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.

1.42x

Quality

58%

Does it follow best practices?

Impact

90%

1.42x

Average score across 3 eval scenarios

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

The canonical home for this skill is emil-design-eng in emilkowalski/skills

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 content is highly actionable, with concrete code, decision tables, and checklists that make it easy to apply, and the animation framework gives a clear sequenced workflow. Its main weaknesses are a padded philosophy section and a monolithic single-file structure with no progressive disclosure to reference files.

Suggestions

Trim or relocate the "Core Philosophy" section so the file opens with actionable guidance and earns its tokens.

Split large reference material (CSS Transform Mastery, clip-path patterns, Performance Rules) into separate files under references/ and link to them from SKILL.md.

Add an explicit review feedback loop (review -> apply fixes -> re-verify against the checklist) to close the workflow with a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The bulk is lean, executable guidance with code, but the "Core Philosophy" section ("Taste is trained, not innate", "Beauty is leverage", the Paul Graham quote) is padding that does not add actionable value, matching the score-3 anchor of mostly efficient with some unnecessary explanation.	3 / 5
Actionability	The body is packed with copy-paste-ready CSS/JS, concrete easing curves, specific duration tables, and decision matrices covering the common cases, matching the score-5 anchor of fully executable examples that cover common cases.	5 / 5
Workflow Clarity	The Animation Decision Framework is a clearly sequenced four-step process with decision tables, and the Review Checklist plus Debugging section provide checkpoints, but there is no explicit validate-fix-retry loop, fitting the score-4 anchor of a clear sequence with most checkpoints present and minor gaps.	4 / 5
Progressive Disclosure	No bundle files exist and the 680-line body inlines several large topics (CSS Transform Mastery, clip-path, Performance Rules) that could live in separate reference files; section headers give structure but content that should be split is inline, matching the score-3 anchor.	3 / 5
	Total	15 / 20 Passed

Description

45%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 conveys a clear topical niche (Emil Kowalski's design-engineering philosophy on UI polish and animation) but is framed abstractly rather than as concrete actions, and it omits any explicit "Use when..." trigger guidance.

Suggestions

Rewrite around concrete actions, e.g. "Reviews UI code for animation, transitions, and component polish; suggests fixes for easing, transform-origin, and timing."

Add an explicit trigger clause such as "Use when the user asks to review or polish UI animations, transitions, or component micro-interactions."

Include natural synonyms users actually say (transitions, micro-interactions, hover/press states, "feel") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("UI polish, component design, animation decisions") but uses the abstract action "encodes ... philosophy" rather than listing concrete actions like reviewing UI code or generating animations, matching the score-2 anchor of naming the domain with minimal/generic actions.	2 / 5
Completeness	There is a clear "what" (encodes a philosophy on UI polish and animation) but no "Use when..." clause or equivalent trigger guidance, so per the guideline a missing trigger caps completeness at the score-3 anchor (clear what, missing when).	3 / 5
Trigger Term Quality	"UI polish", "component design", and "animation decisions" are relevant keywords a user might say, but common synonyms and natural phrasings (transitions, micro-interactions, "polish my UI", animations) are missing, fitting the score-3 anchor of some relevant keywords without common variations.	3 / 5
Distinctiveness Conflict Risk	Tying it to "Emil Kowalski's philosophy" and "design engineering" gives it a niche, but the triggers (UI polish, animation, component design) overlap broadly with general frontend/design skills, matching the score-3 anchor of somewhat specific but with overlap risk.	3 / 5
	Total	11 / 20 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 (680 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: 1weiho/open-slide
Path: .agents/skills/emil-design-eng/SKILL.md
Commit: cc5d2ea

Reviewed: 2 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.