test-level

Test level system (LevelRoot, LevelTag, authored environment, scene hierarchy) against the poke 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-level/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.

This is a strong, executable test procedure: exact CLI commands with JSON payloads, explicit assertions and expected values, well-sequenced steps with validation checkpoints, defined failure paths, and a bounded retry loop. The only real room for improvement is trimming mildly verbose explanatory passages and moving the 'Known Issues & Workarounds' detail into a separate reference file.

Suggestions

Trim second-order explanations, e.g. the fixture-loading rationale in Test 2.2 ('This fixture loads ./public/scenes/...') and the LevelSystem.update() internals, keeping only what the assertion needs.

Move 'Known Issues & Workarounds' into a references/ file (e.g. references/known-issues.md) and link it from the body so the main procedure stays lean.

Consider moving the per-suite command/assertion details into a per-suite reference or shared fixture note if more suites are added, keeping SKILL.md as the orchestration overview.

Dimension	Reasoning	Score
Conciseness	The body is dominated by exact commands, JSON payloads, and assertions with essentially no padding about concepts Claude already knows, and the 'Known Issues' section documents source-specific behavior (identity enforcement, entity 0, level-tag fallback) Claude cannot infer. It sits at anchor 4 rather than 5 because sections like the fixture-URL explanation in Test 2.2 and parts of 'Known Issues' could be trimmed.	4 / 5
Actionability	Every test is a copy-paste-ready 'npx @iwsdk/cli ... --input-json' command with an exact payload, a defined placeholder (<root>, <any-tagged>), and concrete expected values ('id' = '/scenes/poke.iwsdk.scene.json', 10 entities) — fully executable guidance covering the common cases, matching anchor 5.	5 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced with explicit validation checkpoints (parse JSON and verify assertions before the next command, poll for server readiness, browser-log error checks), defined failure paths (report FAIL and skip to Step 5), and a recovery feedback loop with a retry budget — the anchor 5 pattern including error-recovery loops. The destructive/batch cap does not apply since assertions gate every operation.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is one well-sectioned document with clear headers, so nothing is buried or nested; however, it is ~250 lines with no external references, and content such as 'Known Issues & Workarounds' could be split into a reference file. That places it at anchor 4 ('good structure; most content appropriately placed; minor organization gaps') rather than 5, which expects well-signaled one-level-deep references or a short simple skill.	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.

The description is specific, precise, and distinctive within its niche, clearly stating what is tested and with which tool and fixture. Its one material weakness is the absence of any 'Use when...' trigger guidance, which both caps completeness and leaves natural trigger phrasings untapped.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the level system (LevelRoot/LevelTag) or scene loading changes and you need to verify it still passes the poke example tests.'

Add one or two natural trigger variations such as 'run the level tests' or 'verify level loading' so users phrasing the request differently still match.

State the expected outcome ('runs 5 suites and reports a PASS/FAIL table') so the 'what' covers the deliverable, not just the activity.

Dimension	Reasoning	Score
Specificity	'Test level system (LevelRoot, LevelTag, authored environment, scene hierarchy) against the poke example using the iwsdk CLI' names one concrete action but precisely enumerates the test subjects, target fixture, and tool — matching anchor 4 ('several specific actions; minor gaps') rather than anchor 3, since it is far more informative than a bare domain-plus-action statement. Not 5 because it lists a single action rather than multiple distinct capabilities.	4 / 5
Completeness	The 'what' is clear (test the level system's LevelRoot, LevelTag, authored environment, and scene hierarchy against the poke example), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at anchor 3. Not 4 because the 'when' is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	'test', 'level system', 'LevelRoot', 'LevelTag', 'scene hierarchy', 'poke example', and 'iwsdk CLI' are natural phrases a user in this domain would say, giving good keyword coverage (anchor 4). Not 5: missing common variations such as 'run tests', 'verify', or 'regression' that users might use.	4 / 5
Distinctiveness Conflict Risk	Highly niche identifiers ('iwsdk CLI', 'poke example', 'LevelRoot', 'LevelTag') give it a clear niche with distinct triggers and minimal conflict risk with any other skill — matching anchor 5.	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-level/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.