CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

72%

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.

The body is a well-structured overview with exemplary progressive disclosure — a single verified, clearly signaled reference file holding the implementation detail. It is weakened by near-contentless Check/Explain sections that restate the title, a Fix section with no executable command, and no validation step in the body for what is a batch operation.

Suggestions

Make the Fix section executable: replace 'Compress images using tools like ImageOptim, TinyPNG, or automated build processes' with a copy-paste-ready command (e.g., a one-line ImageMagick or sharp-cli invocation) or explicitly point to the commands in references/rule.md.

Tighten redundancy: merge the Check and Explain one-liners, which restate the title and Quick Reference, or replace them with what to do when the check fails.

Add a body-level verification step (e.g., 'Confirm via DevTools Network tab or Lighthouse efficiently-encode-images audit') so the batch compression workflow has an explicit validation checkpoint instead of it living only in references/rule.md.

DimensionReasoningScore

Conciseness

Mostly lean, but the intro 'Uncompressed images are often 5-10x larger than needed' is background Claude already knows, and the Check ('Analyze if images are properly compressed') and Explain ('Explain how proper compression can reduce image sizes by 60-80%') sections mostly restate the title and Quick Reference, so the body could be tightened.

3 / 5

Actionability

The Quick Reference gives concrete numbers ('Compress JPEG to 70-85% quality', 'lossy for photos, lossless for graphics'), but the Fix section only names tools ('ImageOptim, TinyPNG') with no commands, and all executable code is deferred to references/rule.md, leaving the body itself without executable guidance.

3 / 5

Workflow Clarity

A rough Check → Fix → Explain → Code Review sequence is present, but each step is a one-line directive with no validation checkpoints; since image compression is a batch-style operation and the body omits any verification step (it lives only in the reference file), workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

The ~35-line body is a clear overview that appropriately splits implementation detail into the single, well-signaled, one-level-deep references/rule.md ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'), which exists and contains the deferred code examples.

5 / 5

Total

14

/

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 several concrete review dimensions, written in third person. Its main weaknesses are the indirectly stated core capability (the rule title is embedded in a sentence rather than a clear action verb like 'compress' or 'flag') and missing natural synonyms such as 'optimize images' or format names.

DimensionReasoningScore

Specificity

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' — though the core compress action is only implied via the embedded rule title.

4 / 5

Completeness

Explicitly answers 'when' with 'Use when reviewing image assets, markup, and CDN or build transforms' and conveys a what (review/check compression-related delivery), but the what is stated indirectly through the awkward phrase 'related to Compress images without quality loss' rather than a clear capability statement.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('image assets', 'quality loss', 'CDN', 'build', 'above-the-fold') but missing common variations users would say, such as 'optimize images', 'image size', or format names like JPEG/PNG/WebP.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (image compression in frontend performance review) with distinct triggers, but broadening to 'loading strategy, and above-the-fold impact' creates minor overlap risk with sibling image-delivery skills (formats, lazy loading, responsive images).

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-compression/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.