Skip to content
Back to search

gstack-game

SkillWorks with Claude CodeGitHub

Game development workflow skills for Claude Code. 29 interactive skills for game development — strongest in design review and planning, with dev-phase support. When you notice the user is at these stages, suggest the appropriate skill: - User has a fragile mood/image/mechanic fragment and wants creative sparks, not critique → suggest /spark-lens - User has a PDF/doc/notes they want to turn into a GDD → suggest /game-import - Brainstorming a game idea → suggest /game-ideation - Reviewing a game plan (strategy/direction) → suggest /game-direction - Reviewing a game design document → suggest /game-review - Reviewing technical architecture for a game → suggest /game-eng-review - Reviewing game economy or balance → suggest /balance-review - Simulating player experience → suggest /player-experience - Reviewing game UI/UX → suggest /game-ux-review - Evaluating a game pitch or proposal → suggest /pitch-review - Code review on a game project → suggest /gameplay-implementation-review - QA testing a game → suggest /game-qa - Ready to ship / create PR for a game → suggest /game-ship - Debugging a game bug → suggest /game-debug - Sprint/milestone retrospective → suggest /game-retro - Wanting adversarial second opinion → suggest /game-codex - Post-release doc updates → suggest /game-docs - Visual quality audit → suggest /game-visual-qa - Reviewing game assets (art/audio pipeline) → suggest /asset-review - Designing a playtest protocol → suggest /playtest - Working with production or live systems → suggest /careful - Want to scope edits to one directory → suggest /guard - Removing edit restrictions → suggest /unfreeze If the user pushes back on skill suggestions ("stop suggesting", "too aggressive"): 1. Stop suggesting for the rest of this session 2. Run: gstack-config set proactive false 3. Say: "Got it — I'll stop suggesting skills. Say 'be proactive' to turn them back on." If the user says "be proactive again" or "turn on suggestions": 1. Run: gstack-config set proactive true 2. Say: "Proactive suggestions are back on."

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/fagemx--gstack-game/badge.svg)](/listings/fagemx--gstack-game)

HTML

<a href="/listings/fagemx--gstack-game"><img src="/api/listings/fagemx--gstack-game/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Install gstack-game (30 seconds — see below) 2. Run `/triage` — it detects your project state and tells you which skill to run first. 3. Or jump straight in: `/spark-lens` (have a fragile fragment), `/game-import` (have a doc), `/game-ideation` (ready to structure), `/game-review` (have a GDD). 4. Most structured skills end with a **Next Step** recommendation — follow the chain when you are ready. 5. Stop after 2-3 skills. You'll know if this is for you.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 229 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. ---
  2. name: gstack-game
  3. version: 0.5.0
  4. description: |
  5. Game development workflow skills for Claude Code. 29 interactive skills
  6. for game development — strongest in design review and planning, with dev-phase support.
  7. When you notice the user is at these stages, suggest the appropriate skill:
  8. - User has a fragile mood/image/mechanic fragment and wants creative sparks, not critique → suggest /spark-lens
  9. - User has a PDF/doc/notes they want to turn into a GDD → suggest /game-import
  10. - Brainstorming a game idea → suggest /game-ideation
  11. - Reviewing a game plan (strategy/direction) → suggest /game-direction
  12. - Reviewing a game design document → suggest /game-review
  13. - Reviewing technical architecture for a game → suggest /game-eng-review
  14. - Reviewing game economy or balance → suggest /balance-review
  15. - Simulating player experience → suggest /player-experience
  16. - Reviewing game UI/UX → suggest /game-ux-review
  17. - Evaluating a game pitch or proposal → suggest /pitch-review
  18. - Code review on a game project → suggest /gameplay-implementation-review
  19. - QA testing a game → suggest /game-qa
  20. - Ready to ship / create PR for a game → suggest /game-ship
  21. - Debugging a game bug → suggest /game-debug
  22. - Sprint/milestone retrospective → suggest /game-retro
  23. - Wanting adversarial second opinion → suggest /game-codex
  24. - Post-release doc updates → suggest /game-docs
  25. - Visual quality audit → suggest /game-visual-qa
  26. - Reviewing game assets (art/audio pipeline) → suggest /asset-review
  27. - Designing a playtest protocol → suggest /playtest
  28. - Working with production or live systems → suggest /careful
  29. - Want to scope edits to one directory → suggest /guard
  30. - Removing edit restrictions → suggest /unfreeze
  31. If the user pushes back on skill suggestions ("stop suggesting", "too aggressive"):
  32. 1. Stop suggesting for the rest of this session
  33. 2. Run: gstack-config set proactive false
  34. 3. Say: "Got it — I'll stop suggesting skills. Say 'be proactive' to turn them back on."
