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

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/image-compression/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, correctly delegated overview whose progressive disclosure is exemplary. Its weaknesses are in the body itself: repeated size-reduction claims, no inline executable guidance, and no explicit validation checkpoint for the compression workflow.

Suggestions

Deduplicate the "60-80% without visible quality loss" claim so it appears once; remove the restated "5-10x larger" intro or merge it into Quick Reference.

Add one concrete, executable command or snippet to the Fix section (e.g., an ImageMagick `convert -quality 80` line) so the body is actionable without forcing a jump to the reference.

Insert an explicit verification checkpoint between Fix and Code Review (e.g., confirm the compressed output in DevTools Network tab / Lighthouse) so the batch workflow has a feedback step inline.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview that delegates detail to the reference, but the "60-80% reduction / minimal quality loss" claim is restated three times (intro, Quick Reference bullet, Explain) and the "5-10x larger" intro restates what the bullets convey, so it could be tightened further.	2 / 3
Actionability	Concrete quality ranges (70-85%, 60-80%) and named tools (ImageOptim, TinyPNG) are present, but the body has no executable code or commands—those live in the reference—and "Analyze if images are properly compressed" is abstract, so guidance is incomplete.	2 / 3
Workflow Clarity	A Check→Fix→Code Review sequence is implied, but there are no explicit validation checkpoints in the body and verification is delegated to the reference; for a batch compression operation, missing inline validation feedback caps this at 2.	2 / 3
Progressive Disclosure	The body is a concise overview with a single, clearly signaled, one-level-deep reference—"see references/rule.md"—and that file (verified present) holds the detailed code/configs, so content is appropriately split and easy to navigate.	3 / 3
	Total	9 / 12 Passed

Description

85%

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 with an explicit trigger clause and concrete, well-scoped actions tied to a named rule. The main weakness is trigger-term coverage leaning technical rather than capturing the casual phrasings users actually say.

Suggestions

Add natural casual trigger terms such as "optimize images", "reduce image size", or "images are too large" alongside the technical phrasing.

Trim the jargon-heavy "above-the-fold impact" / "rendered size" language or pair each with a plainer synonym so the description reads as something a user would naturally say.

Clarify scope so the loading-strategy/above-the-fold framing does not blur the boundary with sibling image skills (e.g., lazy loading, responsive images).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"reviewing image assets, markup, and CDN or build transforms" and "Check encoded size, rendered size, loading strategy, and above-the-fold impact"—matching the multiple-specific-actions anchor; voice is third-person/imperative with no first/second-person penalty.	3 / 3
Completeness	It has an explicit "Use when..." trigger clause and a clear statement of what the skill does (review assets/markup/CDN transforms and check the four image dimensions), answering both what and when.	3 / 3
Trigger Term Quality	"image assets", "markup", and "Compress images without quality loss" are natural terms, but "CDN or build transforms", "above-the-fold impact", and "rendered size" skew technical and common casual variations ("optimize images", "reduce image size", "images too big") are missing, so it is not comprehensive enough for a 3.	2 / 3
Distinctiveness Conflict Risk	The named rule "Compress images without quality loss" scoped to image assets, markup, and delivery transforms is a clear niche with distinct triggers, unlikely to fire for unrelated skills; the loading-strategy mention broadens it only mildly.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/image-compression/SKILL.md
Commit: 48405aa

Reviewed: about 12 hours ago

Table of Contents

Discovery Implementation Validation

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.