emil-design-eng

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Quality

62%

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 ./skills/emil-design-eng/SKILL.md

Quality

Content

71%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 body is highly actionable with executable, copy-paste-ready code and a well-sequenced decision framework, but it is over-long for a single file with philosophical padding and no progressive disclosure into reference files. Splitting large reference sections into separate files and trimming the philosophy prose would materially improve it.

Suggestions

Move the CSS Transform Mastery, clip-path, and Performance reference material into separate reference files (e.g., references/css-transforms.md, references/clip-path.md) linked one level deep from SKILL.md.

Trim the philosophical narrative sections ('Taste is trained, not innate', 'Beauty is leverage', the Paul Graham quote, Sonner cohesion prose) to a sentence each or remove them, keeping the actionable rules.

Add explicit verification checkpoints to the Animation Decision Framework (e.g., 'After choosing a duration, re-check the frequency table to confirm it should animate at all').

Dimension	Reasoning	Score
Conciseness	The actionable code and rules are efficient and don't re-explain basics Claude knows, but sizable philosophical narrative ('Taste is trained, not innate', the Paul Graham quote, 'Beauty is leverage', Sonner cohesion prose) is padding that could be trimmed.	3 / 5
Actionability	Extensive copy-paste-ready CSS/JS/JSX examples with specific cubic-bezier curves, duration/easing tables, and named libraries (Radix, Framer Motion, Sonner, Vaul) cover the common cases fully.	5 / 5
Workflow Clarity	The Animation Decision Framework is a clearly sequenced four-step process and the mandated Review Format plus Review Checklist act as checkpoints; minor validation gaps exist but the skill is advisory rather than destructive so the destructive cap does not apply.	4 / 5
Progressive Disclosure	Internal section headers provide structure, but the ~675-line skill is a single monolithic file with no bundle files and no references to separate files; content like the CSS reference, gesture patterns, and clip-path catalog that belong in separate files is inlined.	3 / 5
	Total	15 / 20 Passed

Description

53%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 names a clear, distinctive niche tied to a specific person and several focus areas, but it omits any 'Use when...' trigger guidance and frames capabilities as 'philosophy' rather than concrete actions. Adding an explicit when-to-use clause and action verbs would lift the capped dimensions.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when building or reviewing UI, deciding on animations, or polishing component interactions') to satisfy the completeness 'when' requirement.

Replace 'encodes philosophy on' with concrete action verbs the skill performs (e.g., 'Reviews and guides animation decisions, component design, and UI polish').

Add natural trigger synonyms users actually say, such as 'animations', 'motion', 'CSS transitions', and 'Framer Motion'.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete focus areas ('UI polish, component design, animation decisions, and the invisible details'), but uses 'encodes philosophy on' rather than listing concrete actions performed, fitting the 'names domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It clearly states 'what' the skill does but provides no 'when' / 'Use when...' guidance; per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	The description surfaces relevant terms ('Emil Kowalski', 'UI polish', 'component design', 'animation decisions', 'invisible details') but is missing common variations a user would naturally say ('animations', 'motion', 'CSS animation', 'Framer Motion').	3 / 5
Distinctiveness Conflict Risk	The named-person framing ('Emil Kowalski's philosophy') plus 'invisible details' carves a distinct niche with only minor overlap risk against generic design/CSS skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (707 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: skills/emil-design-eng/SKILL.md
Commit: 1a7a23d

Reviewed: about 4 hours 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.