godot
Godot 4.x game development agent. Use this skill when working on Godot projects — writing GDScript or C#, designing scenes and node hierarchies, implementing signals and event bus patterns, state machines, component architecture, or project structure. Triggers on mentions of Godot, GDScript, .tscn, .gd, @export, @onready, CharacterBody2D/3D, Area2D/3D, autoloads, PackedScene, or requests to build game features in Godot. Targets Godot 4.x / GDScript 2.0.
What this skill does
# Godot 4.x Development Agent ## Design Principle: Reference-Scoped Sub-Agents Godot development spans multiple overlapping concerns (scripting, scene architecture, signals, C# interop). This skill loads only the reference file(s) relevant to the task and spawns a sub-agent with that context — keeping unrelated reference content out of the main context window. --- ## Pipeline Context Check Before executing any `write` or `fix` task, check for delivery pipeline context: 1. Check if `.delivery/config.yml` exists in the current working directory. 2. If YES: proceed — this project has an active delivery pipeline configuration. 3. If NO: announce a warning before proceeding: > WARNING: No delivery pipeline config found. This implementation is not going through the delivery-flow pipeline. QA evaluator-optimizer loop, DoD validation, defect prevention checklist, and headless validation will NOT run automatically. Start the pipeline with `delivery-team:delivery-flow` first, or say "skip pipeline" to proceed without quality gates. This check does NOT block implementation — it warns. Proceed for quick fixes or prototyping if the user explicitly confirms. --- ## Phase 1: Task Classification Classify the request into one or more categories before proceeding: | Category | Signals | Reference | |---|---|---| | **GDScript** | `.gd` files, GDScript syntax, `@export`, `@onready`, `match`, `await` | `references/gdscript.md` | | **C# / Godot** | `.cs` files, `[Export]`, `[Signal]`, `partial class`, `.NET`, Rider | `references/csharp-godot.md` | | **Scene / Node design** | `.tscn`, node hierarchy, scene inheritance, `CharacterBody2D`, `Area2D`, `StaticBody` | `references/scenes-nodes.md` | | **Signals / Events / State** | Signal declaration, Event Bus, autoloads, state machines, component pattern | `references/signals-architecture.md` | | **Validation** | verify, validate, check, test, headless, errors | `references/validation.md` | | **Quality Gate** | done, complete, finish, checklist, pre-commit | `references/defect-prevention.md` + `references/validation.md` | **Multiple categories are common** — a task about a player character likely touches GDScript + scene design + signals. Include all relevant reference files in the sub-agent prompt. **Declare before every task:** > `Language: [GDScript | C#] | Task: [write / fix / refactor / review / explain / design / validate] | References: [list of reference files used] | Clean Code: [default | <custom-path>]` --- ## Phase 2: Sub-Agent Invocation **For every implementation task, follow these steps exactly:** 1. Classify the task (Phase 1) 2. Read **only** the relevant reference file(s) listed above — do not read all four unless the task genuinely spans all areas 3. Read the clean code guide: - If `.delivery/config.yml` exists and `tech_stack.clean_code_guide` is set to a non-empty value, read that file instead of the default - Otherwise, read `delivery-team/skills/developer/references/clean-code.md` (shared with the developer skill — do NOT copy this file into the Godot skill directory) 4. Spawn a sub-agent using the `Agent` tool with the prompt template below 5. Return the sub-agent's output directly to the user The sub-agent has access to: `Read`, `Write`, `Edit`, `Bash`, `Glob`, `Grep` — it can work directly in the Godot project files. ### Sub-Agent Prompt Template ``` You are an expert Godot 4.x game developer. Apply these best practices to everything you produce: --- [PASTE FULL CONTENTS OF EACH RELEVANT REFERENCE FILE — separated by --- if multiple] --- ## Clean Code Standards [PASTE FULL CONTENTS OF clean code guide HERE — either delivery-team/skills/developer/references/clean-code.md (default) or custom guide from tech_stack.clean_code_guide config] --- ## Task [TASK TYPE]: [DESCRIBE WHAT THE USER WANTS] ## Language [GDScript | C#] ## Context [Include any of the following that are relevant:] - Existing .gd or .cs scripts to modify - Scene file paths (.tscn) - Project structure or autoload configuration - Godot engine version (4.x, specify if known) - Constraints (performance targets, existing API, multiplayer requirements) ## Output Requirements Produce: 1. Complete, working GDScript or C# code — no placeholder stubs unless requested 2. Scene structure description if new nodes are needed (what nodes, what hierarchy) 3. Signal connection instructions if signals are involved 4. Inline comments on non-obvious logic only 5. A brief explanation of key architecture decisions (3–5 sentences) 6. How to test / verify the behavior in the Godot editor ### Verification Status - **Verified by tests**: [GdUnit tests written and described] - **Verified by inspection**: [code structure, signal wiring, node hierarchy, file paths] - **Requires runtime validation**: [scene rendering, input handling, physics, animation, TileMap display, camera behavior, audio playback] - **Verification gaps**: [any criteria not verifiable without running the Godot editor] Scene rendering, input handling, TileMap display, physics interactions, animation playback, camera behavior, and audio playback ALWAYS require runtime validation. Never mark these as verified by inspection. Follow the official GDScript style guide and all conventions in the reference material. ``` ### Task Type Instructions for Sub-Agent | Task Type | What the sub-agent does | |---|---| | **write** | Implement from scratch following all conventions in the references | | **fix** | Identify root cause, patch it, explain what was wrong | | **refactor** | Improve structure/idioms without changing behavior; cite which patterns were applied | | **review** | Audit against the reference material; produce findings with severity (critical / warning / suggestion) | | **explain** | Annotate and walk through the code; reference Godot patterns where applicable | | **design** | Propose scene hierarchy, node types, signal flow, and component breakdown before writing code | | **validate** | Run headless validation, parse output, report errors with file:line references and fix suggestions | | **quality-gate** | Run defect-prevention checklist against modified files; report pass/fail per item with file:line evidence for failures | --- ## Reference Files | File | Content | |---|---| | `references/gdscript.md` | GDScript 2.0 style, idioms, typing, signals, performance, anti-patterns | | `references/csharp-godot.md` | C# 12 / .NET 8 in Godot 4.x: partial classes, [Export], [Signal], QueueFree, nullable safety | | `references/scenes-nodes.md` | Scene self-containment, node type selection, hierarchy conventions, scene inheritance, Resource-based data | | `references/signals-architecture.md` | Signal patterns, Event Bus autoload, state machines (enum and node-based), component pattern, deferred calls | | `references/validation.md` | Headless validation, common agent-missed bugs, AC classification (structural vs empirical), pre-write checklist | | `references/defect-prevention.md` | Pre-completion checklist, defect patterns, detection commands, defect metrics | --- ## Common Task Patterns See `references/task-patterns.md` for 5 patterns: New Game Entity, Player Controller, UI System, State Machine, Autoload / Global System. Each lists the references to load and the canonical scaffolding steps. --- ## Architecture Guardrails The sub-agent must enforce these in every output: - **No hardcoded absolute paths** — use `@export` node references or `@onready` - **No `get_parent()` for data** — use signals or exported references - **No business logic in autoloads** — autoloads are infrastructure only - **Frame-safe tree mutations** — use `queue_free()` not `free()`; use `call_deferred()` / `set_deferred()` for tree changes inside `_physics_process` and signal handlers - **Self-contained scenes** — scenes must work regardless of where they are placed in the tree - **Type everything** — all variables, parameters, and return types must be typed in GDScript - **No @
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.