CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

optimized

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

Quality

78%

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/optimized/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 body with excellent progressive disclosure to a real references/rule.md file. The main cost is redundancy: the Explain section teaches concepts Claude already knows and Quick Reference duplicates the Fix section's settings, and the workflow lacks a post-fix re-validation step.

Suggestions

Cut or drastically trim the Explain section — Claude already knows how DCT quantisation, DEFLATE, EXIF metadata, and progressive JPEG encoding work; keep only project-specific thresholds and tool choices.

Merge Quick Reference into the Fix section (or vice versa) — both list the same mozjpeg quality-80/progressive, pngquant 65-80, SVGO, and EXIF-strip settings, doubling the token cost.

Add a post-fix validation step (re-run the Lighthouse 'Efficiently encode images' audit and spot-check visual quality) to close the feedback loop for batch re-encoding.

DimensionReasoningScore

Conciseness

The Check, Fix, and Code Review sections are tight and actionable, but the Explain section spends a paragraph on concepts Claude already knows ("JPEG compression works by converting pixel data to frequency components (DCT)", "PNG uses lossless DEFLATE compression", "EXIF metadata (GPS, camera model, timestamps)", progressive JPEG behavior), and Quick Reference largely duplicates the Fix section's tool settings. Mostly efficient with some unnecessary explanation — matches anchor 3; not a 2 because the majority of the body is lean.

3 / 5

Actionability

Concrete tool-plus-parameter guidance throughout ("re-encode with mozjpeg at quality 80 with progressive=true", "run pngquant at quality 65-80... or oxipng for lossless", "AVIF: encode at quality 60 with effort 6") with an explicit reporting requirement. Falls short of 5 because the body contains no copy-paste-ready commands or code snippets — exact CLI invocations and the sharp example live only in references/rule.md.

4 / 5

Workflow Clarity

A clear Check→Fix sequence with numbered sub-steps, and "For each image, show the before/after file size and percentage reduction" acts as a post-fix checkpoint. Minor validation gap keeps it below 5: after batch re-encoding (a destructive operation) the skill never re-runs the Lighthouse audit or checks visual quality, and there is no retry/rollback loop.

4 / 5

Progressive Disclosure

The body is a well-sectioned overview (Quick Reference, Check, Fix, Explain, Code Review) that keeps details out of the main file and closes with a single, clearly signaled one-level-deep pointer: "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — a real file containing the sharp code example and per-format guidance. This matches the anchor-5 clear-overview pattern exactly.

5 / 5

Total

16

/

20

Passed

Description

76%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 both what to do and when to use it, with concrete check dimensions. Its main weaknesses are missing natural trigger synonyms (optimize/compress, page weight, LCP) and reliance on an embedded rule title instead of naming the skill's fixing capabilities.

Suggestions

Add natural trigger synonyms users would actually say — e.g., 'optimize images', 'compress images', 'image file size', 'page weight', 'LCP' — instead of relying on the embedded rule title 'Optimise images for faster loading'.

Name the skill's concrete fixing capabilities (re-encode JPEG/PNG/WebP/AVIF, strip EXIF, run SVGO) so the 'what' covers actions beyond auditing and checking.

DimensionReasoningScore

Specificity

"Check encoded size, rendered size, loading strategy, and above-the-fold impact together" lists several concrete actions, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the capability framing leans on the embedded rule title "related to Optimise images for faster loading" rather than enumerating the skill's actual fixing/compression actions.

4 / 5

Completeness

It explicitly answers 'when' with "Use when reviewing image assets, markup, and CDN or build transforms related to Optimise images for faster loading" and 'what' with "Check encoded size, rendered size, loading strategy, and above-the-fold impact together", both concrete. This matches the anchor-5 example's explicit dual answer with concrete trigger contexts, and is clearly above the anchor-4 example whose 'when' is bare.

5 / 5

Trigger Term Quality

Terms like "image assets", "markup", "CDN or build transforms", and "above-the-fold" are relevant to the domain, but common natural phrasings a user would say — "optimize/compress images", "image file size", "page weight", "LCP" — are missing. Not a 4 because the most likely user trigger words appear only inside the awkwardly embedded rule title, not as natural trigger phrases.

3 / 5

Distinctiveness Conflict Risk

The image-optimisation review niche with triggers like "encoded size", "rendered size", and "above-the-fold impact" is mostly distinct with minor overlap risk against closely related frontend-performance skills (responsive images, lazy loading, format selection). Not a 5 because those sibling rule-skills in the same category would plausibly fire on similar image-review requests.

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/optimized/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.