Behavior Trees & Utility AI
/ai-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.
- GitHub 星数
- 2,085 (所在仓库星数，统计于 2026-10-21)
- 许可证
- Apache-2.0
- 最近提交
- 2026/10/09
- 作者
- gamedev-skills
所属合集
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.
信息来自作者的 README。 GameSkill 还没完整跑过。支持的 Agent 和安装步骤以作者文档为准。
安装
npx skills add gamedev-skills/awesome-gamedev-agent-skills --skill ai-behavior-trees-utility-aiInstalls 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.
命令照搬项目 README。在本机运行前，请先看一眼仓库。
为指定 Agent 安装
| Agent | -a | 文件夹 |
|---|---|---|
| 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/ |
在命令后加 -a <参数>。以上是项目级文件夹；加 -g 则安装到你的用户目录。
包含内容
- A pitfalls section with the mistakes to avoid
- Bundled 4 reference docs the agent reads when needed
适合
- Implementing a reusable behavior-tree or utility-based decision system
- Tuning enemy/NPC decisions beyond a simple FSM
不适合
- Choosing between FSM/BT/steering or for pathfinding: use Game AI: FSM, Behavior Trees & Pathfinding instead
试试这条提示词
Build a reusable behavior tree with a blackboard for my enemy, then add utility scoring to choose its attacks.关于这个 Skill
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system (response curves — linear, exponential, sigmoid, quadratic — considerations, and action evaluators), plus hybrid BT-drives-Utility agents. Use when implementing a reusable behavior-tree or utility-based decision system, or tuning enemy/NPC decisions beyond a simple FSM, or when the user mentions behavior tree, blackboard, decorator, selector, sequence, tick status, utility AI, response/scoring curve, or consideration. For choosing between FSM/BT/steering or for pathfinding, use game-ai; for Unreal's BehaviorTree/Blackboard assets, use unreal-behavior-trees.
From the ai-behavior-trees-utility-ai SKILL.md in gamedev-skills/awesome-gamedev-agent-skills.
What's inside
- Architecture at a glance
- Utility scoring in one snippet
常见问题
搭配使用
作者标注的相关 Skills，或更适合相邻任务的 Skills。
Game AI: FSM, Behavior Trees & Pathfinding
NPC and enemy decision-making with state machines, behavior trees, steering and A* pathfinding, paired with your engine's navigation API.
Game Physics Tuning
Stable, good-feeling physics: fixed timestep with interpolation, mass and drag, CCD against tunneling, jitter fixes and collision layers.
Tower Defense
Build a tower defense: enemies pathing along lanes, wave spawning, towers that auto-target and fire, an economy, and lives.
FPS Shooter
Build a first-person shooter: move+mouse-look controller, hitscan or projectile shooting, weapons, health, and enemy AI.
Awesome Gamedev Agent Skills 中的更多 Skills
查看全部 40 个2D Platformer
Build a 2D platformer: run/jump control with coyote time, jump buffering, and variable jump height, plus tiled levels and hazards.
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.
Create Game Assets
Plan, generate, source, normalize, and validate cohesive visual game assets.
相似 skills
Playtest Report (Claude Code Game Studios)
Structured playtest report template, or turn existing playtest notes into structured feedback.
Universal Modder
Skills, tools and a fal MCP that let Claude Code mod PC games you own: recon, reverse engineering, generated assets, in-game testing.
sprite-gen
Generate clean 2D game sprites and animation atlases: state rows, alpha cleanup, frame extraction, runtime atlases.
Scenario Skills
Production-ready images, video, audio and 3D from any agent through the Scenario MCP, plus expert teams for Blender, Unreal and Unity.