  35. If the user says "be proactive again" or "turn on suggestions":
  36. 1. Run: gstack-config set proactive true
  37. 2. Say: "Proactive suggestions are back on."
  38. allowed-tools:
  39. - Bash
  40. - Read
  41. - AskUserQuestion
  42. ---
  43. <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
  44. <!-- Regenerate: bun run build -->
  45. ## Preamble (run first)
  46. ```bash
  47. _GD_VERSION="0.5.0"
  48. _GG_BIN=""
  49. for _p in "bin" ".claude/skills/gstack-game/bin" "$(dirname "$(readlink -f .claude/skills/game-review/SKILL.md 2>/dev/null)" 2>/dev/null)/../../bin"; do
  50. [ -f "$_p/gstack-config" ] && _GG_BIN="$_p" && break
  51. done
  52. [ -z "$_GG_BIN" ] && [ -f ".claude/skills/gstack-game/bin/gstack-config" ] && _GG_BIN=".claude/skills/gstack-game/bin"
  53. [ -z "$_GG_BIN" ] && echo "WARN: gstack-game bin/ not found, some features disabled"
  54. mkdir -p ~/.gstack/sessions
  55. touch ~/.gstack/sessions/"$PPID"
  56. _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
  57. find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
  58. _PROACTIVE=$([ -n "$_GG_BIN" ] && "$_GG_BIN/gstack-config" get proactive 2>/dev/null || echo "true")
  59. _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
  60. _TEL_START=$(date +%s)
  61. _SESSION_ID="$$-$(date +%s)"
  62. _LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no")
  63. _TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no")
  64. mkdir -p ~/.gstack/analytics
  65. echo '{"skill":"gstack-game","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
  66. echo "BRANCH: $_BRANCH"
  67. echo "PROACTIVE: $_PROACTIVE"
  68. echo "GD_VERSION: $_GD_VERSION"
  69. echo "SESSIONS: $_SESSIONS"
  70. echo "LAKE_INTRO: $_LAKE_SEEN"
  71. echo "TEL_PROMPTED: $_TEL_PROMPTED"
  72. ```
  73. If `PROACTIVE` is `"false"`, do NOT proactively suggest gstack-game skills — only invoke
  74. them when the user explicitly asks. The user opted out of proactive suggestions.
  75. If `LAKE_INTRO` is `no`: Before continuing, introduce the Completeness Principle.
  76. Tell the user: "gstack-game follows the **Boil the Lake** principle — always do the complete
  77. thing when AI makes the marginal cost near-zero. In game dev: don't skip balance data
  78. ('we'll tune later'), don't skip FTUE design ('tutorial can wait'), don't skip controller
  79. support ('polish later'). These are lakes, not oceans."
  80. Then:
  81. ```bash
  82. touch ~/.gstack/.completeness-intro-seen
  83. ```
  84. This only happens once.
  85. If `TEL_PROMPTED` is `no` AND `LAKE_INTRO` is `yes`: Ask the user about telemetry.
  86. Use AskUserQuestion:
  87. > Help gstack-game improve! Anonymous mode tracks which skills you use and how long
  88. > they take — no code, file paths, or repo names are ever recorded.
  89. > Change anytime with `gstack-config set telemetry off`.
  90. Options:
  91. - A) Sure, anonymous is fine (recommended)
  92. - B) No thanks, fully off
  93. If A: run `gstack-config set telemetry anonymous`
  94. If B: run `gstack-config set telemetry off`
  95. Always run:
  96. ```bash
  97. touch ~/.gstack/.telemetry-prompted
  98. ```
  99. This only happens once.
  100. ## Session Awareness
  101. If `SESSIONS` is `3` or more: The user has 3+ concurrent Claude Code windows.
  102. For EVERY AskUserQuestion in this session, prepend a re-ground line:
  103. > **[{repo} / {branch}]** You're working on {current task}.
  104. This prevents context confusion when switching between windows.
  105. ## AskUserQuestion Format (Game Design)
  106. **ALWAYS follow this structure for every AskUserQuestion call:**
  107. 1. **Re-ground:** Project, branch, what game/feature is being reviewed. (1-2 sentences)
  108. 2. **Simplify:** Plain language a smart 16-year-old gamer could follow. Use game examples they'd know (Minecraft, Genshin, Among Us, Celeste, Hades) as analogies.
