Test XR session lifecycle and mode transitions. Use when verifying XR enter/exit behavior, testing mode-dependent features, or debugging session state issues.
71
87%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
75%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 well-structured with a clear 'what' and 'when' clause, and targets a distinct niche (XR session lifecycle testing). Its main weakness is that it could be more specific about the concrete actions performed and could include more natural trigger term variations (e.g., WebXR, VR, AR) that users might actually use when requesting this skill.
Suggestions
Add trigger term variations users might naturally say, such as 'WebXR', 'VR session', 'AR session', 'immersive mode', or 'headset'.
List more specific concrete actions, e.g., 'validate session start/end events, test transitions between immersive and inline modes, verify pose tracking state across mode changes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (XR session lifecycle) and some actions (test mode transitions, verify enter/exit behavior, debug session state), but doesn't list multiple concrete specific actions like specific test operations or tools used. | 2 / 3 |
Completeness | Clearly answers both 'what' (test XR session lifecycle and mode transitions) and 'when' with explicit triggers ('Use when verifying XR enter/exit behavior, testing mode-dependent features, or debugging session state issues'). | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'XR session', 'mode transitions', 'enter/exit behavior', and 'session state', but misses common variations users might say such as 'WebXR', 'VR', 'AR', 'immersive mode', or 'headset session'. | 2 / 3 |
Distinctiveness Conflict Risk | XR session lifecycle testing is a very specific niche that is unlikely to conflict with other skills. The triggers around XR enter/exit, mode transitions, and session state are distinct and narrowly scoped. | 3 / 3 |
Total | 10 / 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 a well-crafted skill that efficiently describes an XR session lifecycle test. It provides clear, sequential steps with specific MCP tool calls and explicit verification criteria at each stage. The content is lean, actionable, and appropriately structured for its scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what XR is or how sessions work. The skill assumes Claude knows the domain and focuses purely on the specific tool calls and verification steps. | 3 / 3 |
Actionability | Each step specifies the exact MCP tool to call and what to verify in the response. The tool names are fully qualified and the expected outputs are concrete (e.g., visibilityState is "visible"). While there's no traditional code, the instruction-only format provides specific, executable guidance. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with verification checkpoints after each state change (steps 3, 6, 7). There's an implicit feedback loop through the pass/fail reporting, and the workflow covers the full lifecycle: check initial state → enter → verify → exit → verify → check logs. | 3 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Test Flow, Arguments, Expected Results). The structure is appropriate for the scope. | 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 | |
3a08b40
Table of Contents
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.