3d-asset-generation

Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.

Quality

78%

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 ./.agents/skills/3d-asset-generation/SKILL.md

Quality

Content

81%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-structured, actionable orchestration skill with strong validation discipline and concrete tooling details. The main improvement is moving time-sensitive pricing into a dated/reference section and adding one or two concrete end-to-end call examples.

Suggestions

Move the dated pricing figures ('As of 2026-08-13') into a clearly marked dated or reference section so stale figures are easy to spot and update.

Include at least one concrete example invocation (e.g. a sample atlas_3d or fal_3d request with the asset prompt contract applied) to lift actionability to fully copy-paste ready.

Consider extracting the mesh-QA checklist and prompt contract into a reference file so the SKILL.md overview stays a lean routing guide.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of what Blender or 3D is), but the time-sensitive pricing block ('As of 2026-08-13' with per-tier dollar figures) is inline rather than in a deprecated/old-patterns section, a minor conciseness cost.	4 / 5
Actionability	Names concrete model IDs ('tripo-h3.1/text-to-3d', 'Hunyuan 3D v3.1 Rapid'), API parameters ('resume: true', 'target_height', 'exclusion_zones'), and a numbered prompt contract, but stops short of full copy-paste call examples.	4 / 5
Workflow Clarity	Clear sequenced disciplines with explicit validation checkpoints and feedback loops: 'Generate one sample before a batch', the mesh-QA checklist, 'Failed samples remain failed; do not silently swap', and 'render a small bounded frame range first and measure' before committing to full resolution.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no problematic nested references, and no bundle files are needed for this self-contained routing skill; the pricing table and QA checklist could optionally be externalized but are acceptable inline.	4 / 5
	Total	17 / 20 Passed

Description

75%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 specific, tool-named, and clearly niched, but omits an explicit 'Use when...' trigger clause, which caps its completeness. Adding a trigger sentence would raise it to a top-tier description.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when a production needs real 3D meshes rather than primitive stand-ins, or when generating, reconstructing, or routing textured assets.'

Add a common synonym or file extension (e.g. '3D models / meshes / .glb') so users' natural phrasings match the description.

Dimension	Reasoning	Score
Specificity	Lists four distinct concrete actions ('Generate, reconstruct, inspect, and route') and names the concrete tooling stack (Atlas Cloud, fal.ai, licensed catalogs, Blender), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes the natural phrase '3D assets' and tool names a user would mention, but misses common synonyms/extensions like '3D model', 'mesh', or '.glb' that a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'OpenMontage worlds' with named providers (Atlas Cloud, fal.ai, Blender) and a distinct asset-provenance niche, making overlap with other skills minimal.	5 / 5
	Total	17 / 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: calesthio/OpenMontage
Path: .agents/skills/3d-asset-generation/SKILL.md
Commit: 08e2151

Reviewed: 2 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.