MCPInstall

tower-defense

Build a tower defense: enemies pathing along lanes, wave spawning, towers that auto-target and fire, an economy, and lives. Use for a tower-defense/wave-defense game, or balancing waves and economy.

Installs
6.3K
Last 24h
+324
Trending rank
#912
Security
Pass

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill tower-defense
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads tower-defense automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

Security audits

Independent scans of the skill's instructions and bundled files.

Gen Agent Trust Hub PassSAFE ·This skill provides design patterns and pseudocode for building tower defense games. It contains documentation only and does not include any executable code, network requests, or sensitive operations.
Socket PassNo alerts
Snyk PassLOW ·Risk: LOW · No issues

SKILL.md

The instructions your agent reads when the skill is triggered.

Tower Defense

A playbook for tower defense — enemy pathing, wave spawning, tower targeting, and the economy that ties them together. This is a compositional skill: it orchestrates pathing, AI, and UI into a TD loop. It does not re-teach pathfinding; it defines the systems and the balance levers (DPS vs. HP vs. income) that decide whether a TD is tense or trivial.

When to use

  • Use when building a game where the player places towers that automatically attack waves of enemies following a path, spends earned currency to expand/upgrade, and loses if too many enemies leak through.
  • Use when designing wave composition/pacing, tower targeting priorities, or the gold economy.

When not to use: the player directly controls a shooter → fps-shooter. Free-form base building with needs → survival-crafting. For the pathfinding algorithm itself, use game-ai.

Core loop

Prepare (place/upgrade towers with current gold) → start the wave → enemies path toward the goal while towers auto-fire → earn gold from kills → survive the wave → repeat against a harder one. The tension is a planning puzzle: is my current DPS enough for what's coming, and can I afford the answer?

Must-have systems

  1. Enemy path — waypoint lanes, or grid + pathfinding for maze TD (refs).
  2. Wave spawner — timed, scripted sequences of enemy types with per-wave scaling.
  3. Towers — range, fire rate, damage, projectile/hitscan, splash; placement validity.
  4. Targeting — per-tower priority (first/last/closest/strongest/weakest) (refs).
  5. Economy — gold from kills + wave bonuses; tower/upgrade costs; sell refund.
  6. Lives / leak — enemies reaching the goal cost lives; 0 = game over.
  7. Wave/prep UI — lives, gold, next-wave preview, start-next-wave control.

Design knobs

KnobEffectNotes
Enemy HP growth/waveupgrade pressureGeometric ~1.1–1.2× (refs).
Income vs. HP curvesdifficultyPlayer should almost afford each wave.
Tower DPS / range / costtower identityCheap+wide vs. expensive+tall.
Targeting priorityoptimal placementChanges play more than raw stats.
Enemy varietycounters one-build winsFast / armored / flying / swarm / boss.
Leak penaltystakesCost lives and lost bounty.
Upgrade vs. build economystrategy depthDiminishing upgrade returns.
Wave pacingtension curveSpike → breather → spike, not monotonic.

Patterns

1. Wave spawner (timed, data-driven)

# Pseudocode. A wave is data: a list of (enemy_type, count, spacing). Spawn over time.
wave = [ ("grunt", 10, 0.5), ("runner", 5, 0.3), ("tank", 2, 1.0) ]

def run_wave(wave):
    for enemy_type, count, spacing in wave:
        for _ in range(count):
            spawn_enemy(enemy_type, at=path[0])   # enter at the path start
            wait(spacing)                          # seconds between spawns (use a timer/coroutine)
    # wave clears when all spawned enemies are dead or have leaked

2. Tower targeting (filter to range, then pick by priority)

# Pseudocode. "First" (furthest along path) is the standard default for stopping leaks.
def acquire_target(tower, enemies, mode="first"):
    in_range = [e for e in enemies if distance(tower.pos, e.pos) <= tower.range]
    if not in_range: return None
    if mode == "first":    return max(in_range, key=lambda e: e.progress)   # furthest along path (stop leaks)
    if mode == "last":     return min(in_range, key=lambda e: e.progress)   # least progress (guard the entrance)
    if mode == "closest":  return min(in_range, key=lambda e: distance(tower.pos, e.pos))
    if mode == "strongest":return max(in_range, key=lambda e: e.hp)         # burn down tanks first
    if mode == "weakest":  return min(in_range, key=lambda e: e.hp)         # secure kills / last-hit bounty
    return in_range[0]

3. "Can this lane hold?" sanity check (DPS vs. HP)

# Pseudocode. One tower's damage to one enemy crossing its range.
tower_dps     = tower.damage * tower.fire_rate
time_in_range = tower.range_coverage_length / enemy.speed
damage_dealt  = tower_dps * time_in_range
# Lane holds if summed damage_dealt from covering towers >= enemy.hp (per enemy). See refs.

