CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

image-optimization

Use when reviewing image assets, markup, and CDN or build transforms related to Optimize all images for web. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Quality

75%

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/image-optimization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-structured overview with genuinely actionable, threshold-specific guidance and an exemplary progressive-disclosure split to references/rule.md. Its weaknesses are redundancy across the Quick Reference, Check, and Fix sections (plus a motivational intro Claude does not need), and a batch-fix workflow with no validation step surfaced in the body, even though the reference file contains a Verification section that could be pointed to.

Suggestions

Remove the motivational intro and deduplicate guidance repeated across Quick Reference, Check, and Fix (e.g. the 80% quality and srcset advice) so each fact appears once.

Add a verification step at the end of the Fix workflow — e.g. 'Verify: re-check file sizes and rendered dimensions as described in the Verification section of references/rule.md' — since the fix is a batch operation.

Inline one short corrected <picture>/srcset markup example (or an explicit pointer to the Code Example section of references/rule.md) so the Fix steps have a concrete output shape.

DimensionReasoningScore

Conciseness

The intro sentence ('Images typically account for 50%+ of page weight. Unoptimized images cause slow load times... frustrated users') motivates what Claude already knows, and format/quality/srcset/lazy-loading guidance is repeated across Quick Reference, Check, and Fix (e.g. '80% quality' appears twice, srcset guidance three times). This matches anchor 3 (mostly efficient but could be tightened) rather than 4, where over-explanation would be only minor.

3 / 5

Actionability

Guidance is concrete and specific: 'srcset with 400w, 800w, 1200w, 1600w variants', 'File sizes are reasonable (< 200KB for photos, < 50KB for graphics)', '80% quality for photos, 60% for AVIF', 'images > 100px wide'. It stays at anchor 4 rather than 5 because the body contains no executable commands or corrected markup examples — those live only in references/rule.md.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sequence is clearly organized with numbered steps, but the Fix step is a batch operation (converting and re-compressing images across the codebase) with no validation or verification step in the body — the Verification section in references/rule.md is not surfaced. Per the batch-operation cap, this holds workflow clarity at anchor 3 rather than 4.

3 / 5

Progressive Disclosure

The body is a concise ~30-line overview while 316 lines of implementation detail (code examples, framework examples, build tool integration, verification) are appropriately split into a real, one-level-deep references/rule.md, clearly signaled ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md') with well-organized sections. This matches anchor 5.

5 / 5

Total

15

/

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 and concrete review dimensions (encoded size, rendered size, loading strategy, above-the-fold impact). Its main weakness is that the capability statement covers only checking/reviewing, understating the skill's fixing and optimization scope. Keywords are domain-appropriate but miss common user phrasings like 'image optimization' or 'WebP'.

Suggestions

State the fix/optimization capability alongside the review capability, e.g. 'Review and fix image assets: check format, srcset, lazy loading, and file size, then convert and compress to WebP/AVIF'.

Add common user phrasings such as 'image optimization', 'WebP', 'srcset', or 'lazy loading' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'reviewing image assets, markup, and CDN or build transforms' and 'Check encoded size, rendered size, loading strategy, and above-the-fold impact' — but the action verbs are limited to reviewing/checking, omitting fixing or optimizing capabilities. This matches anchor 4 (several specific actions, minor gaps in coverage) rather than 5, which requires comprehensive multi-verb coverage.

4 / 5

Completeness

Both parts are explicit: an explicit trigger clause ('Use when reviewing image assets, markup, and CDN or build transforms...') and a concrete what ('Check encoded size, rendered size, loading strategy, and above-the-fold impact together'). It falls short of anchor 5 because the stated what covers only checking/reviewing and does not state the skill's fixing/optimizing capability.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'image assets', 'markup', 'CDN', 'build transforms', 'loading strategy', 'above-the-fold'. Common user phrasings like 'optimize images', 'image optimization', 'srcset', 'WebP', or 'page speed' are absent, keeping it at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

A clear image-optimization niche with distinct, image-specific triggers (encoded size, rendered size, above-the-fold) minimizes conflict risk. Minor overlap remains with closely related web-performance or Core Web Vitals review skills, matching anchor 4 rather than 5.

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/image-optimization/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.