baseline-ui

Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.

Quality

92%

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

Quality

Content

100%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.

A well-organized, lean constraint catalog that is immediately actionable without concept padding. It scores strongly across all dimensions as a simple, self-contained instruction skill.

Dimension	Reasoning	Score
Conciseness	Lean constraint-style lines with no explanation of concepts Claude already knows (e.g. no 'what Tailwind is'); every token earns its place.	3 / 3
Actionability	Highly specific, applicable guidance such as 'use h-dvh' not 'h-screen', 'animate only compositor props (transform, opacity)', and 'MUST add an aria-label to icon-only buttons' — directly actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The /baseline-ui <file> usage clearly sequences the review output (violations, why it matters, concrete fix); the single-pass review task is unambiguous and involves no destructive/batch operation needing validation loops.	3 / 3
Progressive Disclosure	Self-contained SKILL.md with well-organized labeled sections and no nested references; the only external pointer (Base UI docs URL) is appropriately inline, so structure is clean and navigable.	3 / 3
	Total	12 / 12 Passed

Description

85%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.

A tight, third-person description that covers both capability and trigger clearly with concrete fix areas. Its main weakness is the non-standard trigger term 'deslop', which limits natural-keyword coverage.

Suggestions

Replace or supplement 'deslop' with natural phrasings users would actually say, e.g. 'clean up', 'tidy', or 'polish the UI'.

Add common trigger variations like 'fix spacing', 'UI review', or 'hierarchy/typography cleanup' to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete fix areas — 'fixing spacing, hierarchy, typography, and small layout issues' — naming several specific actions rather than vague domain mention.	3 / 3
Completeness	Explicitly answers what ('deslop UI code by fixing spacing, hierarchy, typography, and small layout issues') and when ('Use when the interface needs a fast cleanup or polish pass').	3 / 3
Trigger Term Quality	Includes some natural terms ('UI code', 'cleanup', 'polish pass') but 'deslop' is non-standard jargon and common phrasings like 'fix spacing' or 'tidy the interface' are missing, so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The UI cleanup/polish niche with triggers like 'fast cleanup or polish pass' is clearly distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ibelick/ui-skills
Path: skills/baseline-ui/SKILL.md
Commit: 2b3a114

Reviewed: 6 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.