Skip to content
mcp/skillhub

Agent Skill

AI Behavior Trees Utility AI skill

ai-behavior-trees-utility-aigamedev-skills/awesome-gamedev-agent-skillsskills/disciplines/ai-behavior-trees-utility-ai/SKILL.md

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.

2.7kApache-2.0

always on

158 tokname + description

once used

1,840 tokSKILL.md body

bundled files

435 KB

repo stars

2.7kGitHub

Install the AI Behavior Trees Utility AI skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill ai-behavior-trees-utility-ai

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/gamedev-skills/awesome-gamedev-agent-skills.git /tmp/awesome-gamedev-agent-skills
mkdir -p ~/.claude/skills
cp -R /tmp/awesome-gamedev-agent-skills/skills/disciplines/ai-behavior-trees-utility-ai ~/.claude/skills/ai-behavior-trees-utility-ai

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description158 tok
When the agent uses itThe SKILL.md instructions1,840 tok
Only if opened4 bundled files (35 KB)varies

Until it is used, ai-behavior-trees-utility-ai costs about 8.6× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 75 skills from gamedev-skills/awesome-gamedev-agent-skills would load 6,712 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Behavior Trees & Utility AI
  • When to use
  • Core workflow
  • Architecture at a glance
  • Utility scoring in one snippet
  • Pitfalls
  • References
  • Related skills

More skills from gamedev-skills/awesome-gamedev-agent-skills

All skills in this repo
  1. audio-designgamedev-skills/awesome-gamedev-agent-skills

    Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization. Engine-neutral. Use when the user mentions audio mixing, audio buses, adaptive/dynamic music, ducking, SFX variation, music layers, or syncing gameplay to the beat.

    2.7k81 tok idle · 1,677 in use
  2. bevy-ecsgamedev-skills/awesome-gamedev-agent-skills

    Structure a Bevy app around its Entity Component System: build the App with plugins, define Component/Resource types, write systems with Query/Res/Commands, filter and order systems, and use the Time resource for frame-rate-independent motion. Use when building or debugging a Bevy game in Rust — when the user mentions Bevy, ECS, App::new, add_systems, Query, Commands, components/systems, or a Cargo.toml depending on bevy.

    2.7k100 tok idle · 2,426 in use
  3. camera-systemsgamedev-skills/awesome-gamedev-agent-skills

    Build game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person orbit with collision and first-person look; plus multi-target framing and a shake hook. Engine-neutral techniques that pair with the engine's camera node and rigs like Unity Cinemachine or Godot Camera2D/PhantomCamera. Use when the user mentions camera follow, follow camera, deadzone, look-ahead, camera smoothing, camera bounds/ limits, third-person camera, orbit camera, first-person look, Cinemachine, or camera jitter.

    2.7k127 tok idle · 2,000 in use
  4. card-gamegamedev-skills/awesome-gamedev-agent-skills

    Build a card game: card data, deck/hand/discard zones, draw/shuffle/reshuffle, a turn structure, costs, and effect resolution. Use for a deckbuilder, TCG/CCG, or roguelike deckbuilder.

    2.7k54 tok idle · 1,564 in use
  5. create-game-assetsgamedev-skills/awesome-gamedev-agent-skills

    Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset briefs.

    2.7k252 tok idle · 1,665 in use
  6. dialogue-systemsgamedev-skills/awesome-gamedev-agent-skills

    Build branching dialogue and narrative — a node/choice graph with conditions, variables, and localization hooks — and choose between authoring tools Ink and Yarn Spinner or a custom data-driven runner. Engine-neutral. Use when the user mentions dialogue system, branching dialogue, conversation tree, choices, Ink (.ink), Yarn Spinner (.yarn), or NPC dialogue.

    2.7k75 tok idle · 1,788 in use
  7. fps-shootergamedev-skills/awesome-gamedev-agent-skills

    Build a first-person shooter: move+mouse-look controller, hitscan or projectile shooting, weapons, health, and enemy AI. Use for an FPS, or tuning aim feel, time-to-kill, recoil, or spread.

    2.7k50 tok idle · 1,509 in use
  8. game-aigamedev-skills/awesome-gamedev-agent-skills

    Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A* pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state machine, behavior tree, blackboard, A*, navmesh, seek, or patrol/chase.

    2.7k85 tok idle · 1,838 in use