threejs-gameplay-systems

Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring, objectives, and game feel. Use for first playable slices, new Vite/TypeScript/Three.js setups, level/arena/track/wave/hole/puzzle design, combat encounters, difficulty tuning, and juice.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

93%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.

A lean, highly actionable process skill that pairs a concrete scaffold command with fill-in design templates and well-structured one-level references. The only gap is that the workflow delegates validation feedback loops to the bundled tests rather than spelling them out in the body.

Suggestions

Add an explicit 'Verify' step in the Build section, e.g. 'Run npm run verify:visual and the bot-playtest after each playable increment; fix regressions before expanding content', so the validate→fix→retry loop is visible in the body rather than only in the scaffold.

State the run command for the scaffold tests inline (npm run verify:visual, copying bot-playtest.template.ts to a spec) so the validation checkpoint is copy-paste ready alongside the start command.

Cross-link the 'What goes wrong' failure modes to the reference that resolves each (e.g. mesh/body drift → physics-engine-selection.md 'Sync in exactly one system') to make recovery navigation explicit.

Dimension	Reasoning	Score
Conciseness	The body is dense and opinionated throughout — it assumes Claude knows TypeScript/Three.js, never explains what a library is, and packs each section (Design first, Build, What goes wrong) with only decision-shaping guidance, so every token earns its place.	5 / 5
Actionability	Provides a copy-paste start command ('python3 <this-skill-dir>/scripts/create_threejs_game.py ./my-game') plus three concrete fill-in templates (design brief, core loop contract, level/encounter plan) and an explicit ownership-boundary list; deep executable code is correctly deferred to the references rather than inlined.	5 / 5
Workflow Clarity	A clear Start → Design first → Build (1–6) → Report sequence exists with checkpoints ('something is playable at every step', 'Establish one representative encounter ... before expanding content'), but an explicit validate→fix→retry loop is not spelled out in the body — it is delegated to the scaffold's shipped tests.	4 / 5
Progressive Disclosure	The body is a concise overview with a well-signaled, one-level-deep reference table ('Read it when' column) pointing to real files (game-feel.md, genre-design.md, physics-engine-selection.md) plus a clearly labeled scaffold (assets/threejs-vite-game/) and script; all referenced paths exist and navigation is easy.	5 / 5
	Total	19 / 20 Passed

Description

95%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, specific description that pairs a concrete capability list with an explicit 'Use for...' trigger clause and rich natural synonyms. Its only weakness is that the capability enumeration leans on domain nouns rather than varied action verbs.

Dimension	Reasoning	Score
Specificity	Opens with concrete verbs 'Build and iterate playable Three.js game systems' and lists comprehensive capability areas (starter scaffold, core loops, level/encounter design, collision and physics, scoring, game feel), but the long tail is mostly domain nouns rather than multiple distinct action verbs, so it sits below the comprehensive-verbs anchor at 5.	4 / 5
Completeness	Explicitly answers both what ('Build and iterate playable Three.js game systems: ...') and when ('Use for first playable slices, new Vite/TypeScript/Three.js setups, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasing is densely covered with synonyms a player would actually say — 'first playable slices', 'level/arena/track/wave/hole/puzzle design', 'combat encounters', 'difficulty tuning', 'juice' — giving comprehensive keyword coverage including variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear gameplay-systems niche ('playable Three.js game systems', core loops, level/encounter design, game feel) with distinct triggers and minimal overlap with adjacent rendering or audio skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: majidmanzarpour/threejs-game-skills
Path: skills/threejs-gameplay-systems/SKILL.md
Commit: e5f301d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.