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

63%

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

Quality

Content

77%

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 rich, highly actionable reference with concrete code, an ordered decision framework, and a verification checklist, scoring top marks on actionability and workflow clarity. It loses points for philosophical verbosity and for being a single monolithic file with no progressive disclosure into reference files.

Suggestions

Trim the motivational philosophy sections ('Taste is trained', 'Beauty is leverage', 'Unseen details compound') to one or two lines each to reduce token overhead.

Move the encyclopedic deep-dives (CSS Transform Mastery, clip-patterns, gesture interactions) into reference files and link to them from SKILL.md so the main file stays a concise overview.

Drop or condense basic-concept explanations Claude already knows (e.g. what translateY percentages or scale() do) and keep only the opinionated guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely specialized, actionable guidance, but at ~680 lines it also carries motivational/philosophical prose ('Taste is trained, not innate', 'Beauty is leverage', the Paul Graham quote) and some basic-concept explanation Claude already knows, so it is 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	It provides abundant copy-paste-ready CSS/JS/JSX, concrete cubic-bezier easing values, specific duration tables, and exact thresholds (velocity > 0.11), matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The Animation Decision Framework is an explicitly ordered sequence (Should this animate? -> Purpose? -> Easing? -> Speed?), reinforced by a required review-table format and a final Review Checklist that serves as verification; the domain is non-destructive, so the absence of a validate-retry loop does not cap the score.	3 / 3
Progressive Disclosure	Internal sections are well organized with clear headers and tables, but the skill is a monolithic 680-line single file with no reference files, and detailed deep-dives (CSS Transform Mastery, clip-path patterns, gesture interactions) are inline content that could be split out, matching 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 identifies a clear craft niche but is written as an abstract statement of what the skill 'encodes' rather than as concrete actions with explicit use-when triggers. It answers 'what' reasonably but omits 'when', which caps several dimensions at 2.

Suggestions

Lead with concrete verbs the skill performs, e.g. 'Reviews and fixes UI animations, applies easing curves and transform origins, and polishes component interactions.'

Add an explicit trigger clause such as 'Use when reviewing or improving UI polish, animations, transitions, or component micro-interactions.'

Include natural user phrasings ('make the UI feel polished', 'fix janky animations', 'improve transitions') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names several concrete domains ('UI polish, component design, animation decisions'), but the governing verb 'encodes ... philosophy' is abstract rather than a list of concrete actions, so it matches the 'names domain and some actions, but not comprehensive' anchor and not the multi-action score-3 example.	2 / 3
Completeness	The description states what the skill covers but provides no 'Use when ...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 even though the 'what' is present.	2 / 3
Trigger Term Quality	'UI polish' and 'animation decisions' are terms a user might say, but 'philosophy', 'component design', and 'invisible details' are not natural trigger phrases, and common variations ('make my UI feel polished', 'fix animations') are missing, so it falls short of full trigger coverage.	2 / 3
Distinctiveness Conflict Risk	The 'Emil Kowalski's philosophy' framing gives it a recognizable niche, but without explicit triggers it could still overlap with general frontend/UI or component-styling skills, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 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
skill_md_line_count	SKILL.md is long (683 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openstatusHQ/data-table-filters
Path: .agents/skills/emil-design-eng/SKILL.md
Commit: f1cbf2f

Reviewed: about 10 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.