3d-high-poly-models

Create or integrate highly detailed 3D models with smooth silhouettes, shaped surfaces, believable bevels, and close-up geometry, then prepare suitable runtime LODs and loading. Use when a user requests high polygon counts, ultra-realistic models, detailed architectural assets, or removal of visibly faceted geometry.

Quality

79%

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 ./agent-skills/3d/3d-high-poly-models/SKILL.md

Quality

Content

71%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 body is a well-structured, competent instruction set for high-poly 3D modeling with a clear workflow and Verify checklist. Its main defect is progressive disclosure: it points to a REFERENCES.md file that is missing, leaving a broken navigation link.

Suggestions

Create the referenced REFERENCES.md (or place it under references/) so the "Read [REFERENCES.md](REFERENCES.md)" link resolves; alternatively remove the link if no separate reference material is intended.

Tighten abstract guidance lines like "Judge realism through silhouette, proportions, material response, and lighting" into concrete checks (e.g., specific viewer settings or comparison steps) to lift actionability.

Add an explicit validate→fix→retry loop in the Verify section so failed checks feed back into rework, strengthening workflow_clarity for a multi-step process.

Dimension	Reasoning	Score
Conciseness	Dense, assumes Claude's competence throughout (no basic explanations of LOD, instancing, or quantization), with only minor prose that could be trimmed; not a 5 because several sentences are wordy and the project-specific Seijaku aside is non-essential.	4 / 5
Actionability	Provides concrete, specific guidance (e.g., "sweep rings along a smooth curve, transport the local frame to avoid sudden twist, taper continuously", LOD thresholds derived from projected size) appropriate for an instruction-only DCC skill; not a 5 because some lines stay abstract ("Judge realism through silhouette, proportions, material response, and lighting") and no executable commands or tool-specific steps are given.	4 / 5
Workflow Clarity	Clear sequenced sections (Establish → Model → Prepare runtime versions numbered 1-5 → Avoid startup stall → Verify checklist) with explicit validation cues ("Check subdivision boundaries for pinching", "validate decoded geometry and appearance"); not a 5 because there is no structured validate→fix→retry feedback loop tying the Verify steps back into rework.	4 / 5
Progressive Disclosure	Sections are well-organized and the body signals a one-level-deep reference ("Read [REFERENCES.md](REFERENCES.md)"), but REFERENCES.md does not exist and there are no references/, scripts/, or assets/ directories, so the promised deeper material is a dead link and navigation does not actually resolve.	3 / 5
	Total	15 / 20 Passed

Description

87%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 strong: it covers a well-defined niche, gives concrete actions, and explicitly pairs a what-clause with a Use-when trigger clause. The only weakness is slightly limited keyword breadth (missing common synonyms and 3D file-format extensions).

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("Create or integrate highly detailed 3D models", "prepare suitable runtime LODs and loading") but the listed silhouette/bevel/surface attributes are modifiers on a single modeling action rather than distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states both what the skill does ("Create or integrate... prepare suitable runtime LODs and loading") and when to use it ("Use when a user requests high polygon counts, ultra-realistic models, detailed architectural assets, or removal of visibly faceted geometry") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ("high polygon counts", "ultra-realistic models", "detailed architectural assets", "removal of visibly faceted geometry") but omits common synonyms and format extensions like "high-poly", "low-poly", or .glb/.gltf/.fbx.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (high-poly 3D modeling and runtime LOD prep) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: MengTo/Skills
Path: agent-skills/3d/3d-high-poly-models/SKILL.md
Commit: 798db0a

Reviewed: 5 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.