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.

75

Quality

92%

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

92%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.

The content is a lean, well-structured contract skill: concise rules, a clear build-to-verify workflow with validation gates, and one-level-deep progressive disclosure to a real, organized reference file. It is instruction-focused rather than code-focused, which fits the skill's purpose and is not penalized.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it states rules like "Use +Y up, +Z forward, meters, and a ground-contact root" and "Animation may expose a normalized phase, but it must not create damage by itself" with no padding and no explaining of basic Three.js or combat concepts.

5 / 5

Actionability

It gives concrete, specific guidance — required state names, declared attack fields (startup, active, recovery, cooldown, contact shape/socket, damage/posture, facing rule, interrupt policy), a pure sampler signature, and a conformance failure list — but stops at field/behavior contracts rather than copy-paste executable code, which is appropriate for a contract skill yet leaves minor gaps.

4 / 5

Workflow Clarity

A clear sequenced workflow runs Establish contract -> Separate four layers -> Build rig -> Connect behavior/combat -> Compose testable movesets -> Verify conformance, with explicit validation checkpoints (deterministic fixtures, freeze/reproduce at phase boundaries, and a fail-the-asset gate listing floating attachments, pose-derived damage, LOD socket drift, and unbounded cost).

5 / 5

Progressive Disclosure

SKILL.md is a concise overview that points one level deep to the real references/monster-contract.md file (which exists and is well organized with its own Contents index), keeping the bulk of interface/type detail out of the main body while clearly signaling the reference.

5 / 5

Total

19

/

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.

The description is concrete, complete, and distinct, with an explicit "Use for..." trigger clause and a comprehensive enumeration of capabilities. Trigger-term quality is strong but slightly favors domain jargon over the colloquial phrases a user might actually say.

Suggestions

Add colloquial synonyms like "creatures", "enemies", "bosses", and "hitboxes" alongside the technical terms so the description matches how users naturally phrase monster-related requests.

Consider including common file extensions or asset forms (e.g. ".glb", "imported creature rigs") as trigger terms to broaden natural-language recall.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Build, integrate, audit, or refactor rigged monsters" — plus enumerated capabilities like monster asset contracts, semantic joints and sockets, hurtboxes and attack volumes, combat animation states, enemy-runtime adapters, LODs, and deterministic review fixtures, giving comprehensive coverage.

5 / 5

Completeness

It explicitly answers what the skill does (build, integrate, audit, refactor rigged monsters) and when to use it via the explicit "Use for..." clause enumerating concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage including "rigged monsters", "Three.js", "web action games", "hurtboxes", "attack volumes", "LODs", and "enemy-runtime adapters", but it leans on domain jargon and omits everyday synonyms a user might voice (e.g. "creature", "enemy", "boss", "hitbox").

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — rigged monsters for Three.js/web action games with a shared contract system — with distinct triggers unlikely to fire for unrelated skills; minimal conflict risk.

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.

Validation16 / 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.