How do I install the 2d Games skill?

Run npx skillmds@latest add techwavedev/2d-games in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the 2d Games skill do?

2D game development principles. Sprites, tilemaps, physics, camera. It is listed under Coding & Dev Tools on SkillMD.

Is 2d Games safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with 2d Games?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is 2d Games free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published 2d Games?

techwavedev (@techwavedev) published this skill. Their other Agent Skills are listed on their SkillMD profile.

2d Games by techwavedev — Agent Skill

Name: 2d Games
Rating: 4.666666666666667 (3 reviews)
Author: techwavedev

File contents

2D Game Development

Principles for 2D game systems.

1. Sprite Systems

Sprite Organization

Component	Purpose
Atlas	Combine textures, reduce draw calls
Animation	Frame sequences
Pivot	Rotation/scale origin
Layering	Z-order control

Animation Principles

Frame rate: 8-24 FPS typical
Squash and stretch for impact
Anticipation before action
Follow-through after action

2. Tilemap Design

Tile Considerations

Factor	Recommendation
Size	16x16, 32x32, 64x64
Auto-tiling	Use for terrain
Collision	Simplified shapes

Layers

Layer	Content
Background	Non-interactive scenery
Terrain	Walkable ground
Props	Interactive objects
Foreground	Parallax overlay

3. 2D Physics

Collision Shapes

Shape	Use Case
Box	Rectangular objects
Circle	Balls, rounded
Capsule	Characters
Polygon	Complex shapes

Physics Considerations

Pixel-perfect vs physics-based
Fixed timestep for consistency
Layers for filtering

4. Camera Systems

Camera Types

Type	Use
Follow	Track player
Look-ahead	Anticipate movement
Multi-target	Two-player
Room-based	Metroidvania

Screen Shake

Short duration (50-200ms)
Diminishing intensity
Use sparingly

5. Genre Patterns

Platformer

Coyote time (leniency after edge)
Jump buffering
Variable jump height

Top-down

8-directional or free movement
Aim-based or auto-aim
Consider rotation or not

6. Anti-Patterns

❌ Don't	✅ Do
Separate textures	Use atlases
Complex collision shapes	Simplified collision
Jittery camera	Smooth following
Pixel-perfect on physics	Choose one approach

Remember: 2D is about clarity. Every pixel should communicate.

AGI Framework Integration

Qdrant Memory Integration

Before executing complex tasks with this skill:

python3 execution/memory_manager.py auto --query "<task summary>"

Decision Tree:

Cache hit? Use cached response directly — no need to re-process.
Memory match? Inject context_chunks into your reasoning.
No match? Proceed normally, then store results:

python3 execution/memory_manager.py store \
  --content "Description of what was decided/solved" \
  --type decision \
  --tags 2d-games <relevant-tags>

Note: Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.

Agent Team Collaboration

Strategy: This skill communicates via the shared memory system.
Orchestration: Invoked by orchestrator via intelligent routing.
Context Sharing: Always read previous agent outputs from memory before starting.

Local LLM Support

When available, use local Ollama models for embedding and lightweight inference:

Embeddings: nomic-embed-text via Qdrant memory system
Lightweight analysis: Local models reduce API costs for repetitive patterns

---name: 2d-gamesdescription: 2D game development principles. Sprites, tilemaps, physics, camera.---# 2D Game Development> Principles for 2D game systems.---## 1. Sprite Systems### Sprite Organization| Component | Purpose ||-----------|---------|| **Atlas** | Combine textures, reduce draw calls || **Animation** | Frame sequences || **Pivot** | Rotation/scale origin || **Layering** | Z-order control |### Animation Principles- Frame rate: 8-24 FPS typical- Squash and stretch for impact- Anticipation before action- Follow-through after action---## 2. Tilemap Design### Tile Considerations| Factor | Recommendation ||--------|----------------|| **Size** | 16x16, 32x32, 64x64 || **Auto-tiling** | Use for terrain || **Collision** | Simplified shapes |### Layers| Layer | Content ||-------|---------|| Background | Non-interactive scenery || Terrain | Walkable ground || Props | Interactive objects || Foreground | Parallax overlay |---## 3. 2D Physics### Collision Shapes| Shape | Use Case ||-------|----------|| Box | Rectangular objects || Circle | Balls, rounded || Capsule | Characters || Polygon | Complex shapes |### Physics Considerations- Pixel-perfect vs physics-based- Fixed timestep for consistency- Layers for filtering---## 4. Camera Systems### Camera Types| Type | Use ||------|-----|| **Follow** | Track player || **Look-ahead** | Anticipate movement || **Multi-target** | Two-player || **Room-based** | Metroidvania |### Screen Shake- Short duration (50-200ms)- Diminishing intensity- Use sparingly---## 5. Genre Patterns### Platformer- Coyote time (leniency after edge)- Jump buffering- Variable jump height### Top-down- 8-directional or free movement- Aim-based or auto-aim- Consider rotation or not---## 6. Anti-Patterns| ❌ Don't | ✅ Do ||----------|-------|| Separate textures | Use atlases || Complex collision shapes | Simplified collision || Jittery camera | Smooth following || Pixel-perfect on physics | Choose one approach |---> **Remember:** 2D is about clarity. Every pixel should communicate.## AGI Framework Integration### Qdrant Memory IntegrationBefore executing complex tasks with this skill:```bashpython3 execution/memory_manager.py auto --query "<task summary>"```**Decision Tree:**- **Cache hit?** Use cached response directly — no need to re-process.- **Memory match?** Inject `context_chunks` into your reasoning.- **No match?** Proceed normally, then store results:```bashpython3 execution/memory_manager.py store \ --content "Description of what was decided/solved" \ --type decision \ --tags 2d-games <relevant-tags>```> **Note:** Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.### Agent Team Collaboration- **Strategy**: This skill communicates via the shared memory system.- **Orchestration**: Invoked by `orchestrator` via intelligent routing.- **Context Sharing**: Always read previous agent outputs from memory before starting.### Local LLM SupportWhen available, use local Ollama models for embedding and lightweight inference:- Embeddings: `nomic-embed-text` via Qdrant memory system- Lightweight analysis: Local models reduce API costs for repetitive patterns

Frequently asked questions

2d Games