check-ui

Audit Python-to-JavaScript UI bindings for Gradio _js calls, global window exposure, and ui/globals.d.ts registration.

Quality

76%

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 ./.github/skills/check-ui/SKILL.md

Quality

Content

85%

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 well-structured, actionable audit procedure with explicit validation checkpoints and clean sectioning. Its main weakness is mild redundancy between the goals/reporting/output sections that could be consolidated for token efficiency.

Suggestions

Merge 'Reporting Format' and 'Output Expectations' into a single 'Reporting' section to eliminate restated content.

Trim the 'Audit Goals' section so it only states criteria not already covered step-by-step in 'Procedure'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no concept explanations, direct commands), but the 'Reporting Format' and 'Output Expectations' sections largely restate each other and 'Audit Goals' overlaps the 'Procedure', so it could be tightened.	2 / 3
Actionability	It gives concrete executable commands (`pnpm eslint`, `pnpm tsc`, `pnpm build`), specific file paths, literal `_js=` pattern examples, and copy-paste-ready fix declarations.	3 / 3
Workflow Clarity	A six-step numbered procedure is clearly sequenced, and step 6 provides an explicit validation/feedback loop (run typecheck/lint/build and fix issues that arise).	3 / 3
Progressive Disclosure	Content is well-organized into clearly labeled sections with a single one-level-deep pointer (`core.instructions.md`); no monolithic wall or nested reference chains, and no skill bundle files are needed.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 distinctive with concrete actions, but lacks an explicit 'Use when...' trigger clause and leans on technical jargon, capping completeness and trigger-term quality. Adding natural-language trigger conditions would raise both dimensions.

Suggestions

Append a 'Use when...' clause naming natural triggers (e.g., 'Use when reviewing Python UI code that uses _js= callbacks or when debugging Python-triggered JavaScript bugs').

Soften jargon like 'global window exposure' toward phrasings a user would actually say, such as 'JavaScript functions exposed on the global window object'.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — auditing Gradio `_js` calls, global `window` exposure, and `ui/globals.d.ts` registration — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger guidance, so per the judging guidelines completeness is capped at 2 even though the 'what' is strong.	2 / 3
Trigger Term Quality	It uses domain-relevant terms (`_js`, Gradio, globals.d.ts) that a developer in this repo would say, but leans on technical jargon ('global window exposure') and omits common phrasings; not a full coverage of natural trigger variations.	2 / 3
Distinctiveness Conflict Risk	The niche is highly specific (Gradio `_js` Python-to-JS binding audits with globals.d.ts registration) and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 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: vladmandic/sdnext
Path: .github/skills/check-ui/SKILL.md
Commit: 058a7f0

Reviewed: 1 day 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.