CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

make-interfaces-feel-better

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/make-interfaces-feel-better/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers dense, concrete, repo-aware guidance with an exemplary output-format specification, but it is undermined by triple redundancy (principles, mistakes table, checklist) and by referencing four detail files that are absent from the bundle, leaving key patterns inaccessible. Tightening the restated sections and fixing the reference structure would raise it substantially.

Suggestions

Ship the four referenced files (typography.md, surfaces.md, animations.md, performance.md) in the bundle — body sections like the Motion/CSS cross-fade and image-outline patterns defer to them, so their absence leaves dead links and incomplete guidance.

Consolidate the redundant restatements: the Common Mistakes table and Review Checklist each restate the 16 core principles, and the Reference Files section duplicates the Quick Reference table — merging them into a single review-oriented checklist would cut ~25 lines without losing information.

For workflow clarity, add a brief ordering to the review pass (e.g., static surface details first, then animation behavior, then performance properties) so the checklist has an explicit sequence rather than an unordered list.

DimensionReasoningScore

Conciseness

The 16 core principles are lean and each earns its place, but the body restates them three times — the Common Mistakes table ("Same border radius on parent and child", "Numbers cause layout shift"), the Review Checklist (14 items mirroring the principles), and a Reference Files list duplicating the Quick Reference table. This is anchor 3's 'mostly efficient but could be tightened', not 4, because roughly a quarter of the body is redundant restatement.

3 / 5

Actionability

Guidance is highly concrete — exact properties (`font-variant-numeric: tabular-nums`, `text-wrap: balance`, `initial={false}`), specific values (40×40px hit area, 0.96–0.97 press scale, ~100ms stagger), tokens, Tailwind classes, and a worked Before/After output format. It falls short of anchor 5 because several principles defer their actual patterns to reference files ("see animations.md for the Motion and CSS cross-fade patterns") that are not present in the bundle.

4 / 5

Workflow Clarity

The review workflow is well defined: a checklist of concrete checkpoints and a precisely specified output format ("one table per principle with a heading above it, one diff per row... omit that table entirely"). It matches anchor 4's clear checkpoints with minor gaps rather than 5, since there is no explicit ordering of the review pass itself and no verification step for the proposed changes.

4 / 5

Progressive Disclosure

Structure is good in intent — one-level-deep references clearly signaled in a Quick Reference table — but all four referenced files (typography.md, surfaces.md, animations.md, performance.md) are missing from the bundle, so every reference link is a dead end, and the same four links are listed twice with near-identical descriptions. Missing reference targets and duplicated navigation exceed anchor 4's 'minor organization gaps', fitting anchor 3's 'could be better organized'.

3 / 5

Total

14

/

20

Passed

Description

91%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.

A strong description that explicitly covers what the skill provides and when to use it, with an unusually rich set of natural trigger phrases. Its only weaknesses are an abstract core capability statement and a few overly broad trigger terms that could fire on ordinary frontend work.

DimensionReasoningScore

Specificity

The description lists many specific topic areas ("hover states, shadows, borders, typography, micro-interactions, enter/exit animations"), giving broad concrete coverage, but the headline capability statement ("Design engineering principles for making interfaces feel polished") is abstract rather than a concrete action, matching anchor 4's 'several specific actions; minor gaps' rather than the fully concrete anchor 5.

4 / 5

Completeness

Both parts are explicit: the 'what' ("Design engineering principles for making interfaces feel polished") and a detailed 'when' ("Use when building UI components, reviewing frontend code... or any visual detail work") reinforced by a second concrete trigger list — mirroring the anchor 5 example's structure. Not 4 because the 'when' clause is already maximally explicit with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings like "make it feel better" and "feels off" appear verbatim, alongside comprehensive synonyms spanning every topic area ("stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows") — matching anchor 5's comprehensive natural-term coverage. Not 4 because no common variation of the polish request is conspicuously missing.

5 / 5

Distinctiveness Conflict Risk

The framing is consistently niche-focused ("polished", "feels off", "visual detail work"), giving a clear identity, but trigger terms like "borders", "typography", and "shadows" appear in nearly any frontend conversation, creating minor overlap risk with general frontend/design skills — anchor 4's 'mostly distinct; minor overlap risk'.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository

simstudioai/sim

Path

.agents/skills/make-interfaces-feel-better/SKILL.md

Reviewed

Table of Contents

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.