CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

responsive-units

Use when reviewing stylesheets, component styles, and responsive behavior related to Use relative units for responsive layouts. Check the rendered layout across breakpoints and interaction states before proposing a fix.

Quality

73%

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 ./skills/responsive-units/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 lean, well-structured overview with an appropriately disclosed one-level reference file and concrete unit-selection rules. Its main weaknesses are the absence of an explicit verification step in the Check→Fix workflow (it is only in rule.md) and a small amount of concept explanation Claude already knows in the intro paragraph.

Suggestions

Add an explicit validation checkpoint to the main workflow (e.g. after Fix: 'Verify the rendered layout at affected breakpoints and confirm computed styles in DevTools before finishing'), since the Check step is a batch operation over the stylesheet.

Trim or cut the opening paragraph explaining why fixed px harms accessibility — Claude already knows this and rule.md repeats it under 'Why It Matters'.

State the px→rem conversion rule (divide px by the root font size, e.g. 16px base → 1rem) in the body or Quick Reference so the most common fix needs no reference hop.

DimensionReasoningScore

Conciseness

The ~30-line body is mostly lean directives ('Find all px-based font-size, width, and padding values…', 'Convert fixed px font sizes to rem equivalents'), but the opening paragraph 'Fixed pixel values override user browser preferences, making your site inaccessible…' explains a px-vs-rem concept Claude already knows and duplicates rule.md's 'Why It Matters' section.

4 / 5

Actionability

Quick Reference gives concrete unit-choice rules ('Use rem for font sizes', 'Use clamp() for fluid typography') and Check/Fix are executable directives, with code examples correctly placed in references/rule.md. Minor gap: the px→rem conversion rule (divide by 16) is never stated in the body and is only implicit in rule.md code comments.

4 / 5

Workflow Clarity

A rough Check → Fix → Explain → Code Review sequence is present, but no validation checkpoint is wired into the flow — verification steps live only in rule.md's Verification section. Since the Check step is a batch operation across a whole stylesheet ('Find all px-based… values'), the missing feedback loop caps this dimension at 3 per the rubric's batch-operations rule.

3 / 5

Progressive Disclosure

The body is a clear, well-sectioned overview and the single bundle file (references/rule.md, verified to exist) is one level deep and clearly signaled: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md.' Code examples are appropriately split into the reference.

5 / 5

Total

16

/

20

Passed

Description

62%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 has an explicit 'Use when…' trigger and identifies its CSS-responsive domain, but the 'what' stays at generic review-level verbs, omits the term 'CSS' and unit names (rem, em, px), and splices the rule title awkwardly into the sentence. It would benefit from naming the concrete capability — converting fixed px values to relative units — and from more natural trigger vocabulary.

Suggestions

State the concrete capability explicitly, e.g. 'Convert fixed px font-size, width, and padding values to rem/em/%/clamp() equivalents in CSS.'

Add missing natural trigger terms users would say: 'CSS', 'responsive design', 'media queries', and the unit names 'rem', 'em', 'px'.

Remove the awkward title splice 'related to Use relative units for responsive layouts' — either rephrase naturally or move the rule name into the metadata.

DimensionReasoningScore

Specificity

Names the domain ('stylesheets, component styles, and responsive behavior') and a couple of actions ('Check the rendered layout across breakpoints and interaction states before proposing a fix'), but these are generic review verbs — the concrete capability of converting fixed px values to rem/em/% is never stated, so coverage is not comprehensive.

3 / 5

Completeness

Both 'what' (review styles, check rendered layout, propose a fix) and an explicit 'Use when reviewing stylesheets…' clause are present. Not a 5 because the 'what' is weak — the actual fix action is only implied via the awkward title-splice 'related to Use relative units for responsive layouts' rather than concrete trigger phrases like px or rem.

4 / 5

Trigger Term Quality

'stylesheets', 'responsive behavior', and 'breakpoints' are natural terms, but the word 'CSS' itself never appears, nor do common user phrases like 'media queries', 'responsive design', or the unit names 'rem'/'em'/'px' — so common variations and synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

Scoped to responsive-unit review in stylesheets — a mostly distinct niche with only minor overlap risk against closely related CSS-review skills (e.g., media-query or accessibility review); it lacks the unit-name or extension triggers that would make it fully distinct.

4 / 5

Total

14

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/responsive-units/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.