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

48%

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

60%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 a highly actionable, code-rich design-engineering reference with a strong decision framework and review checklist. Its weaknesses are verbosity from philosophical padding and a complete lack of progressive disclosure — everything lives in one 680-line file.

Suggestions

Move the philosophical material (Core Philosophy, Paul Graham quote, The Sonner Principles, 'Cohesion matters', 'Review your work the next day') into a separate reference file or trim it, keeping SKILL.md focused on actionable guidance.

Split the large reference material (CSS Transform Mastery, clip-path patterns, Debugging Animations) into reference files under references/ and link to them from a concise overview in SKILL.md to enable progressive disclosure.

Remove explanations of CSS basics Claude already knows (percentage translate semantics, scale affecting children) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The ~680-line body is noticeably verbose: the Core Philosophy section, a Paul Graham quote, The Sonner Principles, 'Cohesion matters', and 'Review your work the next day' are padded/philosophical, and a few passages explain basics Claude already knows (e.g. percentage translate, scale affecting children). It is above a 1 because the technical sections are largely code-dense and useful, but below a 3 due to several clearly unnecessary sections.	2 / 5
Actionability	It provides extensive copy-paste-ready code in CSS/JSX/JS, exact cubic-bezier curves, millisecond duration tables, a Before/After/Why review table, and a concrete review checklist covering the common cases. It fully meets the 'executable, copy-paste ready, covers common cases' anchor.	5 / 5
Workflow Clarity	The Animation Decision Framework is a clearly ordered 4-step sequence, the Review Checklist and Debugging Animations sections provide checklists and a slow-motion/frame-by-frame feedback loop. It is not a 5 because there is no strict validate->fix->retry procedural workflow, though the destructive/batch cap does not apply to this design-review skill.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the entire skill is a ~680-line monolithic SKILL.md with no references to separate files; detailed material (CSS reference, Sonner principles, debugging guide) that belongs in separate reference files is inlined. The good in-file section headers keep it above a 1, but the total absence of across-file disclosure holds it below a 3.	2 / 5
	Total	13 / 20 Passed

Description

36%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 design-engineering niche but frames it as philosophy rather than capability, lists no concrete actions, and provides no 'when to use it' trigger guidance. It is distinguishable yet under-specified for triggering.

Suggestions

Rewrite in third person around concrete actions, e.g. 'Reviews and refines UI code for animation, component polish, and interaction feel, applying Emil Kowalski's design engineering principles.'

Add an explicit 'Use when ...' clause naming natural trigger phrases such as 'UI polish', 'animation timing/easing', 'component feel', 'microinteractions', or 'making the interface feel right'.

Replace the philosophical framing ('invisible details that make software feel great') with concrete capability and trigger terms to lift specificity and trigger quality.

Dimension	Reasoning	Score
Specificity	Names specific domains ('UI polish, component design, animation decisions') but the only stated action is the vague 'encodes ... philosophy', with no concrete capabilities listed. It is above a 1 because the domains are concrete, but below a 3 since no real actions are described.	2 / 5
Completeness	It offers only a vague 'what' ('encodes Emil Kowalski's philosophy on ...') and entirely omits any 'when'/Use-when trigger guidance, which caps completeness. It is not a 3 because the 'what' is not a clear capability, and not a 1 because a domain is at least named.	2 / 5
Trigger Term Quality	It includes some relevant keywords a user might say ('UI polish', 'component design', 'animation'), but they are embedded in philosophical framing ('invisible details that make software feel great') and miss common natural variations and trigger phrases. Not a 4 because coverage of natural user terms is incomplete and not a 2 because several domain-relevant terms are present.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to a named person's philosophy (Emil Kowalski) and specific domains gives it a recognizable niche, but 'UI polish, component design, animation' broadly overlaps with general frontend/design skills. Not a 4 because overlap risk with related design skills remains non-trivial.	3 / 5
	Total	10 / 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 (681 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: simstudioai/sim
Path: .agents/skills/emil-design-eng/SKILL.md
Commit: 417ae20

Reviewed: 3 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.