concept-game-builder
Use when Codex should turn a concept, topic, tutorial, lesson, algorithm, system, workflow, or abstract idea into a playable browser game that teaches through interaction. Use for planning or implementing educational web games with the Game Studio plugin, including concept-to-mechanic translation, gameplay loop design, learning progression, and browser-game QA.
What this skill does
# Concept Game Builder
Create a browser game that teaches by making the player act on the concept.
This skill owns the learning design and concept-to-game translation; Game Studio
owns engine choice, runtime implementation, assets, UI, and playtesting.
## Core Workflow
1. State the learning goal in one sentence: what should the player understand,
predict, or do after playing?
2. Decide whether a game is the right medium. Use a game when the topic has
decisions, constraints, feedback loops, failure states, strategy, incentives,
sequencing, systems, or tradeoffs. If the request needs an explorable article
more than a game, route to `visual-learner` instead.
3. Start concrete. Put a playable challenge in the first viewport before
definitions, lectures, or long explanations.
4. Convert the concept into a playable model:
- player verbs
- state variables
- rules and constraints
- visible consequences
- success and failure conditions
- inspectable explanations after action
5. Use Game Studio for production planning and implementation:
- Load `game-studio:game-studio` or `$game-studio` after the learning model is
clear.
- Default to a 2D Phaser route unless the user asks for 3D, Three.js, React
Three Fiber, or a specific engine.
- Route HUD and overlays through `game-studio:game-ui-frontend` when present.
- Route browser QA through `game-studio:game-playtest` before calling the game
done.
6. Build or plan the smallest complete game that teaches the topic. Prefer one
polished core loop over many disconnected minigames.
## Game Design Contract
Define these before writing code:
- **Player mission:** a 10-30 second challenge the player can attempt with no
prior vocabulary.
- **Learning model:** the concept's variables, rules, and relationships.
- **Misconception:** the naive idea the game should test or overturn.
- **Player verbs:** actions that map directly to the concept, such as allocate,
route, tune, trade, predict, combine, debug, classify, or negotiate.
- **Feedback:** how the game shows consequences through motion, score, state,
resources, failure, or changed world behavior.
- **Progression:** 3-5 levels, rounds, or scenarios that add one concept at a
time.
- **Explanation timing:** explain after the player acts; keep text synchronized
with the current game state.
- **Inspection path:** hover, focus, click, pause, replay, or detail panels that
reveal the rule, formula, trace, or evidence behind the result.
## Game Studio Handoff
When handing the plan to Game Studio, include this compact brief:
```markdown
Learning goal:
Core loop:
Player verbs:
Concept model:
Progression:
UI/HUD needs:
Asset style:
Target runtime:
Playtest checks:
```
For implementation tasks, continue through Game Studio rather than inventing a
separate stack. Use its specialist routing for Phaser, Three.js, React Three
Fiber, UI, assets, and playtesting. If Game Studio is unavailable in the current
session, follow its defaults manually: 2D Phaser first, DOM HUD for menus and
learning panels, responsive controls, and browser playtest verification.
## Quality Rules
- Do not make a quiz with decorative motion and call it a game. The answer
choices must change game state, strategy, or consequences.
- Do not hide the concept behind lore. Theme should make the model easier to
remember, not replace the model.
- Do not front-load exposition. Let the player do something first, then name the
concept.
- Keep the first build small enough to finish and playtest in one session.
- Make win, loss, replay, reset, and pause states explicit.
- Keep touch, keyboard, and responsive layouts viable from the start.
- Expose toy-model assumptions when the numbers are illustrative.
- Verify with an actual browser when possible; check that the game renders,
responds to input, avoids overlapping text, and teaches the intended takeaway.
## Reference
Read [teaching-game-patterns.md](references/teaching-game-patterns.md) when
choosing mechanics for a topic or when the first concept-to-game mapping feels
too literal.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.