AI Behavior Trees Utility AI

What it does

When your agent uses it

• Implementing a reusable behavior-tree
• Utility-based decision system
• Tuning enemy/NPC decisions beyond a simple FSM
• The user mentions behavior tree

Example prompts

• “/ai-behavior-trees-utility-ai”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Pick the model. Structured, prioritized, interruptible behavior → BT. Continuous
2. 2Design the Blackboard first. One typed key/value store per agent is the shared memory that
3. 3Write leaves. Conditions return Success/Failure immediately; actions return
4. 4Compose. Selector = OR/fallback (first non-failure wins); Sequence = AND (stop at first
5. 5For Utility: enumerate considerations, map each raw fact through a normalized 0..1 curve,
6. 6Tick deliberately. Tick the tree/evaluator once per decision step (often slower than

What it can do on your machine

Read from SKILL.md and the folder at commit 0a70cfc. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are csharp and mermaid).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Behavior Trees Utility AI loads about 2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 695 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~187

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gamedev-skills/awesome-gamedev-agent-skills at commit 0a70cfc, republished under its Apache-2.0 licence (© gamedev-skills). 695 words, ~2,050 tokens.

name

ai-behavior-trees-utility-ai

description

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.

flowchart TD
    Root["Selector (root)"] --> Combat["Sequence: Combat"]
    Root --> Patrol["Action: Patrol"]
    Combat --> See["Condition: CanSeePlayer?"]
    Combat --> InRange{"Selector: Reach"}
    Combat --> Attack["Action: Attack (Running)"]
    InRange --> Close["Condition: InAttackRange?"]
    InRange --> MoveTo["Action: MoveToPlayer (Running)"]

facts (distance, health, ammo…)
      │  each fact → a normalized 0..1 response curve (consideration)
      ▼
score(action) = weight · combine(consideration_1 … consideration_n)   # product+compensation or sum
      ▼
select: argmax  ·  or softmax / weighted-random for variety  ·  + hysteresis to avoid jitter

public enum Status { Success, Failure, Running }

public abstract class Node
{
    public abstract Status Tick(Blackboard bb, float dt);
    public virtual void Reset() { }   // called when a parent abandons this subtree
}

// Selector = fallback/OR: return the first child that is not Failure.
public sealed class Selector : Composite
{
    public override Status Tick(Blackboard bb, float dt)
    {
        for (; _current < Children.Count; _current++)
        {
            var s = Children[_current].Tick(bb, dt);
            if (s != Status.Failure) return s;   // Success or Running stops the scan
        }
        _current = 0;
        return Status.Failure;                    // every child failed
    }
}

// A consideration maps one raw fact to 0..1 through a response curve.
float Score(Blackboard bb)
{
    float distance01 = Curves.InverseLerp01(bb.Get<float>("distToPlayer"), 20f, 2f); // near = 1
    float health01   = Curves.Sigmoid(bb.Get<float>("health01"), k: 8f, mid: 0.4f);  // hurt = low
    // Product + compensation keeps a single 0 from vetoing while low values still dampen.
    return Curves.CompensatedProduct(new[] { distance01, health01 });
}

© gamedev-skills, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/disciplines/ai-behavior-trees-utility-ai of gamedev-skills/awesome-gamedev-agent-skills.

• SKILL.md
• references/behavior-tree-core.md
• references/best-practices-and-pitfalls.md
• references/practical-examples.md
• references/utility-ai-system.md

Open the folder on GitHubat commit 0a70cfc