iwsdk-ray
Ray-based interactions in the WebXR scene — click objects, press UI buttons, or distance-grab with DistanceGrabbable. Use when the user wants to point at and interact with something at a distance, click a UI button, or test ray-based selection.
79
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 well-crafted skill description that clearly defines its niche (ray-based interactions in WebXR), lists specific concrete actions, and provides explicit 'Use when' trigger guidance. It uses third person voice correctly and includes both natural language terms and domain-specific terminology that would help Claude accurately select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'click objects', 'press UI buttons', 'distance-grab with DistanceGrabbable'. These are clear, actionable capabilities within a well-defined domain. | 3 / 3 |
Completeness | Clearly answers both what ('click objects, press UI buttons, distance-grab with DistanceGrabbable') and when ('Use when the user wants to point at and interact with something at a distance, click a UI button, or test ray-based selection') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'click objects', 'UI buttons', 'distance-grab', 'DistanceGrabbable', 'point at', 'interact with something at a distance', 'ray-based selection'. Good coverage of both natural language and technical terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to ray-based interactions in WebXR scenes, with domain-specific terms like 'DistanceGrabbable', 'ray-based selection', and 'WebXR'. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently teaches a complex multi-branch XR interaction workflow. It provides concrete API calls with exact parameters, clear decision points for branching, and important disambiguation notes (click vs hold, trigger vs squeeze). The structure is clean and scannable, with every token contributing actionable information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place — no explanations of basic concepts, no padding. The skill assumes Claude understands XR concepts and focuses purely on the specific API calls and decision logic needed. The notes section is dense and each bullet addresses a real confusion point (click vs hold, trigger vs squeeze). | 3 / 3 |
Actionability | Provides specific tool calls with exact parameters (device names, button indices, default positions, coordinate offsets). Each step has concrete, copy-paste-ready API invocations rather than abstract descriptions. The branching logic clearly specifies which API to use for each interaction type. | 3 / 3 |
Workflow Clarity | The workflow is clearly structured with a required core (steps 1-4) and well-defined interaction branches (A vs B). Branch B has explicit sub-steps (engage, move, release, return) in clear sequence. The 'if not found, report and stop' checkpoint in Step 2 and the optional verification screenshot in Step 5 provide appropriate validation. The decision criteria for choosing branches are explicit. | 3 / 3 |
Progressive Disclosure | For a skill of this complexity with no bundle files, the content is well-organized with clear section hierarchy: Required Core → Interaction Branches → Notes. The branching structure (A vs B) with sub-steps keeps the document scannable without needing external files. Content is appropriately sized for a single file. | 3 / 3 |
Total | 12 / 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
- facebook/immersive-web-sdk
- Commit
b3d1162
- 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.