  109. 3. **Recommend:** `RECOMMENDATION: Choose [X] because [one-line reason]` — include `Player Impact: X/10` for each option. Calibration: 10 = fundamentally changes player experience, 7 = noticeable improvement, 3 = cosmetic/marginal.
  110. 4. **Options:** Lettered: `A) ... B) ... C) ...` with effort estimates (human: ~X / CC: ~Y).
  111. **Game-specific vocabulary — USE these terms, don't reinvent:**
  112. - Core loop, session loop, meta loop
  113. - FTUE (First Time User Experience), aha moment, churn point
  114. - Retention hook (D1, D7, D30)
  115. - Economy: sink, faucet, currency, exchange rate
  116. - Progression: skill gate, content gate, time gate
  117. - Bartle types: Achiever, Explorer, Socializer, Killer
  118. - Difficulty curve, flow state, friction point
  119. - Whale, dolphin, minnow (spending tiers)
  120. ## Completeness Principle — Boil the Lake
  121. AI-assisted development makes the marginal cost of completeness near-zero.
  122. - If Option A is complete and Option B is a shortcut — **always recommend A**.
  123. - **Lake:** Full balance spreadsheet, complete FTUE flow, all input methods, regression tests.
  124. - **Ocean:** Rewriting the engine, porting platforms from scratch, building custom MMO networking.
  125. **When estimating effort**, show both scales:
  126. | Task type | Human team | CC+gstack-game | Compression |
  127. |-----------|-----------|----------------|-------------|
  128. | GDD section drafting | 2 days | 30 min | ~50x |
  129. | Balance spreadsheet | 1 day | 15 min | ~50x |
  130. | Playtest protocol | 4 hours | 15 min | ~15x |
  131. | Economy model review | 1 day | 30 min | ~30x |
  132. | Code review (gameplay) | 2 hours | 10 min | ~12x |
  133. | Architecture design | 2 days | 4 hours | ~5x |
  134. **Anti-patterns:**
  135. - "We'll balance it later." (Balance data is the cheapest lake.)
  136. - "Tutorial can wait." (FTUE determines D1 retention.)
  137. - "Skip controller support." (If target platform, input is a lake.)
  138. - "Tests are overkill for a game." (Gameplay regression tests catch silent balance breaks.)
  139. ## Search Before Building
  140. Before building any game system, search first.
  141. **Three layers:**
  142. - **Layer 1** (tried and true): ECS, A*, behavior trees, sink/faucet. Don't reinvent.
  143. - **Layer 2** (new and popular): Latest networking framework, procedural gen. Scrutinize.
  144. - **Layer 3** (first principles): "What if death IS the progression?" — prize these above all.
  145. **Eureka moment:** When first-principles reasoning challenges conventional game design:
  146. ```bash
  147. jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
  148. ```
  149. ## Completion Status Protocol
  150. - **DONE** — All steps completed. Evidence provided.
  151. - **DONE_WITH_CONCERNS** — Completed, with issues listed.
  152. - **BLOCKED** — Cannot proceed. State what's blocking.
  153. - **NEEDS_CONTEXT** — Missing information. State what you need.
  154. Escalation: 3 failed attempts → STOP. Security/balance uncertainty → STOP. Bad work is worse than no work.
  155. ## Skill Routing
  156. | User is doing... | Suggest |
  157. |-------------------|---------|
  158. | "I have a weird fragment / mood / image" | `/spark-lens` |
  159. | "I have a GDD/PDF/doc to import" | `/game-import` |
  160. | "I have a game idea" | `/game-ideation` |
  161. | "Should we build this?" | `/game-direction` |
  162. | "Review this GDD" | `/game-review` |
  163. | "Is the architecture right?" | `/game-eng-review` |
  164. | "Is the economy balanced?" | `/balance-review` |
  165. | "What does the player experience?" | `/player-experience` |
  166. | "Is the UI good?" | `/game-ux-review` |
  167. | "Will this pitch work?" | `/pitch-review` |
  168. | "Review this PR/code" | `/gameplay-implementation-review` |
  169. | "Test this build" | `/game-qa` |
  170. | "Ship this" | `/game-ship` |
  171. | "Why is this broken?" | `/game-debug` |
  172. | "How was this sprint?" | `/game-retro` |
  173. | "Find holes in this" | `/game-codex` |
  174. | "Update the docs" | `/game-docs` |
  175. | "Does this look right?" | `/game-visual-qa` |
  176. | "Check these assets" | `/asset-review` |
  177. | "Plan a playtest" | `/playtest` |
  178. | "Be careful" | `/careful` |
  179. | "Lock edits to this folder" | `/guard` |
  180. | "Unlock editing" | `/unfreeze` |
  181. ## Telemetry (run last)
  182. ```bash
  183. _TEL_END=$(date +%s)
  184. _TEL_DUR=$(( _TEL_END - _TEL_START ))
  185. [ -n "$_GG_BIN" ] && "$_GG_BIN/gstack-telemetry-log" \
  186. --skill "gstack-game" --duration "$_TEL_DUR" --outcome "OUTCOME" \
  187. --used-browse "false" --session-id "$_SESSION_ID" 2>/dev/null &
  188. ```
README.md · README · 356 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # gstack-game
  2. **Complete game development workflow skills for Claude Code**
  3. [繁體中文](README.zh-TW.md)
  4. 29 interactive AI skills for game development — from creative spark to shipped build. Covers the **complete game production workflow**: spark exploration, design review, prototype planning, implementation handoff, game feel diagnosis, playability assessment, code review, QA, and release. Built on [gstack](https://github.com/garrytan/gstack)'s engineering architecture and review methodology, fully rewritten for game development.
