CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

modern-format

Use when reviewing image assets, markup, and CDN or build transforms related to Use modern image formats (WebP, AVIF). 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/modern-format/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 has strong bones — concrete Check and Fix guidance and an exemplary progressive-disclosure split to references/rule.md — but it is dragged down by triple-repeated statistics, a redundant Explain section of concepts Claude already knows, and no validation checkpoint in a batch fix workflow.

Suggestions

Merge the Quick Reference and Explain sections into one: the same web.dev statistics (25-35% smaller, 40-50% smaller, 97% support) currently appear three times in the intro, Quick Reference, and Explain.

Add an inline validation step to the Fix workflow (e.g., verify converted file size and visual quality, and confirm the JPEG fallback still loads in Safari) since the Fix is a batch operation across all images — the verification content in references/rule.md should be surfaced as a step in the body.

Drop the Explain section's generic compression background and time-sensitive version details ('Chrome 85+', 'Firefox 93+', 'as of 2024') or move them to references/rule.md — Claude already knows WebP/AVIF basics, and dated version numbers go stale.

DimensionReasoningScore

Conciseness

Noticeably verbose with several padded sections: the same web.dev size statistics (25-35%, 40-50%, 97% support) appear three times across the intro, Quick Reference, and Explain; the Explain section instructs Claude to explain WebP/AVIF compression basics it already knows and carries time-sensitive version numbers ('Chrome 85+', 'as of 2024') outside any deprecated section; and the Code Review section restates the description. The core Check/Fix sections are tight, keeping this above anchor 1.

2 / 5

Actionability

Check and Fix give concrete, executable guidance: 'Convert to WebP at 80% quality using Squoosh or Sharp', specific <picture>/<source> markup structure, an @supports CSS pattern, and findings reported with 'file path and line number'. Minor gap: no copy-paste code block in the body itself (those live in references/rule.md).

4 / 5

Workflow Clarity

A clear Check → Fix sequence with numbered, specific steps, but the Fix is a batch operation (converting every image and rewriting markup across the codebase) with no inline validation checkpoint — only the vague 'describe how to confirm the fix in DevTools'. Per the batch-operation rule, workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

A ~45-line overview body with a well-signaled, one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md') that exists and contains exactly the promised code examples, conversion script, framework guidance, and verification steps. Content is appropriately split between overview and reference.

5 / 5

Total

14

/

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 that explicitly covers both what to do and when to trigger, with concrete review dimensions and natural keywords. The awkward duplicated rule-name phrasing ('related to Use modern image formats') and omission of the fix/convert capability keep specificity and trigger coverage just below top marks.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Check encoded size, rendered size, loading strategy, and above-the-fold impact together', 'reviewing image assets, markup, and CDN or build transforms'), but coverage is check-only — the Fix/convert workflow documented in the body is not reflected, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what ('Check encoded size, rendered size, loading strategy, and above-the-fold impact together') and when ('Use when reviewing image assets, markup, and CDN or build transforms related to Use modern image formats (WebP, AVIF)') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say ('WebP', 'AVIF', 'image assets', 'markup', 'CDN', 'build transforms'), but a few natural variations are missing such as 'optimize images', 'compress images', or 'JPEG/PNG'.

4 / 5

Distinctiveness Conflict Risk

WebP/AVIF format review is a clear niche with distinctive format names, but 'loading strategy' and 'encoded size' language creates minor overlap risk with closely related image-performance skills such as lazy loading or responsive sizing.

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/modern-format/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.