test-interactions

Test XR interactions (ray, poke/touch, dual-mode, audio, UI panel) against the poke example using the iwsdk CLI.

Quality

81%

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

88%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.

This is a strong operational runbook: fully executable commands, explicit assertions, and a validation-after-every-step discipline with recovery and reporting built in. The main improvement opportunities are de-duplicating the repeated query/assert boilerplate across suites and moving suite details or known issues into reference files to shrink the monolithic body.

Suggestions

Factor the repeated 'query entity for [Hovered, Pressed] then assert' pattern into a single stated convention ('after each interaction command, query the target entity and check the listed components') instead of repeating full command blocks in every suite.

Consider moving per-suite details or the Known Issues & Workarounds section into a reference file (e.g. references/known-issues.md), keeping SKILL.md as a tighter overview with clearly signaled links.

State the placeholder-substitution convention once at the top (e.g. '<z+0.3> means robot-pos.z + 0.3') and drop the repeated inline 'where' notes.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable command blocks with almost no explanation of concepts Claude already knows, earning the 'efficient' anchor. It is not a 5 because of repeated boilerplate: near-identical ecs query assertion blocks recur across suites, and inline 'where <z+0.3> = ...' substitution notes are explained multiple times when one convention note up front would do.	4 / 5
Actionability	Every step is a fully executable, copy-paste-ready CLI command with exact JSON payloads, timeouts, sleep durations, and a defined placeholder-substitution convention. The failure mode of ambiguous pseudocode is absent, matching the top anchor.	5 / 5
Workflow Clarity	A clear five-step sequence (install, start server, verify connectivity, run suites, cleanup/results) with explicit validation checkpoints after each command ('Parse the JSON output and verify assertions before moving to the next'), defined failure paths ('report FAIL for all suites and skip to Step 5'), and a Recovery section with a retry loop. This matches the anchor with explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	The single file is well-sectioned (steps, numbered suites, recovery, known issues) with no buried or nested references, and no bundle files exist that need signaling. It is not a 5 because at ~600 lines the repetitive per-suite command blocks and the Known Issues section are candidates for splitting into reference files, leaving SKILL.md as a tighter overview.	4 / 5
	Total	18 / 20 Passed

Description

75%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.

The description is specific, well-targeted, and highly distinct, naming five concrete interaction modes plus the exact tool and target example. Its main gap is the absence of any explicit 'Use when...' trigger guidance, which both limits completeness and leaves the user to infer when to invoke it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to test or verify XR interactions in an IWSDK example, or mentions ray, poke/touch, hand, audio, or UI-panel interaction testing.'

Include natural synonyms users might say, such as 'XR testing', 'hover/select', and 'hand tracking', to broaden trigger term coverage.

Consider noting the outcome it produces (a 12-suite PASS/FAIL report) so the 'what' also conveys the deliverable.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities ("ray, poke/touch, dual-mode, audio, UI panel") and grounds them in a concrete target and tool ("against the poke example using the iwsdk CLI"), giving comprehensive coverage of what the skill does. It is not a 4 because the coverage has no notable gaps; each interaction mode the skill handles is named.	5 / 5
Completeness	The "what" is clear (test XR interaction behaviors via the iwsdk CLI against the poke example), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because the "when" is entirely missing rather than merely implicit-but-present.	3 / 5
Trigger Term Quality	Natural trigger phrases like "XR interactions", "ray", "poke/touch", "audio", and "UI panel" give good keyword coverage a user working in this codebase would plausibly say. It falls short of 5 because common variations and synonyms such as "hand tracking", "hover/select", or "XR testing" are absent.	4 / 5
Distinctiveness Conflict Risk	References to "the poke example" and "the iwsdk CLI" establish a clear niche with distinct triggers, so it is unlikely to fire for unrelated skills. It clearly matches the top anchor rather than the 'minor overlap risk' anchor below it.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (613 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: facebook/immersive-web-sdk
Path: .claude/skills/test-interactions/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.