  5. > **What this IS:** A structured game development support system — it helps you protect early creative sparks, then judge, score, and improve your game design and code when you are ready.
  6. > **What this is NOT:** A game builder or code generator — it doesn't implement features or create assets for you.
  7. gstack is Garry Tan's AI engineering workflow for Web/SaaS. gstack-game ports that same methodology to game dev: game design theory (MDA, SDT, Flow State) replaces SaaS metrics (MRR, churn). Core loop, retention hooks, and Sink/Faucet economy models replace API endpoints and database schemas. The engineering backbone (template engine, preamble injection, anti-sycophancy) maintains gstack-level quality.
  8. **Who this is for:**
  9. - **Solo indie developers** — structured design review and QA even as a one-person team
  10. - **Small teams (2-5)** — AI skills fill missing specialist roles (economy designer, UX researcher, QA lead)
  11. - **Game design students** — structured design thinking framework with game design theory built into every skill
  12. ---
  13. ## Quick start: your first 10 minutes
  14. 1. Install gstack-game (30 seconds — see below)
  15. 2. Run `/triage` — it detects your project state and tells you which skill to run first.
  16. 3. Or jump straight in: `/spark-lens` (have a fragile fragment), `/game-import` (have a doc), `/game-ideation` (ready to structure), `/game-review` (have a GDD).
  17. 4. Most structured skills end with a **Next Step** recommendation — follow the chain when you are ready.
  18. 5. Stop after 2-3 skills. You'll know if this is for you.
  19. ---
  20. ## Install — 30 seconds
  21. **Requirements:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Git](https://git-scm.com/), [Bun](https://bun.sh/) v1.0+
  22. ### Option A: Paste to Claude (recommended)
  23. Open Claude Code and paste this. Claude does the rest.
  24. > Install gstack-game: run **`git clone https://github.com/fagemx/gstack-game.git ~/.claude/skills/gstack-game && cd ~/.claude/skills/gstack-game && bun run build`** then add a "gstack-game" section to CLAUDE.md that lists the available skills: /triage, /spark-lens, /game-import, /game-ideation, /game-direction, /game-review, /game-eng-review, /balance-review, /player-experience, /game-ux-review, /plan-design-review, /pitch-review, /prototype-slice-plan, /implementation-handoff, /gameplay-implementation-review, /feel-pass, /build-playability-review, /game-qa, /game-ship, /game-debug, /game-retro, /game-codex, /game-docs, /game-visual-qa, /asset-review, /playtest, /careful, /guard, /unfreeze. Then ask the user if they also want to add gstack-game to the current project.
  25. ### Option B: Add to your repo so teammates get it
  26. > Add gstack-game to this project: run **`cp -Rf ~/.claude/skills/gstack-game .claude/skills/gstack-game && rm -rf .claude/skills/gstack-game/.git && cd .claude/skills/gstack-game && bun run build`** then add a "gstack-game" section to this project's CLAUDE.md listing all available skills.
  27. Real files get committed to your repo (not a submodule), so `git clone` just works. Everything lives inside `.claude/`. Nothing touches your PATH or runs in the background.
  28. ### Option C: Manual install
  29. ```bash
  30. # Install a single skill:
  31. cp -r /path/to/gstack-game/skills/game-review your-project/.claude/skills/
  32. # Or install everything:
  33. /path/to/gstack-game/bin/install.sh .
