test-ui

Test UIKitML asset and ScreenSpace UI behavior against the poke example using the iwsdk CLI.

Quality

67%

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-ui/SKILL.md

Quality

Content

77%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 body is a highly actionable, well-sequenced test procedure with concrete commands, exact assertions, and explicit recovery/retry loops; its main weaknesses are mild tighten-able prose and a monolithic single-file structure with no progressive disclosure into reference files.

Suggestions

Trim redundant prose such as the opening summary line and the 'no path tricks are required' aside so every line is an instruction or assertion.

Consider splitting the per-suite assertion details or the Known Issues section into a references/ file linked from a concise overview, to give the SKILL.md body a clearer one-level-deep structure.

Move the domain-specific Known Issues explanations into a referenced doc so the main body stays a pure executable checklist.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, executable command/assertion blocks that earn their tokens, but it also carries tighten-able prose such as the redundant opening 'Run 5 test suites covering...' line and explanatory asides like 'The CLI auto-discovers the IWSDK app root from cwd, so no path tricks are required', placing it at 'mostly efficient but could be tightened' rather than the fully lean anchor.	2 / 3
Actionability	Every test is a copy-paste-ready `npx iwsdk ...` command with exact `--input-json` payloads and precise assertions (e.g. `height` = `"50%"`, `ScreenSpaceUISystem: panels: 1`), matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps 1-5 are explicitly sequenced with validation checkpoints (parse JSON output, verify assertions before proceeding), a dedicated Recovery section with a retry feedback loop, and clear failure/skip gating, satisfying the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	The skill is a single self-contained file with no references/ scripts/ or assets/ bundles and no external file links, and at ~244 lines it exceeds the 'under 50 lines' allowance for a 3 on organization alone; sections are well-structured but all content is inline with no one-level-deep reference split, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

57%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 niched, naming the exact domain, target example, and CLI tool, but it lacks an explicit 'Use when' trigger clause and offers only a single action verb rather than enumerating multiple concrete actions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when validating UI changes in the poke example or when ScreenSpace/panel behavior regresses.'

Enumerate concrete actions instead of the single verb 'Test', e.g. 'Verify panel loading, ScreenSpace layout values, and system/component registration.'

Include a couple of natural-language trigger terms a user would actually say (e.g. 'UI test', 'ScreenSpace layout check') alongside the proper-noun jargon.

Dimension	Reasoning	Score
Specificity	The description names the domain ('UIKitML asset and ScreenSpace UI behavior') and the tool ('iwsdk CLI') plus a concrete target ('the poke example'), but uses a single action verb ('Test') rather than listing multiple specific concrete actions, so it stops at the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' anchor.	2 / 3
Completeness	It clearly answers 'what' (test UIKitML/ScreenSpace behavior via iwsdk CLI against the poke example) but omits any 'Use when...' or equivalent explicit trigger guidance for when Claude should invoke it; per the rubric guidelines a missing 'Use when' clause caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces relevant domain keywords ('UIKitML', 'ScreenSpace UI', 'poke example', 'iwsdk CLI'), but these are proper-noun jargon with no natural user-facing trigger phrasing or common variations, matching 'some relevant keywords but missing common variations' rather than the full coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The combination of 'UIKitML asset', 'ScreenSpace UI', 'the poke example', and 'iwsdk CLI' carves out a very specific niche with distinct triggers that is unlikely to fire for any other skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 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-ui/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.