build-game-monster-system — Claude Code skill: Three.js monsters
A skill that builds rigged monsters for Three.js and web action games: asset contract, sockets, hurtboxes, combat states.
npx skills add MengTo/Skills --skill build-game-monster-system -a claude-codeWhat build-game-monster-system does
The skill walks an agent through building, integrating and auditing monsters as gameplay runtime assets rather than decorative meshes. Before any work it reads references/monster-contract.md and checks the real content model: combat events, the enemy state machine, the collision API, camera distance and the asset loader.
Four layers stay separate. MonsterDefinition holds authored facts and budgets, MonsterRig the semantic hierarchy with joints and sockets, MonsterRuntime the state and timers, and MonsterViewAdapter drives poses, VFX and LOD from runtime state. The rig uses +Y up, +Z forward, meters and a ground-contact root. Limb segments are real joint chains, so shoulder motion travels through the elbow to the wrist. Visual meshes stay out of physics by default, with simple solid, navigation, hurt and attack shapes defined separately.
Contacts come from authoritative action IDs and collision events. Animation can expose a normalized phase, but it never creates damage on its own. Verification runs on deterministic fixtures: active-window boundaries, action ID stability across attack phases, ID renewal per loop. An asset fails if it has floating attachments, missing mandatory states, pose-derived damage or socket drift across LOD changes. That is worth checking before the monster reaches a build.
What it helps with
- build a rigged monster for a web action game runtime
- check that sockets and hurtboxes survive LOD switching
- keep authored combat values out of the visual pose
- define combat states from idle through defeated
- create deterministic fixtures for attack phases
Example prompts for the agent
- Build a monster against
references/monster-contract.mdand verify the attack sockets - Audit the rig: joints, colliders, combat states and LOD
- Add fixtures for the startup, active and recovery boundaries of every attack
How to install build-game-monster-system
1Skills CLI (Vercel)
npx skills add MengTo/Skills --skill build-game-monster-system -a claude-code2Manually: put the files in place
~/.claude/skills/build-game-monster-system/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/build-game-monster-system/
1Skills CLI (Vercel)
npx skills add MengTo/Skills --skill build-game-monster-system -a codex2Manually: put the files in place
.agents/skills/build-game-monster-system/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MengTo/Skills --skill build-game-monster-system -a cursor2Manually: put the files in place
.cursor/skills/build-game-monster-system/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MengTo/Skills build-game-monster-system2Manually: put the files in place
.github/skills/build-game-monster-system/SKILL.md1Skills CLI (Vercel)
npx skills add MengTo/Skills --skill build-game-monster-system -a gemini-cli2Platform CLI
gemini skills install https://github.com/MengTo/Skills --path agent-skills/game-development/build-game-monster-systemManually: put the files in place
.devin/skills/build-game-monster-system/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add MengTo/Skills --skill build-game-monster-system -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about build-game-monster-system
How do I install build-game-monster-system in Claude?
Run npx skills add MengTo/Skills --skill build-game-monster-system -a claude-code. The skill lands in ~/.claude/skills/build-game-monster-system/SKILL.md.
What does build-game-monster-system do?
It builds, integrates and audits rigged monsters for Three.js and web action games: asset contract, joints and sockets, hurtboxes, combat states, runtime adapters and LODs.
Which skills does it work with?
img2threejs for image-driven procedural reconstruction, build-hybrid-game-assets for choosing procedural versus imported representation, tune-enemy-ai for enemy behavior and design-action-combat for combat timing.
Source text
SKILL.md · MIT
--- name: build-game-monster-system description: Build, integrate, audit, or refactor rigged monsters for Three.js and web action games. Use for monster asset contracts, procedural or imported creature rigs, semantic joints and sockets, hurtboxes and attack volumes, combat animation states, enemy-runtime adapters, LODs, deterministic review fixtures, and validating that every monster follows one shared system. --- # Build Game Monster System Build monsters as gameplay-compatible runtime assets, not decorative meshes. ## Establish the contract Read [references/monster-contract.md](references/monster-contract.md) before implementation or audit. Check the real game content model, combat events, enemy state machine, collision API, camera distance, and asset loader before extending the contract. Use related skills when applicable: - Use `img2threejs` for image-driven procedural reconstruction and its staged visual gates. - Use `build-hybrid-game-assets` to choose procedural versus imported representation and record provenance/budgets. - Use `tune-enemy-ai` for perception, intent, movement, and behavior transitions. - Use `design-action-combat` for startup/active/recovery timing and authoritative contact. ## Separate four layers 1. `MonsterDefinition`: serializable authored facts, tags, scale, stats, attacks, locomotion, asset provenance, and budgets. 2. `MonsterRig`: semantic transform hierarchy, joints, sockets, secondary-motion anchors, materials, and LOD visuals. 3. `MonsterRuntime`: current state, timers, target intent, health/posture, cooldowns, and authoritative combat events. 4. `MonsterViewAdapter`: drives rig poses, VFX, audio, visibility, and LOD from runtime state; never decides hits from rendered pose. Do not duplicate authored combat values in the rig or UI. ## Build the rig - Use `+Y` up, `+Z` forward, meters, and a ground-contact root. - Keep `root -> motion -> body` stable across every monster and LOD. - Parent limb segments as real joint chains so shoulder/hip motion propagates through elbows/knees to wrists/ankles. - Name semantic equivalents for nonhumanoids; do not fake absent anatomy. - Provide sockets for attack origins, VFX, audio, targeting, ground contact, attachments, and death effects. - Keep visual meshes out of physics by default. Provide simple solid, navigation, hurt, attack, and trigger shapes separately. - Preserve root, joints, sockets, collision, and animation state across LOD changes. ## Connect behavior and combat Support at least `idle`, `investigate`, `pursue`, `reposition`, `windup`, `attack`, `recover`, `stagger`, and `defeated`. Each attack definition must declare startup, active, recovery, cooldown, contact shape/socket, damage/posture output, facing rule, and interrupt/cancel policy. Drive contacts from authoritative action IDs and collision events. Animation may expose a normalized phase, but it must not create damage by itself. ## Compose testable movesets - Author movesets as serializable sequences of intent states and attack IDs. Keep attack timing in the attack definitions; the moveset references it instead of copying it. - Compile attack steps into explicit startup, active, and recovery phases. - Provide a pure sampler from `(movesetId, elapsed)` to state, attack, normalized phase, active flag, interruptibility, and stable action ID. - Give every loop cycle a new action ID while preserving one ID across an attack's startup, active, and recovery phases. - Expose queryable or seeded fixtures for the midpoint and boundaries of every phase so reviewers can freeze and reproduce them without campaign playthrough. ## Verify conformance - Add deterministic fixtures for all required states, each attack phase, interrupt/stagger, death, LOD switching, and reset. - Test moveset timeline continuity, exact active-window boundaries, full attack coverage, per-action ID stability, and per-loop ID renewal. - Test joint propagation, socket stability, collider coverage, single-contact idempotence, and disposal. - Render the monster at real encounter distance in the in-app browser. - Measure triangles, draw calls, textures, frame time, and mobile pixel-ratio behavior. - Fail the asset if it has floating attachments, missing mandatory states, pose-derived damage, LOD socket drift, or unbounded resource cost. Report whether the monster fully conforms, conforms with documented exceptions, or needs a new archetype capability added to the shared contract.
© MengTo · MIT · MengTo/Skills