective or cycle structures the moment-to-moment play? Encounters, puzzles, rounds, quests. This is where "one more turn" or "one more run" psychology lives.]
Session-Level (30-120 minutes)
[What does a full play session look like? What does the player accomplish? This should end with a natural stopping point AND a reason to come back.]
Long-Term Progression
[How does the player grow over days/weeks? Character progression, unlocks, story advancement, mastery. What is the player working toward?]
Retention Hooks
[What specifically brings the player back for their next session?]
- Curiosity: [Unanswered questions, unexplored areas, locked content]
- Investment: [Progress they don't want to lose, characters they care about]
- Social: [Friends playing, guild obligations, shared goals]
- Mastery: [Skills to improve, challenges to overcome, rankings to climb]
Game Pillars
Design pillars are non-negotiable principles that guide EVERY decision. When two design choices conflict, pillars break the tie. Keep to 3-5 pillars.
Real AAA examples:
- God of War: "Intense combat", "Father-son story", "World exploration"
- Hades: "Fast fluid combat", "Narrative depth through repeated runs"
- The Last of Us: "Story as essential", "AI partners build relationships", "Stealth encouraged"
Pillar 1: [Name]
[One sentence defining this non-negotiable design principle.]
Design test: [A concrete decision this pillar would resolve. "If we're debating between X and Y, this pillar says we choose __."]
Pillar 2: [Name]
[Definition]
Design test: [Decision it resolves]
Pillar 3: [Name]
[Definition]
Design test: [Decision it resolves]
Anti-Pillars (What This Game Is NOT)
Anti-pillars are equally important — they prevent scope creep and keep the vision focused. Every "no" protects the "yes."
- NOT [thing]: [Why this is explicitly excluded and what it would compromise]
- NOT [thing]: [Why]
- NOT [thing]: [Why]
Inspiration and References
| Reference | What We Take From It | What We Do Differently | Why It Matters |
|---|---|---|---|
| [Game 1] | [Specific mechanic, feeling, or approach] | [Our twist] | [What it validates about our concept] |
| [Game 2] | [What we learn] | [Our twist] | [Validation] |
| [Game 3] | [What we learn] | [Our twist] | [Validation] |
Non-game inspirations: [Films, books, music, art, real-world experiences that influence the tone, world, or feel. Great games often pull from outside the medium.]
Target Player Profile
[Be specific. "Gamers" is not a target audience.]
| Attribute | Detail |
|---|---|
| Age range | [e.g., 18-35] |
| Gaming experience | [Casual / Mid-core / Hardcore] |
| Time availability | [e.g., "30-minute sessions on weeknights, longer on weekends"] |
| Platform preference | [Where they play most] |
| Current games they play | [2-3 specific titles] |
| What they're looking for | [The unmet need this game fills] |
| What would turn them away | [Dealbreakers for this audience] |
Technical Considerations
| Consideration | Assessment |
|---|---|
| Recommended Engine | [Godot / Unity / Unreal and why — consider scope, team expertise, platform targets] |
| Key Technical Challenges | [What's technically hard about this game?] |
| Art Style | [Pixel / 2D / 2.5D / 3D stylized / 3D realistic] |
| Art Pipeline Complexity | [Low (asset store + modifications) / Medium (custom 2D) / High (custom 3D)] |
| Audio Needs | [Minimal / Moderate / Music-heavy / Adaptive] |
| Networking | [None / P2P / Client-Server / Dedicated Servers] |
| Content Volume | [Estimate: X levels, Y items, Z hours of gameplay] |
| Procedural Systems | [Any procedural generation? What scope?] |
Risks and Open Questions
Design Risks
[Things that could make the game unfun or uncompelling]
- [Risk 1 — e.g., "Core loop may not sustain sessions > 30 minutes"]
- [Risk 2 — e.g., "Player motivation unclear after main story ends"]
Technical Risks
[Things that could be hard or impossible to build]
- [Risk 1 — e.g., "Procedural generation quality is unproven"]
- [Risk 2 — e.g., "Networking for 100+ players may require dedicated infrastructure"]
Market Risks
[Things that could prevent commercial success]
- [Risk 1 — e.g., "Genre is saturated with established competitors"]
- [Risk 2 — e.g., "Target audience may be too niche for financial sustainability"]
Scope Risks
[Things that could blow the timeline]
- [Risk 1 — e.g., "Content volume exceeds team capacity"]
- [Risk 2 — e.g., "Feature X depends on technology we haven't prototyped"]
Open Questions
[Things that need prototyping or research before we can answer]
- [Question 1 — and how we plan to answer it]
- [Question 2 — and what prototype would resolve it]
MVP Definition
[The absolute minimum version that validates the core hypothesis. The MVP answers ONE question: "Is the core loop fun?"]
Core hypothesis: [The single statement the MVP tests, e.g., "Players find the combat-crafting loop engaging for 30+ minute sessions"]
Required for MVP:
- [Essential feature 1 — directly tests the hypothesis]
- [Essential feature 2]
- [Essential feature 3]
Explicitly NOT in MVP (defer to later):
- [Feature that's nice but doesn't test the hypothesis]
- [Feature that adds scope without validating the core]
Scope Tiers (if budget/time shrinks)
| Tier | Content | Features | Timeline |
|---|---|---|---|
| MVP | [Minimal] | [Core loop only] | [X weeks] |
| Vertical Slice | [One complete area] | [Core + progression] | [X weeks] |
| Alpha | [All areas, placeholder] | [All features, rough] | [X weeks] |
| Full Vision | [Complete content] | [All features, polished] | [X weeks] |
Next Steps
- Get concept approval from creative-director
- Fill in CLAUDE.md technology stack based on engine choice (
/setup-engine) - Create game pillars document (
/design-reviewto validate) - Prototype core idea (
/prototype [core-mechanic]) — before writing GDDs, validate the concept is worth designing - If prototype PROCEEDS: Decompose concept into systems (
/map-systems) - Design each system (
/design-system [system-name]) — use prototype learnings in Tuning Knobs and Formulas sections - Build vertical slice in Pre-Production (
/vertical-slice) — validate full game loop before committing to Production - Validate core loop with playtest (
/playtest-report) - Plan first milestone (
/sprint-plan new)