CtrlK
BlogDocsLog inGet started
Tessl Logo

styling

CSS and Tailwind, cn(), flex layouts. Use for "style this", "fix the CSS", "add classes", "not scrolling", "overflow", Tailwind utilities.

68

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A high-quality, repo-specific styling reference: executable Svelte code, good/bad contrasts, and a clear decision rule for the codebase's most common layout bug. Weakest point is mild repetition in the flex-scroll section and a few over-explanations of basic HTML/CSS knowledge.

DimensionReasoningScore

Conciseness

The body is largely lean — no intro fluff, no explanation of what Tailwind or Svelte are, and code examples carry the weight. Two trimmable spots: the flex fix is restated three times (table, 'All three are required' bullets, 'Rule of Thumb'), and bullets like 'disabled natively blocks clicks' and 'Semantically correct for accessibility' explain basic HTML knowledge Claude already has. That places it at 'efficient; minor instances of over-explanation' rather than the every-token-earns-its-place level of 5.

4 / 5

Actionability

Guidance is copy-paste ready: complete Svelte snippets for the good/bad wrapper cases, the disabled pattern with a concrete anti-pattern, good vs. 'Suspicious' primitive override examples, and before/after code for the scroll trap. The decision rules are executable as written ('If you write h-full on a flex child that has siblings... replace it with flex-1 min-h-0 overflow-hidden'), covering the common cases.

5 / 5

Workflow Clarity

For a guidelines skill, each section gives an unambiguous decision procedure — symptom, fix, and rule of thumb — and the disabled section contrasts pattern vs. anti-pattern explicitly. There are no validation checkpoints, but styling changes carry no destructive/batch risk that would require them, and no numbered sequence is needed for this skill type; the only gap is a light verification cue (e.g., how to confirm the scroll fix took effect). This is 'clear sequence with most checkpoints present' territory rather than the explicit validate/re-validate loop of 5, which doesn't apply here.

4 / 5

Progressive Disclosure

Structure is good: the header cleanly signals when to consult the external ui-design component-system reference versus when 'no external lookup' is needed, and sections are well-organized with scannable headers and a table. The one-level-deep reference is clearly signposted, though it lives outside this skill's bundle and could not be verified to exist here; and the ~90-line Flex Column Scroll Trap section is arguably a candidate for its own reference file. These are minor organization gaps consistent with the level-4 anchor rather than the fully-split, easy-navigation level of 5.

4 / 5

Total

17

/

20

Passed

Description

83%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: concrete capability list, explicit 'Use for' triggers phrased as natural user utterances, and a distinct CSS/layout niche. Minor gaps — the 'what' is a compressed keyword list and a few common trigger synonyms are missing.

DimensionReasoningScore

Specificity

The description names several concrete capabilities — 'CSS and Tailwind, cn(), flex layouts' — giving Claude specific tools to act on, though they are stated as topics rather than action verbs and coverage is not comprehensive (e.g., variants, disabled states, scroll layout fixes from the body are absent). It fits the 'lists several specific actions; minor gaps' anchor better than 3 (more than 1-2 concrete items) and falls short of 5's comprehensive coverage.

4 / 5

Completeness

Both what ('CSS and Tailwind, cn(), flex layouts') and when ('Use for "style this", "fix the CSS", "add classes", "not scrolling", "overflow", Tailwind utilities') are explicitly present with concrete quoted trigger phrases. The 'when' clause is maximally explicit; only the 'what' being a terse keyword list rather than a fuller statement keeps it close to, but still at, the top anchor — it answers both questions clearly and concretely.

5 / 5

Trigger Term Quality

Trigger phrases like '"style this"', '"fix the CSS"', '"add classes"', '"not scrolling"', and '"overflow"' are natural user utterances with good variety. It misses a few common synonyms (e.g., 'styling', 'layout is broken', 'make it scroll'), so it matches 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym-level anchor at 5.

4 / 5

Distinctiveness Conflict Risk

The CSS/Tailwind/styling niche with distinctive behavioral triggers ('not scrolling', 'overflow', 'cn()') is mostly distinct, but phrases like 'fix the CSS' and 'add classes' could overlap with a broader ui-design or component skill in the same workspace. It matches 'mostly distinct; minor overlap risk with closely related skills' rather than 5's minimal-conflict clear niche.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.