macos-spatial-metal-engineer
Native Swift and Metal specialist building high-performance 3D rendering systems and spatial computing experiences for macOS and Vision Pro
43
30%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./spatial-macos-metal-engineer/skills/SKILL.mdQuality
Discovery
32%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 reads more like a developer bio or role title than a skill description. While it identifies a clear technical niche (Swift/Metal 3D rendering for Apple platforms), it lacks concrete action verbs describing what the skill actually does and entirely omits trigger guidance for when Claude should select it. Adding specific capabilities and a 'Use when...' clause would significantly improve its utility for skill selection.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about Metal shaders, 3D rendering on macOS, visionOS/Vision Pro development, or spatial computing experiences.'
Replace the role-style phrasing with concrete action verbs, e.g., 'Creates Metal shaders, builds 3D scene graphs, optimizes GPU render pipelines, implements spatial computing interactions for visionOS.'
Include additional natural trigger terms users might say: 'visionOS', 'RealityKit', 'SceneKit', 'GPU programming', 'shaders', 'AR', '.metal files'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (3D rendering, spatial computing) and technologies (Swift, Metal, macOS, Vision Pro), but doesn't list concrete actions like 'create shaders', 'build scene graphs', or 'optimize render pipelines'. 'Building high-performance 3D rendering systems' is somewhat specific but reads more like a role description than a list of capabilities. | 2 / 3 |
Completeness | Describes what the skill is about (3D rendering with Swift/Metal) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also more of a role description than concrete capabilities, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Swift', 'Metal', '3D rendering', 'Vision Pro', 'macOS', and 'spatial computing' that users might naturally mention. However, it misses common variations like 'visionOS', 'RealityKit', 'SceneKit', 'GPU', 'shaders', 'AR', 'augmented reality', or '.swift files'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Swift + Metal + Vision Pro + 3D rendering is fairly distinctive and unlikely to conflict with generic coding skills. However, it could overlap with general Swift development skills or Apple platform skills since the boundaries aren't clearly drawn. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like an AI persona/character sheet than an actionable technical skill document. It wastes significant tokens on identity framing, communication style instructions, and success metrics that don't help Claude perform tasks. While it contains some useful code examples, several use fabricated APIs, and the overall structure is a monolithic wall without progressive disclosure or proper validation workflows.
Suggestions
Remove all persona/identity/communication style sections and focus purely on actionable technical instructions—Claude doesn't need to be told to 'think in parallel' or remember its 'personality'.
Verify all code examples compile against real APIs—RemoteImmersiveSpace and several Compositor Services calls appear fabricated. Replace with actual API usage or clearly mark as pseudocode.
Split content into focused files: a concise SKILL.md overview with links to separate METAL_PIPELINE.md, VISION_PRO_INTEGRATION.md, and SPATIAL_INTERACTIONS.md reference files.
Add explicit validation checkpoints to the workflow (e.g., 'Run Metal validation layer to check shader compilation', 'Verify stereo frame timing with Metal System Trace before proceeding').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Includes extensive personality/identity sections ('Your Identity & Memory', 'Communication Style', 'Learning & Memory', 'Success Metrics') that are unnecessary fluff. Explains concepts Claude already knows (what ARC is, what frustum culling is). The persona framing wastes significant tokens on role-play instructions rather than actionable technical content. | 1 / 3 |
Actionability | Contains substantial Swift and Metal code examples that appear mostly executable, but several are incomplete or illustrative rather than copy-paste ready (e.g., VisionProCompositor uses APIs that don't exist in their shown form, RemoteImmersiveSpace API is fabricated). The Metal compute shader is reasonable but the Swift integration code has fictional API calls that would not compile. | 2 / 3 |
Workflow Clarity | The 4-step workflow process is listed but lacks validation checkpoints. Steps like 'Build Rendering System' and 'Optimize Performance' are high-level descriptions without explicit verification gates. For a skill involving GPU rendering pipelines and stereoscopic output—where errors can be subtle—missing validation/feedback loops caps this at 2. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content—from basic setup to advanced capabilities—is inlined in a single massive document. The 'Advanced Capabilities' section lists features without any depth or links. No separation of reference material, examples, or detailed guides into supporting files. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.