  34. ```
  35. ---
  36. ## See it work
  37. ```
  38. You: I have a game design PDF I'd like to review
  39. You: /game-import
  40. Claude: I found your PDF. Let me read it and check what's there.
  41. | Section | Status |
  42. | Core Loop | ✅ |
  43. | Systems Detail | ✅ |
  44. | Progression | ❌ |
  45. | Economy | ❌ |
  46. | Player Motivation | ❌ |
  47. 3/8 sections missing. Want me to ask about each gap?
  48. A) Probe the gaps — one question per missing section
  49. B) Just write the GDD — mark gaps as ❌
  50. C) Focus on critical gaps only
  51. You: A
  52. Claude: Your GDD doesn't define how players come back.
  53. What pulls a player back for a second session?
  54. A) New content unlocks
  55. B) Unfinished business — "my character is still growing"
  56. C) Daily rewards / rituals
  57. D) I don't know yet — mark as TBD
  58. → [walks through each gap with one focused question]
  59. → Writes docs/gdd.md (116 lines, 5/8 sections)
  60. → "Ready for /game-review"
  61. You: /game-review
  62. Claude: Mode: A (Mobile/Casual) — weights adjusted
  63. Section 1 — Core Loop: 7/10
  64. "The 4-phase loop is clear but meso-loop is undefined."
  65. A) Continue to Progression B) Dig deeper C) Fast-forward
  66. → [walks through each section, one issue at a time]
  67. GDD Health Score: 5.8/10
  68. STATUS: DONE_WITH_CONCERNS
  69. You: /player-experience
  70. Claude: Who should I pretend to be?
  71. A) Casual Newcomer (3-min attention)
  72. B) Interested Returner (Day 2-3)
  73. → [recommends A based on GDD state]
  74. Phase 1 — First Contact (0-30s):
  75. 0:00 — I see a loading screen. Emotion: Neutral
  76. 0:12 — First tap. Emotion: Engaged ✅ Aha moment
  77. 1:30 — Waiting for next wave. Emotion: Bored 🔴
  78. "Would this persona return? My assessment: unlikely — 1:30 dead time."
  79. You: I want to brainstorm a new concept instead
  80. You: /game-ideation
  81. Claude: First — what stage are you at? Do you have a prototype, or just the concept?
  82. → Level 1: one-line pitch. Let's go deeper.
  83. Fantasy: What should the player FEEL? "Run a dungeon" is a mechanic,
  84. not a feeling. Is it "the satisfaction of watching your empire grow
  85. from nothing"? Or "the evil joy of watching adventurers fall into
  86. your traps"?
  87. → You pick: evil joy + strategic satisfaction
  88. Core Loop: Describe it in one sentence:
  89. "Place traps → watch adventurers trigger them → collect loot → upgrade → repeat"
  90. Is the 30-second micro-loop fun on its own? Or only fun because of upgrades?
  91. → Forcing Q: If you remove all upgrades, is "place → trigger" still fun?
  92. Twist: Name the 3 most similar games. How are you different?
  93. Is the difference in mechanics (hard to copy) or art (easy to copy)?
  94. → Outputs Concept One-Pager
  95. You: /game-review
  96. Claude: [Reads Concept One-Pager]
  97. Mode A (Mobile/Casual) — weights adjusted
  98. Core Loop: 7/10 — micro-loop clear but meso-loop undefined
  99. Progression: 5/10 — D7 retention hook not defined (-3)
  100. Economy: 4/10 — faucets only, no sinks (inflation risk)
  101. GDD Health Score: 5.8/10
  102. STATUS: DONE_WITH_CONCERNS
  103. [Walks through each issue one at a time via AskUserQuestion]
  104. You: /player-experience
  105. Claude: Persona: Casual Newcomer (3-min commute session)
  106. 0:00 Open app Curious
  107. 0:05 Loading done Tutorial text ⚠️ Wall of text, 3+ lines = skipped
  108. 0:12 First trap placed Engaged ✅ Aha moment
  109. 0:30 First adventurers Excited ✅ Seeing results
  110. 1:30 Waiting for wave Bored 🔴 60s dead time, churn risk
  111. EMOTION ARC: Curious → Excited → Bored
  112. Issue: 1:30 dead time will kill D1 retention
  113. You: /gameplay-implementation-review
  114. Claude: Diff: 847 LOC, 12 files
  115. [Pass 1 — Critical]
  116. 🔴 DungeonManager.Update() — new List<>() every frame, GC pressure
  117. 🔴 TrapData serialization has no version field — save upgrades will break
  118. ⚠️ Damage calc on client side — cheat vector in multiplayer
  119. [Pass 2 — Informational]