Pitfalls / failure modes

  • Enemy HP scales slower than player income/DPS → game trivializes after a few waves. Tune the HP curve against the income curve (refs).
  • One dominant tower/strategy → no decisions. Add enemy types that hard-counter builds (armored vs. rapid-fire, flying vs. ground-only) and diminishing upgrade returns.
  • Maze TD that can fully block the goal → enemies get stuck/softlock. Forbid placements that sever the path for the spawn or for any enemy already walking; recompute paths when towers change (refs §1).
  • Fast enemies slow down at corners or skip waypoints → per-step movement stops at each waypoint or overshoots it. Carry the leftover distance to the next waypoint (refs §1).
  • No next-wave telegraph → specials feel random and unfair. Preview upcoming composition.
  • Per-frame movement unscaled by dt → speed varies with frame rate. Scale steering by dt.
  • Leaks only cost lives, not gold → leaking is sometimes optimal. Make leaks lose bounty too.
  • Monotonic difficulty ramp → exhausting. Pace spikes and breathers.

Composition (build it from these skills)

  • Pathing: game-ai for A*/flow-field/steering; for fixed lanes, simple waypoint following.
  • Enemy movement: godot-2d-movement (or engine equivalent) to move along the path; unity-navmesh for nav-based pathing.
  • Map: godot-tilemap / unity-tilemap-2d for the grid/lanes; level-design for map layouts.
  • Data: godot-resources / unity-scriptableobjects to define towers, enemies, and waves as assets.
  • UI: game-ui-ux for HUD layout, scaling, and the build menu; godot-ui-control for the concrete widgets (lives, gold, wave preview).
  • Polish: audio-design for fire/hit/leak sound cues.

References

  • For path representations (waypoints / A* / flow fields), targeting modes, DPS and economy math, enemy scaling, and wave pacing, read references/balancing.md.

FAQ

What does the tower-defense skill do?

Build a tower defense: enemies pathing along lanes, wave spawning, towers that auto-target and fire, an economy, and lives. Use for a tower-defense/wave-defense game, or balancing waves and economy.

How do I install tower-defense?

Run npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill tower-defense in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/tower-defense/ (personal) or .claude/skills/tower-defense/ (project).

Which AI agents can use tower-defense?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is tower-defense safe to install?

Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk passed. As with any skill, read the SKILL.md and bundled scripts before installing.

Who maintains tower-defense?

It is published by gamedev-skills in gamedev-skills/awesome-gamedev-agent-skills. It has 6,278 recorded installs.

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

View all →

game-feel

gamedev-skills/awesome-gamedev-agent-skills

Add "juice" and game feel that makes actions satisfying — screen shake, hit-stop/freeze frames, tweened/eased motion, squash & stretch, knockback, and layered audio-visual feedback — as engine-neutral techniques that pair with the detected engine's tween, particle, and camera APIs. Use when the user mentions game feel, juice, "make it feel good/punchy", screen shake, hit stop, screen freeze, easing, squash and stretch, impact frames, or feedback/polish on hits, jumps, pickups, and deaths.

Media & Creative10.2K installs

game-ui-ux

gamedev-skills/awesome-gamedev-agent-skills

Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected engine's UI skill. Use when the user mentions HUD, health bar, main menu, pause menu, settings screen, UI layout, anchors, UI scaling, aspect ratio, safe area, controller/keyboard menu navigation, or wiring UI to game state.

Frontend & Design10K installs

level-design

gamedev-skills/awesome-gamedev-agent-skills

Design and build playable levels — the blockout/whitebox-to-playable workflow, player metrics and grid layout, pacing and flow (tension/rest curve), gating and the critical path, and encounter design. Engine-neutral practice. Use when the user mentions level design, blockout/whitebox/greybox, level layout, level pacing, encounter design, or the critical path through a level.

Frontend & Design8.2K installs

performance-optimization

gamedev-skills/awesome-gamedev-agent-skills

Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each engine's profiler. Use when the user mentions performance, optimize, low/dropping FPS, frame drops, stutter, lag, profiler, frame budget, draw calls, batching, garbage collection/GC spikes, object pooling, or "the game runs slow".

game-ai

gamedev-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.

Media & Creative7.8K installs

audio-design

gamedev-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.

Media & Creative7.8K installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs