threejs

Three.js skills for creating 3D elements and interactive experiences in the browser — scenes, materials, controls, and post-processing.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/threejs/SKILL.md

Quality

Content

40%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.

This body is a catalogue advertisement, not a usable skill: it is lean and well-sectioned but provides no executable guidance for the Three.js domain itself, delegating everything to an external GitHub repo with only vague install instructions. Actionability and workflow clarity are the clear weak points.

Suggestions

Replace the "open" the repo instruction with concrete steps, e.g. "git clone https://github.com/CloudAI-X/threejs-skills ~/.claude/skills/threejs" plus a verification command, so the install is copy-paste executable.

Include a minimal Quick start with an actual runnable Three.js snippet (scene, camera, renderer setup) so the skill delivers value without requiring the external bundle.

Drop the verbatim duplication of the frontmatter description in "What it does" and replace it with task-specific guidance for when and how to apply the skill.

Dimension	Reasoning	Score
Conciseness	The body is short and free of padding about concepts Claude already knows, but the "What it does" section repeats the frontmatter description verbatim and the OpenDesign-catalogue meta-explanation is not task guidance. Anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened") fits; not 4 because the duplication is avoidable overhead in an already minimal document.	3 / 5
Actionability	The only concrete command is "open https://github.com/CloudAI-X/threejs-skills", which merely opens a page; "install the upstream bundle into your active agent's skills directory" is a high-level hint with no steps to execute it. This matches anchor 2 ("minimal concrete guidance; high-level hints but missing the specific steps to execute"); not 1 because a concrete URL and one runnable command are present.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README → install bundle → ask the agent to invoke by name/trigger) but with major gaps: no install command, no local copy step, and no verification that the skill works after installation. Anchor 2 ("rough sequence present but many gaps; steps poorly defined") is the best fit; not 3 because the steps are described only loosely in prose rather than listed.	2 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is under 50 lines with clear sections ("What it does", "Source", "How to use") and a single well-signaled one-level-deep external reference. It falls short of the 5 anchor because all substantive content is delegated to an external URL rather than appropriately split into local files the agent can actually load.	4 / 5
	Total	11 / 20 Passed

Description

66%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 decent description: specific about the Three.js domain and its capability areas, with natural trigger keywords. Its main weakness is the missing "when to use" guidance, which the rubric explicitly caps at 3 for completeness.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for 3D scenes, WebGL visualizations, or interactive Three.js experiences in the browser."

Lead the capability list with verb-led actions (e.g. "Builds 3D scenes, configures materials and camera controls, adds post-processing effects") to sharpen specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	"creating 3D elements and interactive experiences in the browser — scenes, materials, controls, and post-processing" lists several specific capability areas beyond just naming the Three.js domain. It stops short of 5 because the items are topic nouns rather than fully concrete verb-led actions like the anchor-5 examples.	4 / 5
Completeness	It clearly answers "what" ("creating 3D elements... scenes, materials, controls, and post-processing") but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely underspecified.	3 / 5
Trigger Term Quality	"Three.js", "3D", "interactive", and "browser" are natural terms users would say when needing this skill. Not 5: common variations a user might say ("WebGL", "3D model", "render") are absent from the description field itself.	4 / 5
Distinctiveness Conflict Risk	"Three.js" names a specific library with a clear niche, keeping conflict risk low. Not 5: broader phrases like "interactive experiences in the browser" could overlap with generic frontend/WebGL skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/threejs/SKILL.md
Commit: 1b47e60

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.