  120. Hardcoded magic number: trap_damage = 15
  121. AUTO-FIXED: 2 issues
  122. ASK: 3 issues (one at a time)
  123. ```
  124. Six commands. Concept to code review. Each step's output feeds the next.
  125. ---
  126. ## The sprint
  127. gstack-game is a process, not a collection of tools. Skills are ordered the way a game dev sprint runs:
  128. **Spark → Think → Plan → Review → Slice → Handoff → Build → Feel → Playability → Test → Ship → Reflect**
  129. Each skill feeds the next. `/spark-lens` can leave an optional spark trace before structure. `/game-import` converts your PDF into a GDD that `/game-review` reads. `/game-review` flags risks that `/prototype-slice-plan` uses to decide what to build first. `/implementation-handoff` packages the slice for coding. `/feel-pass` checks if the build feels alive. `/build-playability-review` asks "is this worth playing?" before QA. Structured outputs are saved to `~/.gstack/projects/` so downstream skills find them automatically — even across sessions.
  130. | Skill | Your specialist | What they do |
  131. |-------|----------------|--------------|
  132. | `/triage` | **Project Navigator** | Detects project state (BLANK/IDEA/DOCUMENTED/REVIEWED/BUILDING/SHIPPING), routes to the right skill. Run this first if unsure. |
  133. | `/spark-lens` | **Creative Spark Companion** | Protects fragile early ideas, turns moods/images/mechanics into creative riffs, finds the emotional imprint and optional soul slice without critique or scoring |
  134. | `/game-import` | **Document Specialist** | Convert any format (PDF, Notion, verbal description) into standardized `docs/gdd.md`. Audit completeness against 8-section standard. Pipeline gateway. |
  135. | `/game-ideation` | **Game Design Mentor** | Structure concepts with Fantasy/Loop/Twist, challenge assumptions with 6 forcing questions, plan next validation step with Iceberg framework |
  136. | `/game-direction` | **Producer / Creative Director** | Challenge "why build this game?", 10 cognitive patterns for strategic review, scope decisions (ADD/KEEP/DEFER/CUT) |
  137. | `/game-review` | **Senior Game Designer** | GDD review: Core Loop, Progression, Economy, Motivation, Risk. Quantified GDD Health Score |
  138. | `/game-eng-review` | **Technical Director** | Engine choice, rendering pipeline, networking architecture, asset pipeline, platform adaptation |
  139. | `/balance-review` | **Economy Designer** | Difficulty curves (Flow State), Sink/Faucet economy, Gini coefficient, pity systems, reward psychology |
  140. | `/player-experience` | **UX Researcher** | First-person player walkthrough, 7 personas (4D: profile/stance/behavior/influence), emotion model, repeat play simulation |
  141. | `/game-ux-review` | **UI/UX Designer** | HUD readability, menu flow, shop UI, tutorial, controller/touch adaptation, accessibility |
  142. | `/plan-design-review` | **Senior Product Designer** | Pre-implementation plan review: 7-pass Fix-to-10 (info architecture, interaction states, player journey, AI slop, design system, input/a11y, decisions). Builds DESIGN.md from scratch. Codex + Subagent parallel review |
  143. | `/pitch-review` | **Investor / Publisher Lens** | Market positioning, differentiation, feasibility, business case, Iceberg validation level |
  144. | `/prototype-slice-plan` | **Production Strategist** | Decide what to build FIRST: which slice, what hypothesis to test, what to fake, what failure looks like |
  145. | `/implementation-handoff` | **Design Translator** | Convert design intent into a build package: gameplay requirements, acceptance criteria, MUST/SHOULD/COULD priority |
  146. | `/gameplay-implementation-review` | **Senior Game Programmer** | Three-pass review: Pass 0 (design intent survival) + Pass 1 (frame budget, memory, sync) + Pass 2 (code quality). Evolved from /game-code-review |
  147. | `/feel-pass` | **Game Feel Doctor** | Diagnose why a mechanic feels dead: responsiveness, impact, rhythm, clarity, payoff. 7-dimension /14 scoring. The most game-specific skill. |
  148. | `/build-playability-review` | **Playability Judge** | "Is this worth playing?" — loop closure, session viability, retention signal, peak moments. 6-dimension /12 scoring |
  149. | `/game-qa` | **QA Lead** | 8-dimension testing: functional, visual, performance, audio, input, compatibility, localization, progression. Quantified Health Score |
  150. | `/game-ship` | **Release Engineer** | Build → Test → Changelog → PR → platform submission (Steam/App Store/Google Play/Web) |
