CtrlK
BlogDocsLog inGet started
Tessl Logo

image-compression

Use when reviewing image assets, markup, and CDN or build transforms related to Compress images without quality loss. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

60

Quality

70%

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-compression/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.

A well-structured overview with excellent progressive disclosure into a real, content-rich reference file, but the body itself is padded with tautological Check/Explain sections and lacks any executable guidance or explicit verification checkpoints of its own.

Suggestions

Cut redundancy: remove the duplicated 60-80% statistic and replace the tautological Check ("Analyze if images are properly compressed...") and Explain sections with distinct, useful content or fold them into Quick Reference.

Add one copy-paste-ready command to the Fix section (e.g. a one-liner like `convert input.jpg -quality 80 output.jpg` or `npx sharp-cli input.jpg -o output.webp --quality 80`) so the body handles the common case without opening the reference.

Make the workflow explicit and verifiable: order the Check → Fix → Verify phases and spell out the DevTools confirmation steps (Lighthouse "Efficiently encode images" audit, Network tab file sizes) instead of just alluding to DevTools.

DimensionReasoningScore

Conciseness

The body is short and free of concept-explaining filler, but contains redundant padding: the 60-80% reduction stat appears twice ("Can reduce file sizes by 60-80% without visible quality loss" and "Explain how proper compression can reduce image sizes by 60-80%"), and the Check section ("Analyze if images are properly compressed without significant quality loss") merely restates the title.

3 / 5

Actionability

The Quick Reference gives concrete parameters ("Compress JPEG to 70-85% quality", "lossy compression for photos, lossless for graphics") and names tools, but the Fix section ("Compress images using tools like ImageOptim, TinyPNG, or automated build processes") offers only high-level hints with no executable command in the body — all runnable code is deferred to references/rule.md. This lands between minimal guidance and mostly-executable guidance.

3 / 5

Workflow Clarity

Check → Fix → Explain → Code Review provides a recognizable phase sequence, but the phases are parallel headings rather than an ordered workflow, and validation is only implicit: "describe how to confirm the fix in DevTools" names no concrete checkpoint steps (the actual verification steps live only in the reference file).

3 / 5

Progressive Disclosure

The body is a lean, well-sectioned overview (~45 lines) with a clearly signaled, one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — and that file exists and delivers exactly what is promised (ImageMagick/sharp commands, Webpack/Vite configs, verification steps).

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 answers both what it does and when to use it with concrete, domain-specific trigger phrases, held back only by minor gaps: no synonyms like "optimize images" and no mention of the fix/compress actions the skill supports.

DimensionReasoningScore

Specificity

Several concrete actions are listed — "Check encoded size, rendered size, loading strategy, and above-the-fold impact together" plus "reviewing image assets, markup, and CDN or build transforms" — but coverage has minor gaps: the description names only review/check actions and omits the compress/fix capabilities the skill actually covers.

4 / 5

Completeness

Both parts are explicit and concrete: the when is "Use when reviewing image assets, markup, and CDN or build transforms related to Compress images without quality loss", and the what is "Check encoded size, rendered size, loading strategy, and above-the-fold impact together" — matching the anchor that answers both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "Compress images without quality loss", "image assets", "CDN or build transforms", "above-the-fold" — but a few common terms users would say are missing, e.g. "optimize images", "page weight", or format names (JPEG/PNG/WebP).

4 / 5

Distinctiveness Conflict Risk

The compression-review niche is mostly distinct, but terms like "loading strategy", "rendered size", and "above-the-fold" overlap with closely related image-performance skills (lazy loading, responsive images), creating minor conflict risk rather than a fully clear niche.

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
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.