CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, action-oriented, and well-structured with concrete tool calls and verification steps, but it lacks an explicit failure-recovery feedback loop, capping workflow clarity at 2. It appropriately keeps everything inline given the skill's scope and absence of bundle files.

Suggestions

Add an explicit error-recovery branch after the verification steps (e.g., 'If session is not active after xr_accept_session, retry once or report the failure and stop') to reach the score-3 workflow_clarity anchor.

Specify expected handling when a tool call fails or returns an unexpected state, so Claude has a defined feedback loop rather than only happy-path checks.

DimensionReasoningScore

Conciseness

The body is a lean procedural sequence using specific MCP tool invocations and brief bullets, with no padding or explanation of concepts Claude already knows; every line earns its place per the score-3 anchor.

3 / 3

Actionability

Each step gives a concrete, named executable tool call (e.g. 'mcp__iwsdk-dev-mcp__xr_accept_session') plus expected sub-states like 'visibilityState is "visible"', matching the score-3 anchor of fully executable, copy-ready commands rather than vague direction.

3 / 3

Workflow Clarity

Steps 1-7 are clearly sequenced with explicit verification checkpoints after transitions (steps 3, 6, 7), which exceeds the score-2 'checkpoints missing' anchor, but no explicit failure-recovery/feedback loop is specified, so it falls short of the score-3 'feedback loops for error recovery' anchor.

2 / 3

Progressive Disclosure

This is a self-contained single-purpose skill with no bundle files and clean sectioning (Test Flow, Arguments, Expected Results), fitting the rubric's simple-skill carve-out where well-organized sections alone warrant a 3 with no need for external references.

3 / 3

Total

11

/

12

Passed

Description

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.

The description is concise, action-oriented, and clearly defines both the skill's purpose and explicit trigger conditions, with concrete XR-specific actions and natural trigger terms. It is well above the bad examples and on par with the good examples.

DimensionReasoningScore

Specificity

Names multiple concrete actions—'Test XR session lifecycle', 'mode transitions', 'verifying XR enter/exit behavior', 'testing mode-dependent features', 'debugging session state issues'—matching the score-3 anchor of listing several specific concrete actions rather than just a domain.

3 / 3

Completeness

Explicitly answers what ('Test XR session lifecycle and mode transitions') and when ('Use when verifying XR enter/exit behavior...'), matching the score-3 anchor for both what AND when with an explicit 'Use when' trigger.

3 / 3

Trigger Term Quality

Covers natural terms a user would say—'XR enter/exit', 'mode-dependent features', 'session state issues', 'debugging'—with good variation, matching the score-3 anchor rather than the partial coverage of score 2.

3 / 3

Distinctiveness Conflict Risk

The XR session-lifecycle niche is narrowly scoped with distinct XR/mode/session triggers unlikely to overlap with unrelated skills, matching the score-3 anchor of a clear niche with distinct triggers.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
facebook/immersive-web-sdk
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.