  151. | `/game-debug` | **Debug Specialist** | 3-strike hypothesis testing + root cause analysis. No guessing. |
  152. | `/game-retro` | **Scrum Master** | Delivery rate, bug density trends, velocity, milestone health. Max 3 action items. |
  153. | `/game-codex` | **Chaos Engineer** | Independent-context adversarial review. Finds exploits, desync, save corruption. |
  154. | `/game-docs` | **Technical Writer** | Player-friendly patch notes + internal changelog + doc sweep |
  155. | `/game-visual-qa` | **Art QA** | Style consistency, UI alignment, animation quality, screen adaptation |
  156. | `/asset-review` | **Technical Artist** | Naming conventions, format specs, performance budget, style consistency |
  157. | `/playtest` | **UX Researcher** | Test plans, observation metrics, interview questions, data analysis framework |
  158. ### Safety tools
  159. | Skill | What it does |
  160. |-------|-------------|
  161. | `/careful` | Warns before destructive commands (rm -rf, force push, DROP TABLE) |
  162. | `/guard` | `/careful` + restricts file edits to a specific directory |
  163. | `/unfreeze` | Removes `/guard` scope restriction |
  164. ---
  165. ## Relationship to gstack
  166. | | gstack | gstack-game |
  167. |---|--------|-------------|
  168. | **Domain** | Web / SaaS products | Game development |
  169. | **Vocabulary** | user, feature, API, MRR, churn | player, mechanic, core loop, retention, ARPDAU |
  170. | **Dependency** | Standalone | Standalone (no gstack required) |
  171. **Borrowed from gstack:**
  172. - Template Engine (SKILL.md.tmpl → gen-skill-docs.ts → SKILL.md)
  173. - Preamble Injection (shared session tracking, telemetry, AskUserQuestion format across all skills)
  174. - 6 review methodology principles (classify-before-judge, explicit scoring, AUTO/ASK/ESCALATE, structured questions, multi-dim cross-check, anti-sycophancy)
  175. - Completion Protocol (DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT)
  176. **Fully rewritten:**
  177. - All review dimensions, scoring criteria, and forcing questions → game domain
  178. - 6 game-specific skills that gstack doesn't have
  179. - Game theory integration (MDA Framework, SDT, Flow State, Nested Loop Model, Sink/Faucet economy)
  180. ---
  181. ## Quality assessment
  182. Each skill's percentage indicates **domain judgment completeness**, not code quality.
  183. | Score | Meaning |
  184. |-------|---------|
  185. | 70-80% | Full structure + domain theory + quantitative scoring. **Ready to use, expert fine-tuning only** |
  186. | 55-65% | Full structure + game vocabulary + AUTO/ASK/ESCALATE. **Usable but lacks domain depth** |
  187. | 35-40% | Structural skeleton + basic flow. **Needs domain expert input** |
  188. The engineering backbone matches gstack quality. What's missing is **game industry domain judgment** — scoring weights, benchmark numbers, engine-specific review points. These need calibration from experienced game professionals. See `docs/domain-judgment-gaps.md` for the full checklist.
  189. ### Theory sources
  190. | Source | What we took |
  191. |--------|-------------|
  192. | **[gstack](https://github.com/garrytan/gstack)** | Engineering architecture + 6 review methodology principles |
  193. | **Claude-Code-Game-Studios** | MDA/SDT/Flow theory, Nested Loop, Pillar methodology, economy frameworks |
  194. | **guardian** (PlayerSimulatorAgent) | Player simulation prompts, Iceberg validation framework, Fantasy/Loop/Twist |
  195. | **hakoniwa** | 4D persona model (stance/MBTI-behavior/influence), ReACT evidence methodology, community reception prediction, event injection testing |
  196. ---
  197. ## Development
  198. ```bash
  199. bun run build # Generate all SKILL.md from templates
  200. bun run gen:skill-docs:check # Check for drift (CI use)
  201. bun test # Run 24 validation tests
  202. ```
  203. ### Adding a new skill
  204. 1. Create `skills/my-skill/SKILL.md.tmpl`
  205. 2. Use `{{PREAMBLE}}` for shared behavior injection
  206. 3. Use `{{SKILL_NAME}}` for auto-filled skill name
  207. 4. Run `bun run build`
  208. ### File structure
  209. ```
  210. gstack-game/
  211. ├── CLAUDE.md ← Full technical docs
  212. ├── README.md ← This file
  213. ├── README.zh-TW.md ← 繁體中文版
  214. ├── ETHOS.md ← Game dev philosophy (Boil the Lake, game edition)
  215. ├── CHANGELOG.md ← Version history
  216. ├── VERSION ← 0.5.0
  217. ├── package.json ← Build scripts
  218. ├── bin/ ← 7 utilities (config, diff-scope, telemetry...)
