Game AI

What it does

When your agent uses it

• Building enemy AI
• Steering/flocking
• The user mentions state machine

Example prompts

• “/game-ai”

Requirements

• Python 3
• Compatibility (from SKILL.md): Engine-agnostic (algorithms). Concrete snippets in GDScript-like / Python pseudocode; pairs with unity-navmesh, unreal-behavior-trees, or Godot NavigationServer.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Finite state machine (one state object, explicit transitions)
2. 2Behavior tree tick (composite nodes return a status)
3. 3Steering: seek and arrive (smooth, frame-rate independent)
4. 4A* heuristic must not overestimate (or paths stop being shortest)

What it can do on your machine

Read from SKILL.md and the folder at commit 2f4ac6b. 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 gdscript and python).

  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.

• Compatibility

  Engine-agnostic (algorithms). Concrete snippets in GDScript-like / Python pseudocode; pairs with unity-navmesh, unreal-behavior-trees, or Godot NavigationServer.

  From compatibility in the SKILL.md frontmatter.

Context cost

Game AI loads about 2.1k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 631 words of instructions outside code blocks.

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

~100

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

~2.1k

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

~4.5k

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 ukanwat/overtime at commit 2f4ac6b, republished under its Apache-2.0 licence (© ukanwat). 631 words, ~2,060 tokens.

name

game-ai

description

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.

compatibility

Engine-agnostic (algorithms). Concrete snippets in GDScript-like / Python pseudocode; pairs with unity-navmesh, unreal-behavior-trees, or Godot NavigationServer.

license

Apache-2.0

metadata.engine

none

metadata.category

disciplines

metadata.difficulty

advanced

# Each state is a small object with enter/update/exit. The machine owns "current".
class_name State
func enter(agent): pass
func update(agent, dt) -> State: return null   # return a new state to transition
func exit(agent): pass

# --- Chase state: returns Patrol when the player escapes sight range ---
class Chase extends State:
    func update(agent, dt) -> State:
        if not agent.can_see(agent.target):
            return Patrol.new()                 # transition by returning next state
        agent.move_toward(agent.target.position, dt)
        return null                             # null = stay in this state

# --- Driver: call once per frame ---
func tick(dt):
    var next = current.update(self, dt)
    if next != null:
        current.exit(self); next.enter(self); current = next

# A node's tick() returns SUCCESS, FAILURE, or RUNNING (still working this frame).
enum Status { SUCCESS, FAILURE, RUNNING }

# Sequence: run children in order; stop at the first non-SUCCESS (logical AND).
func sequence_tick(children, agent, dt) -> int:
    for child in children:
        var s = child.tick(agent, dt)
        if s != Status.SUCCESS:
            return s                 # FAILURE or RUNNING short-circuits the sequence
    return Status.SUCCESS

# Selector: try children until one succeeds or is RUNNING (logical OR / fallback).
func selector_tick(children, agent, dt) -> int:
    for child in children:
        var s = child.tick(agent, dt)
        if s != Status.FAILURE:
            return s                 # SUCCESS or RUNNING stops the search
    return Status.FAILURE

# Seek: accelerate toward a target at full speed. Steering = desired - current.
func seek(pos, vel, target, max_speed, max_force) -> Vector2:
    var desired = (target - pos).normalized() * max_speed
    return (desired - vel).limit_length(max_force)   # a force, not a teleport

# Arrive: like seek, but ramp speed down inside slow_radius so it stops cleanly.
func arrive(pos, vel, target, max_speed, max_force, slow_radius) -> Vector2:
    var offset = target - pos
    var dist = offset.length()
    if dist < 0.001: return -vel                      # already there: kill drift
    var ramped = max_speed * min(dist / slow_radius, 1.0)
    var desired = offset / dist * ramped
    return (desired - vel).limit_length(max_force)

# Per frame: vel += steering * dt; pos += vel * dt   (always scale by dt)

# Match the heuristic to the movement. An ADMISSIBLE heuristic (never larger
# than the true remaining cost) keeps A* optimal.
def heuristic(a, b):
    dx, dy = abs(a.x - b.x), abs(a.y - b.y)
    # return dx + dy             # Manhattan: 4-direction grids (no diagonals)
    return (dx + dy) + (1.414 - 2) * min(dx, dy)   # octile: 8-direction grids
# f(n) = g(n) + h(n): g = cost from start, h = heuristic to goal.
# Overestimating h is faster but no longer guarantees the shortest path.

© ukanwat, 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 2 other files (references) in .claude/skills/game-ai of ukanwat/overtime.

• SKILL.md
• references/behavior-trees.md
• references/pathfinding.md

Open the folder on GitHubat commit 2f4ac6b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ukanwat/overtime, which our catalogue first saw on October 7, 2026.

• gamedev-skills/awesome-gamedev-agent-skillsskills/disciplines/game-ai