CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

responsive-size

Use when reviewing image assets, markup, and CDN or build transforms related to Serve images at the correct display size. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Quality

77%

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-size/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured, actionable review workflow with concrete thresholds, tooling, and an exemplary one-level-deep reference split. The main cost is redundancy: the bandwidth-waste rationale is repeated across the intro, Quick Reference, and Explain sections (with an internally inconsistent "4x the data" figure), and the body's verification step is gestured at rather than specified.

Suggestions

Consolidate the bandwidth-waste rationale into one place (e.g., keep only the Explain section) and fix the inconsistent math — the intro's "downloads 4x the data" contradicts the pixel-scaling figures (~16x, ~25x) used in Quick Reference and Explain.

Make the verification checkpoint explicit in the body, e.g., a short "Verify" step after Fix naming how to confirm in DevTools (compare rendered vs intrinsic width in the Network/Elements panel) instead of only "describe how to confirm the fix in DevTools".

Trim the intro paragraph to one or two sentences of motivation; the Lighthouse-audit context already appears in Quick Reference, so the duplicate mention can be cut.

DimensionReasoningScore

Conciseness

The body explains why oversized images waste bandwidth in three places — the intro paragraph ("serving a 1600px image downloads 4x the data users need"), Quick Reference bullet 1 ("wastes ~16x the necessary bandwidth"), and the Explain section ("bandwidth scales with pixel count, not linear dimensions") — a concept Claude already knows. The intro's "4x the data" claim is also inconsistent with the pixel-scaling figures (16x, 25x) used elsewhere, so tightening would both save tokens and remove the contradiction; this fits anchor 3 rather than anchor 4's minor trims.

3 / 5

Actionability

The Check and Fix sections give concrete, mostly executable guidance with specific thresholds ("more than 2x the rendered width", "images over 200px wide should have srcset variants"), named tools ("use Sharp or Squoosh"), exact variant widths ("400w, 800w, 1200w, 1600w"), and an inline sizes example. It stops short of anchor 5's copy-paste-ready code in the body — the actual HTML examples are deferred to references/rule.md — leaving minor gaps.

4 / 5

Workflow Clarity

A clear Check → Fix → Explain → Code Review sequence, with numbered steps inside Check and Fix and a verification cue ("describe how to confirm the fix in DevTools"; rule.md has Automated/Manual Checks). It matches anchor 4 rather than anchor 5 because the body's verification is mentioned but not spelled out — no explicit validate-then-iterate checkpoint in the body itself.

4 / 5

Progressive Disclosure

The ~34-line body is a well-organized overview (Quick Reference, Check, Fix, Explain, Code Review) that appropriately pushes full code examples and framework-specific guidance to a single, clearly signaled, one-level-deep reference — "see `references/rule.md`" — which exists and contains no nested references. This matches anchor 5: clear overview, well-signaled shallow reference, easy navigation.

5 / 5

Total

16

/

20

Passed

Description

75%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 solid description with an explicit "Use when..." trigger clause, a named domain, and several concrete check dimensions. Its main weaknesses are the self-referential trigger phrasing that quotes the rule title instead of natural user phrases, and the absence of the fix-side actions and common synonyms (srcset, responsive images) that would round out coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "reviewing image assets, markup, and CDN or build transforms" plus "Check encoded size, rendered size, loading strategy, and above-the-fold impact together" — with a clearly named domain. It falls short of anchor 5 because coverage is review-only: no fix-side actions (e.g., generating size variants, adding srcset/sizes) are mentioned, leaving minor gaps.

4 / 5

Completeness

Both parts are present: the "what" ("Check encoded size, rendered size, loading strategy, and above-the-fold impact together") and an explicit "Use when reviewing image assets, markup, and CDN or build transforms..." trigger clause. The "when" could be more explicit and less self-referential — it leans on the rule title "related to Serve images at the correct display size" rather than concrete user-facing trigger phrases — which matches anchor 4 rather than anchor 5.

4 / 5

Trigger Term Quality

Good keyword coverage including natural phrases users would say: "image assets", "markup", "CDN", "build transforms", "encoded size", "rendered size", "above-the-fold". A few natural terms are missing — notably "responsive images", "oversized images", and "srcset" — so it does not reach anchor 5's comprehensive synonym coverage; it is clearly above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The image-sizing niche (display size, encoded vs rendered size) is mostly distinct with a clear focus, but the check dimensions "loading strategy" and "above-the-fold impact" overlap with closely related image-delivery skills (e.g., lazy loading), matching anchor 4's minor overlap risk rather than anchor 5's minimal conflict risk.

4 / 5

Total

16

/

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-size/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.