CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web-3d-asset-pipeline

Prepare and optimize browser-game 3D assets. Use when the user asks for GLB or glTF shipping work, including Blender cleanup and export, collision or LOD setup, compression, texture packaging, and runtime validation.

64

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/game-studio/skills/web-3d-asset-pipeline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 well-organized, token-efficient overview with clear scoping (use/don't-use sections) and sensible defaults, but it reads as a policy checklist rather than an executable guide: no commands, no validator, no feedback loop, and its references point to files that do not exist in the bundle.

Suggestions

Add concrete executable commands for the core steps, e.g. `npx @gltf-transform/cli optimize in.glb out.glb --compress meshopt --texture-compress ktx2` and a named validator such as gltf-validator, plus numeric texture-budget targets.

Add an explicit validation checkpoint with a fix-and-retry loop after export/optimization (validate -> fix in Blender/glTF Transform -> re-validate -> only then ship).

Fix the References section paths to bundle-local `references/` and ensure the six referenced files actually exist in the skill bundle.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no padding or explanation of concepts Claude already knows (it never explains what GLB or glTF is). Minor redundancy between the 'Default Pipeline' section and the 'Format Rules' ('Export to GLB or glTF 2.0' vs 'Default shipping format: GLB or glTF 2.0') keeps it below the every-token-earns-its-place anchor.

4 / 5

Actionability

It names the right tools (glTF Transform, Draco, Meshopt, KTX2/BasisU) but contains no commands, flags, validator names, or numeric budgets — e.g. 'Optimize with glTF Transform' and 'Validate naming, pivots, transforms... and texture budgets' give no executable step or threshold. This is some concrete guidance with key execution details missing, not the mostly-executable anchor.

3 / 5

Workflow Clarity

The six-step 'Default Pipeline' gives a clear sequence including a 'Validate' step, but validation has no mechanism and there is no fix-and-retry feedback loop for a batch optimization workflow. The sequence is present but checkpoints are implicit, matching the score-3 anchor rather than the most-checkpoints-present anchor.

3 / 5

Progressive Disclosure

Sections are well organized and the References list is clearly labeled, but the six reference paths use '../../references/' (non-bundle-local) and no references/ directory — nor any of the named files — exists in the bundle, so navigation to the detailed material fails. Structure is good but the references are not actually resolvable, which fits the could-be-better-organized anchor.

3 / 5

Total

13

/

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: third-person voice, concrete capability list, and an explicit 'Use when' clause with natural trigger terms. The only gap is missing a few synonyms and file extensions (.glb/.gltf) in the trigger vocabulary.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Blender cleanup and export, collision or LOD setup, compression, texture packaging, and runtime validation' — covering the shipping pipeline comprehensively. It exceeds the score-4 anchor (minor gaps) and matches the comprehensive multi-action anchor; nothing is vague.

5 / 5

Completeness

It explicitly answers both: what it does ('Prepare and optimize browser-game 3D assets') and when to use it ('Use when the user asks for GLB or glTF shipping work, including...') with concrete trigger phrases. This matches the score-5 example pattern exactly; the 'when' clause is fully explicit, so 4 does not apply.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'GLB or glTF shipping', 'Blender', 'collision', 'LOD', 'compression', 'texture packaging', 'runtime validation'. It misses a few natural terms users would say, such as file extensions (.glb, .gltf) or synonyms like '3D model optimization', so it does not reach the comprehensive score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche — browser-game 3D asset shipping in GLB/glTF — with distinct triggers (Blender export, LOD, collision, texture packaging) that minimal-conflict skills would use. Only slight adjacency to runtime Three.js skills, which keeps it at the minimal-risk 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

openai/plugins

Path

plugins/game-studio/skills/web-3d-asset-pipeline/SKILL.md

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.