test-audio

Test audio system (AudioSource loading, playback state, stop, spatial audio) against the audio example using the iwsdk CLI.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/test-audio/SKILL.md

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.

A high-quality, execution-focused skill body: every step is an executable CLI command with explicit assertions, validation checkpoints, failure short-circuits, and a bounded recovery loop. The main improvements are trimming duplicated guidance (the boolean warning appears twice) and moving the long known-issues detail into a reference file.

Suggestions

Remove the duplicate boolean-value warning: it appears both in the top-level IMPORTANT block and in 'Known Issues & Workarounds'; keep it once (preferably the known-issues entry) and cross-reference it.

Move the 'Known Issues & Workarounds' section into a references/ file (e.g., references/known-issues.md) to reduce SKILL.md length, keeping a one-line pointer, since it is lookup material rather than run-order instructions.

Consider consolidating the near-verbatim dev-server commands in Step 2, Recovery, and Step 5 into a single defined procedure referenced from the other locations.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven: nearly every section is an executable command plus assertions, with no explanation of concepts Claude already knows. Not a 5 because of minor redundancy — the boolean-vs-string warning appears twice (top-level IMPORTANT block and again under 'Known Issues & Workarounds'), and the recovery/known-issue guidance repeats a few commands verbatim.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout, each with exact JSON payloads, timeouts, and concrete pass/fail assertions (e.g., '_loaded = true', 'AudioSystem at priority 0', 'available array matching maxInstances'). Placeholders like <audio> are explicitly defined ('Save the first as <audio>'), and edge-case handling (loop-before-play to keep state observable) is concretely specified.	5 / 5
Workflow Clarity	Clear sequenced steps (install → background dev server → connectivity check → pre-test setup → six suites → cleanup/summary) with explicit validation checkpoints at each stage: 'If the server fails to start within 60 seconds, report FAIL for all suites and skip to Step 5', the error-log assertion in pre-test setup, a dedicated Recovery section with a bounded retry loop ('Only give up after one retry attempt per suite'), and a final summary table requiring actual-vs-expected values on failure.	5 / 5
Progressive Disclosure	No bundle files exist, and the body is well-sectioned (configuration, steps, per-suite headings, recovery, known issues), so navigation within SKILL.md is easy. Not a 5 because at ~280 lines it exceeds the simple-skill threshold: content such as the 'Known Issues & Workarounds' details and per-suite assertions could be offloaded to reference files, keeping SKILL.md at a leaner overview level.	4 / 5
	Total	18 / 20 Passed

Description

70%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 specific, distinctive, third-person description that names concrete capabilities and the tool used, but it lacks any 'when to use' trigger guidance, which limits its discoverability and caps completeness. Adding an explicit use-when clause and a few natural synonyms would make it fully effective.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to verify audio behavior in the iwsdk audio example, when audio playback, spatial/positional audio, or AudioSource components seem broken, or when running the audio test suites.'

Include natural synonym phrasing users might say, such as 'sound', 'positional/3D audio', and 'volume', so the description matches more trigger utterances.

Optionally enumerate the full suite coverage (system registration, component schema, stability) so the description's capability list matches what the skill actually does.

Dimension	Reasoning	Score
Specificity	The description lists several concrete test areas — 'AudioSource loading, playback state, stop, spatial audio' — plus the concrete tool ('iwsdk CLI') and target ('the audio example'). Not a 5 because coverage of what the testing entails is a terse enumeration; minor gaps (e.g., no mention of system registration, component schema, or stability checks that the skill actually performs).	4 / 5
Completeness	The 'what' is clear and concrete (test the audio system against the audio example with the iwsdk CLI), but there is no 'Use when...' or equivalent trigger clause — when to invoke this skill is entirely unstated. Per the judging guideline, a missing 'Use when' clause caps completeness at 3; it is not a 2 because the 'what' is specific rather than vague.	3 / 5
Trigger Term Quality	Good natural-keyword coverage: 'audio system', 'AudioSource', 'playback', 'spatial audio', 'stop', 'audio example' are phrases a user working in this codebase would plausibly say. Not a 5 because common synonyms and variations are missing ('sound', 'positional audio', '3D audio', 'audio testing', 'volume').	4 / 5
Distinctiveness Conflict Risk	Clear niche with minimal conflict risk: it is scoped to the iwsdk audio example, the AudioSource component, and spatial audio, which distinguishes it from generic audio/media skills and from other iwsdk example testers. It would not plausibly trigger for the wrong skill.	5 / 5
	Total	16 / 20 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-audio/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.