arcgis-3d-layers
Add 3D layer types including SceneLayer, IntegratedMeshLayer, PointCloudLayer, VoxelLayer, and DimensionLayer to SceneView. Use for 3D buildings, LiDAR, volumetric data, glTF models, and 3D measurements.
88
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies specific 3D layer types, their target context (SceneView), and when to use them. It uses concrete technical terms that serve as effective trigger keywords while remaining comprehensible. The description is concise, uses third person voice, and covers both the 'what' and 'when' effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and layer types: SceneLayer, IntegratedMeshLayer, PointCloudLayer, VoxelLayer, DimensionLayer, and specifies the target (SceneView). Very concrete and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (add 3D layer types to SceneView, listing specific layer types) and 'when' ('Use for 3D buildings, LiDAR, volumetric data, glTF models, and 3D measurements'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: '3D', 'buildings', 'LiDAR', 'volumetric data', 'glTF models', '3D measurements', 'SceneView', 'PointCloudLayer'. These cover both technical and natural language terms a user working with 3D GIS would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in 3D GIS layer types for SceneView. The specific layer names (VoxelLayer, IntegratedMeshLayer, PointCloudLayer) and domain terms (LiDAR, glTF, volumetric) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured reference skill covering multiple 3D layer types with strong, executable code examples. Its main weakness is the lack of explicit multi-step workflows with validation checkpoints — important steps like loading layers before accessing metadata are mentioned as pitfalls rather than integrated into the code patterns. Minor verbosity in descriptive sentences and a few placeholder comments slightly reduce token efficiency.
Suggestions
Integrate 'await layer.load()' calls directly into code examples that access metadata properties (variables, styles, allSublayers) rather than relying on a pitfall note at the end.
Remove or flesh out placeholder comments like 'Customize color stops for variable rendering / Accessed through voxelLayer.styles' — either provide executable code or remove the section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with code-forward examples, but includes some unnecessary descriptive sentences (e.g., 'SceneLayer displays 3D building models, objects, and mesh data from scene services') and a few incomplete/placeholder code comments (e.g., 'Customize color stops for variable rendering / Accessed through voxelLayer.styles') that add little value. The overall length is substantial but largely justified by the breadth of layer types covered. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples for every layer type, including imports, configuration, renderers, queries, filters, and interactive placement. Concrete patterns cover real use cases like PointCloud classification, VoxelLayer slicing, glTF model import, and DimensionLayer measurement. | 3 / 3 |
Workflow Clarity | Individual code snippets are clear, but multi-step processes lack explicit sequencing and validation checkpoints. For example, the VoxelLayer setup spans multiple disconnected snippets without a clear workflow, and the 'Load before accessing metadata' pitfall is mentioned at the end rather than integrated as a validation step in relevant workflows. The interactive dimension placement is well-sequenced though. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers for each layer type, a useful properties table for VoxelLayer, a summary table for 3D analysis components, and clear references to related skills and sample projects. Content is appropriately structured for discovery without deeply nested references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (578 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Commit
d84407b
- 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.