test-grab

Test grab system (distance grab, one-hand grab, two-hand grab) against the grab example using the iwsdk CLI.

Quality

86%

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

100%Weight 40%Scale 1-3

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

The skill body is a well-engineered, executable test harness: concise, fully actionable commands with explicit assertions, a clear sequenced workflow with validation checkpoints and a bounded recovery loop, and clean section organization with no external-reference overhead. It is a strong example of an instruction-only skill done well.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational: it jumps straight into numbered steps with executable commands, asserts outcomes inline, and avoids explaining concepts Claude already knows (no preamble on what XR or grab is). Every line earns its place.	3 / 3
Actionability	Nearly every instruction is a copy-paste-ready `npx iwsdk ...` command with complete --input-json payloads, explicit timeouts, and concrete assertions ('Assert: Hovered present'), fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Steps 1-5 are explicitly sequenced with validation checkpoints (connectivity check, error-log assertion, snapshot/diff verification), a dedicated Recovery section gives a validate-restart-retry feedback loop, and the 'one retry per suite' rule bounds recovery — matching the rubric's feedback-loop anchor.	3 / 3
Progressive Disclosure	No bundle files exist, so the body is appropriately self-contained for a single-task skill: it is organized into clearly signaled sections (Pre-test Setup, Component Reference, Suites 1-5, Recovery, Known Issues) with no nested references to follow, which warrants a top score under the simple-skills note.	3 / 3
	Total	12 / 12 Passed

Description

72%Weight 40%Scale 1-3

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 specific and clearly occupies a distinct niche, but it omits an explicit 'Use when...' trigger clause, leaving the when-to-use signal only implied and capping completeness. Trigger-term coverage is decent but missing common user phrasings.

Suggestions

Add an explicit trigger clause, e.g. 'Use when verifying grab interactions (distance, one-hand, two-hand) in the IWSDK grab example.'

Broaden trigger terms with natural user phrasings such as 'XR grab', 'controller grab', or 'grab interaction tests' to improve discoverability.

Consider stating the success criterion (PASS/FAIL across 5 suites) so the what-it-does side is even more concrete.

Dimension	Reasoning	Score
Specificity	Names three concrete capability axes (distance grab, one-hand grab, two-hand grab) and the concrete tool (iwsdk CLI) plus the target (grab example), listing multiple specific concrete actions rather than vague language.	3 / 3
Completeness	Clearly states what the skill does (test the grab system via iwsdk CLI) but has no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should reach for it, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms like 'grab', 'distance grab', 'one-hand grab', and 'two-hand grab' that a user would say, but lacks common phrasings or synonyms a user might naturally invoke (e.g. 'XR grab', 'controller grab', 'test grab interactions'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The narrow niche of testing an XR grab system with named grab modes against a specific example via a specific CLI is highly distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: facebook/immersive-web-sdk
Path: .claude/skills/test-grab/SKILL.md
Commit: 0fb2195

Reviewed: 7 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.