Puzzle Game
/puzzle
Build a puzzle game: grid/board state, move input, rule-based resolution (match-3 cascades, sokoban pushes, tile logic), scoring, and undo.
- GitHub stars
- 2,085 (repository stars as of 2026-10-21)
- License
- Apache-2.0
- Last commit
- 2026/10/09
- By
- gamedev-skills
Part of
Awesome Gamedev Agent Skills
74 portable SKILL.md skills for Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE and Roblox, with a router.
Listed from the author's README. GameSkill has not run this end to end yet. Agent support and install steps are as documented by the author.
Install
npx skills add gamedev-skills/awesome-gamedev-agent-skills --skill puzzleInstalls only this skill. Add -a claude-code (puts it in .claude/skills/), -a codex or -a cursor (.agents/skills/) to choose the agent, and -g to install it for your user instead of the project.
Commands are copied from the project's README. Check the repository before running anything on your machine.
Install for a specific agent
| Agents | -a | Folder |
|---|---|---|
| Claude Code | claude-code | .claude/skills/ |
| Codex | codex | .agents/skills/ |
| Cursor | cursor | .agents/skills/ |
| Gemini CLI | gemini-cli | .agents/skills/ |
| GitHub Copilot | github-copilot | .agents/skills/ |
| OpenCode | opencode | .agents/skills/ |
| Windsurf | windsurf | .windsurf/skills/ |
Add -a <flag> to the command. These are project folders; add -g to install for your user account instead.
What you get
- Worked steps: Board model + match detection; Resolve → collapse → refill → cascade; Undo via state snapshot or command
- A pitfalls section with the mistakes to avoid
- Bundled 1 reference doc the agent reads when needed
Good fit
- A match-3, sokoban, or grid-logic puzzle
Try this prompt
Build a match-3 board with cascades, scoring and undo.About this skill
Build a puzzle game: grid/board state, move input, rule-based resolution (match-3 cascades, sokoban pushes, tile logic), scoring, and undo. Use for a match-3, sokoban, or grid-logic puzzle.
From the puzzle SKILL.md in gamedev-skills/awesome-gamedev-agent-skills.
What's inside
- Core loop
- Must-have systems
- Design knobs
- Board model + match detection (logic separate from visuals)
- Resolve → collapse → refill → cascade (repeat to stability)
- Undo via state snapshot or command
- Composition (build it from these skills)
FAQ
More from Awesome Gamedev Agent Skills
See all 452D Platformer
Build a 2D platformer: run/jump control with coyote time, jump buffering, and variable jump height, plus tiled levels and hazards.
Behavior Trees & Utility AI
Build a behavior-tree runtime and a Utility AI system with response curves, plus hybrid agents where the behavior tree drives utility scoring.
Bevy ECS
Structure a Bevy app around ECS: plugins, components and resources, systems with Query and Commands, system ordering and Time.
Card Game
Build a card game: card data, deck/hand/discard zones, draw/shuffle/reshuffle, a turn structure, costs, and effect resolution.
Similar skills
Novel to Game
Agent skills for source-grounded adaptation of novels into games: cited design docs, target-runtime builds and evidence-based QA.
Novel to Game: Art Direction
Direct game art and creative vision.
Novel to Game: Book Analysis
Deconstruct a novel for game adaptation.
Novel to Game: Concept
Design game concepts from a novel.