xr-mode-test

Test XR session lifecycle and mode transitions. Use when verifying XR enter/exit behavior, testing mode-dependent features, or debugging session state issues.

Quality

90%

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

Quality

Content

93%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.

An exemplary lean, fully actionable skill body: exact tool calls with expected values at every step and zero fluff. The only weakness is the absence of failure-path guidance between the checkpoint and the final report.

Suggestions

Add brief error-recovery guidance after each transition step (e.g., if `xr_accept_session` fails or `xr_get_session_status` shows an unexpected state, report the raw status and console errors rather than continuing).

In the Expected Results section, note how to capture 'time taken for session transitions' (e.g., timestamps around steps 2 and 5) so that reporting requirement is actionable.

Dimension	Reasoning	Score
Conciseness	Every line is either an exact tool invocation ("Use `mcp__iwsdk-dev-mcp__xr_accept_session` to enter XR") or an expected-state check; there is no padding and no explanation of XR concepts Claude already knows. Nothing could be trimmed, so it exceeds the level-4 anchor.	5 / 5
Actionability	Fully executable guidance: exact MCP tool names for all seven steps, specific expected values ("`visibilityState` is `\"visible\"`"), and a concrete invocation example ("/xr-mode-test \"MODE\|RESET\"" as a log-pattern filter). This matches the copy-paste-ready level-5 anchor; there are no gaps on the common path.	5 / 5
Workflow Clarity	The 7-step sequence is clear with explicit verification checkpoints after each state change (steps 3, 6, and 7), matching the checkpoint presence of level 5. It falls to 4 because there is no error-recovery guidance — e.g., what to do if `xr_accept_session` fails or the session never ends — only a final "report whether each step passed or failed".	4 / 5
Progressive Disclosure	This is a short (~64-line), single-purpose, self-contained skill with well-organized sections (Test Flow, Arguments, Expected Results); no bundle files exist and none are needed, so the simple-skill exception applies and organization alone earns the top score. Nothing is inlined that belongs in a separate file, so it is above level 4.	5 / 5
	Total	19 / 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.

A strong description: concise, third-person, with an explicit 'Use when' clause covering three concrete trigger scenarios. Trigger coverage is good but could add common synonyms like 'WebXR', 'VR mode', or 'immersive session'.

Dimension	Reasoning	Score
Specificity	"Test XR session lifecycle and mode transitions" plus "verifying XR enter/exit behavior" names several concrete actions with only minor coverage gaps (device/log checks appear only in the body). It lists more than the 1-2 actions of the level-3 anchor but is not fully comprehensive of capabilities, so it fits the level-4 anchor best.	4 / 5
Completeness	It explicitly answers both questions: the what ("Test XR session lifecycle and mode transitions") and a concrete multi-scenario when ("Use when verifying... testing... or debugging session state issues"), directly matching the anchor-5 example structure. The when-clause is specific and explicit, so it is above level 4.	5 / 5
Trigger Term Quality	Phrases like "verifying XR enter/exit behavior", "testing mode-dependent features", and "debugging session state issues" are natural things a user would say. Coverage is good but misses common synonyms and variants (e.g., "WebXR", "VR mode", "immersive"), so it is not the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	"XR session lifecycle", "XR enter/exit behavior", and "session state issues" carve out a clear niche with distinct, unlikely-to-collide triggers, matching the level-5 anchor. It is not the level-4 anchor because the triggers are specific enough that overlap with other skills is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: facebook/immersive-web-sdk
Path: .claude/skills/xr-mode-test/SKILL.md
Commit: 0778f51

Reviewed: 3 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.