CtrlK
BlogDocsLog inGet started
Tessl Logo

test-audio

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

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

81%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.

The content is a highly executable, well-sequenced test workflow with strong validation and recovery guidance, scoring top marks on actionability and workflow clarity. Its only weakness is mild redundancy and a few trims available for conciseness.

Suggestions

Dedupe the JSON-boolean warning: keep it once (e.g. in Known Issues) and reference it from the IMPORTANT block rather than restating it.

Tighten explanatory asides like 'The audio example uses a native scene level that creates entities via composition' to the minimum needed to justify the ecs find approach.

Consider extracting the Known Issues & Workarounds into a references file so the main SKILL.md stays a lean overview of the run procedure.

DimensionReasoningScore

Conciseness

The body is mostly command-focused and efficient, but the JSON-boolean warning is repeated in the IMPORTANT block and the Known Issues section, and a few explanatory asides (e.g. about native scene composition) could be trimmed.

3 / 5

Actionability

Every step gives copy-paste-ready `npx iwsdk` commands with full --input-json payloads, explicit timeouts, and concrete assertions, fully covering the common audio test cases.

5 / 5

Workflow Clarity

Steps 1-5 are explicitly sequenced with validation checkpoints (connectivity check, error-log assertions), and a Recovery section provides a validate-fix-retry feedback loop with a one-retry cap.

5 / 5

Progressive Disclosure

No bundle files exist, so the single-file body is self-contained and well-sectioned into Steps/Suites/Known Issues; minor organization gaps (e.g. the Known Issues block could be a separate reference) keep it just below 5.

4 / 5

Total

17

/

20

Passed

Description

58%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 clearly states what the skill does and names specific audio test areas, but it lacks an explicit 'when to use' trigger clause and leans on technical jargon over natural user phrasing. It is distinct within the iwsdk skill set.

Suggestions

Add a 'Use when ...' clause naming natural triggers, e.g. 'Use when testing the iwsdk audio example or debugging AudioSource playback/loading/spatial-audio behavior.'

Soften jargon in the trigger phrasing (e.g. pair 'AudioSource' with the more natural term 'audio component') and include synonyms users might actually say.

Consider stating the outcome (e.g. 'verifies ECS audio state transitions') to round out the 'what' beyond listing test areas.

DimensionReasoningScore

Specificity

Names the audio domain and several concrete test actions ('AudioSource loading, playback state, stop, spatial audio'), comparable to the 4-anchor; not a 5 because the listed actions are testing scopes rather than a comprehensive set of distinct operations.

4 / 5

Completeness

The 'what' is clear ('Test audio system ... against the audio example using the iwsdk CLI') but there is no 'Use when...' trigger clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant terms like 'audio', 'playback', and 'spatial audio' appear, but the phrasing leans technical ('AudioSource', 'iwsdk CLI') and omits common synonyms or natural variations a user might say.

3 / 5

Distinctiveness Conflict Risk

The scope is tightly bound to the iwsdk audio example and AudioSource component, giving it a clear niche with only minor overlap risk against other iwsdk test skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.