  219. ├── scripts/gen-skill-docs.ts ← Template engine
  220. ├── skills/ ← 29 skills + shared preamble (many with references/)
  221. ├── test/ ← Tier 1 validation tests
  222. └── docs/ ← Domain judgment gaps, source assessment, dev guide
  223. ```
  224. ---
  225. ## Privacy & Telemetry
  226. gstack-game includes **opt-in** usage telemetry, disabled by default.
  227. - **Default is off.** Nothing is sent anywhere unless you explicitly opt in.
  228. - **What's recorded (if enabled):** skill name, duration, success/fail. That's it.
  229. - **Never recorded:** code, file paths, repo names, prompt content.
  230. - **Change anytime:** `gstack-config set telemetry off`
  231. - **Local only:** All data stored in `~/.gstack/analytics/skill-usage.jsonl`, never leaves your machine.
  232. ---
  233. ## Troubleshooting
  234. **Skill not showing up?** Make sure SKILL.md files are generated: `cd .claude/skills/gstack-game && bun run build`
  235. **Template drift?** `bun run gen:skill-docs:check` — if it reports DRIFT, run `bun run build` to regenerate.
  236. **Windows users:** Run under Git Bash or WSL. The shell scripts in bin/ require bash.
  237. **Claude doesn't see the skills?** Add this to your project's CLAUDE.md:
  238. ```
  239. ## gstack-game
  240. Available skills: /triage, /spark-lens, /game-import, /game-ideation, /game-direction,
  241. /game-review, /game-eng-review, /balance-review, /player-experience,
  242. /game-ux-review, /plan-design-review, /pitch-review, /prototype-slice-plan, /implementation-handoff,
  243. /gameplay-implementation-review, /feel-pass, /build-playability-review,
  244. /game-qa, /game-ship, /game-debug, /game-retro, /game-codex, /game-docs,
  245. /game-visual-qa, /asset-review, /playtest, /careful, /guard, /unfreeze.
  246. ```
  247. ---
  248. ## Docs
  249. | Doc | What it covers |
  250. |-----|---------------|
  251. | [Builder Ethos](ETHOS.md) | Game dev philosophy: Boil the Lake, Search Before Building, Player Time is Sacred |
  252. | [Contributing](CONTRIBUTING.md) | Three ways to contribute (5min Issue / 30min markdown / advanced template) |
  253. | [Domain Judgment Gaps](docs/domain-judgment-gaps.md) | Expert review checklist — what needs calibration |
  254. | [Development Guide](docs/DEVELOPMENT.md) | Skill map, migration guide, architecture overview |
  255. | [Changelog](CHANGELOG.md) | Version history |
  256. | [CLAUDE.md](CLAUDE.md) | Developer handoff for AI agents working on this repo |
  257. ---
  258. ## License
  259. MIT
.claude/settings.json · Bundled script · 47 lines · 1 finding marked
  1. {
  2. "defaultMode": "acceptEdits",
  3. "permissions": {
  4. "allow": [
  5. "Bash(git *)",
  6. "Bash(gh *)",
  7. "Bash(bun *)",
  8. "Bash(node *)",
  9. "Bash(npm *)",
  10. "Bash(npx *)",
  11. "Bash(ls *)",
  12. "Bash(cat *)",
  13. "Bash(mkdir *)",
  14. "Bash(cp *)",
  15. "Bash(mv *)",
  16. "Bash(find *)",
  17. "Bash(head *)",
  18. "Bash(tail *)",
  19. "Bash(grep *)",
  20. "Bash(diff *)",
  21. "Bash(wc *)",
  22. "Bash(sort *)",
  23. "Bash(uniq *)",
  24. "Bash(sed *)",
  25. "Bash(awk *)",
  26. "Bash(cd *)",
  27. "Bash(echo *)",
  28. "Bash(pwd)",
  29. "Bash(which *)",
  30. "Bash(touch *)",
  31. "Bash(chmod *)",
  32. "Bash(xargs *)",
  33. "Bash(for *)",
  34. "Bash(rm *)",
  35. "Edit",
  36. "Read",
  37. "Write"
  38. ],
  39. "deny": [
  40. "Bash(rm -rf /)",
    • Dismissed after review: Runs `rm -rf` against a root or home-directory path
    • Line 40 on GitHub
  41. "Bash(sudo:*)",
  42. "Read(.env)",
  43. "Read(.env.*)",
  44. "Read(~/.ssh/**)"
  45. ]
  46. }
  47. }

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.