CtrlK
BlogDocsLog inGet started
Tessl Logo

build-game-monster-system

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.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Excellent instruction-style skill content: lean, dense, and concrete, with exact conventions, states, and per-attack requirements, a real verification section with fail conditions, and clean delegation of detail to an existing one-level reference. No weaknesses found worth scoring below the top anchor.

DimensionReasoningScore

Conciseness

The body is ~60 dense, bullet-driven lines with zero padding and no explanation of concepts Claude already knows — even the opening principle line ("Build monsters as gameplay-compatible runtime assets, not decorative meshes") earns its place as a design constraint. Every token carries information.

5 / 5

Actionability

Guidance is fully concrete: exact conventions ("`+Y` up, `+Z` forward, meters, and a ground-contact root"), a named nine-state minimum ("idle, investigate, pursue, reposition, windup, attack, recover, stagger, defeated"), an exact per-attack declaration list (startup, active, recovery, cooldown, contact shape/socket, damage/posture output, facing rule, interrupt/cancel policy), and a pure sampler signature from `(movesetId, elapsed)`. Per the rubric's instruction-only note, the absence of code is not penalized when guidance is this actionable — and the detailed TS interfaces live in the referenced contract file.

5 / 5

Workflow Clarity

A clear ordered sequence (read the contract → define the four layers → build the rig → wire behavior/combat → compose movesets → verify → report) is capped by an explicit validation section with hard fail conditions ("Fail the asset if it has floating attachments, missing mandatory states, pose-derived damage, LOD socket drift, or unbounded resource cost") and a three-outcome conformance report, satisfying the checklist-and-validation anchor.

5 / 5

Progressive Disclosure

The body is a concise overview that delegates the detailed field-level contract to a single, clearly signaled, one-level-deep reference ("Read [references/monster-contract.md](references/monster-contract.md) before implementation or audit") — verified to exist and to contain the interface definitions the body only summarizes. No buried or nested references.

5 / 5

Total

20

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete actions comprehensively and gives an explicit, well-triggered use clause with a clearly bounded niche. The only weakness is a few capability phrases written in system jargon rather than the words a user would naturally say.

Suggestions

Add one or two natural user phrasings (e.g., "adding enemies or bosses", "rigging a creature") to the use clause so trigger matching works for how users actually ask.

Consider trimming the tail of the trigger list ("enemy-runtime adapters, deterministic review fixtures") toward user-facing terms, since these describe implementation artifacts rather than user requests.

DimensionReasoningScore

Specificity

The description lists four concrete verbs ("Build, integrate, audit, or refactor rigged monsters") and a comprehensive capability inventory ("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"), matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

Both parts are explicit: what is "Build, integrate, audit, or refactor rigged monsters for Three.js and web action games" and when is the concrete "Use for monster asset contracts, ... and validating that every monster follows one shared system" clause — matching the anchor that clearly answers both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("rigged monsters", "Three.js", "creature rigs", "hurtboxes", "web action games", "LODs"), but "enemy-runtime adapters" and "deterministic review fixtures" are author-side jargon users would not naturally say, and common user synonyms like "enemies", "boss", or "character rig" are missing — fitting the good-but-few-missing anchor, not the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous (rigged, combat-capable monsters for Three.js and web action games) and its trigger terms (hurtboxes, movesets, monster rig contracts) are unlikely to fire for adjacent animation or general game-asset skills, matching the clear-niche-minimal-conflict anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MengTo/Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.