CtrlK
BlogDocsLog inGet started
Tessl Logo

imagegen-frontend-web

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

56

Quality

63%

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 ./.agents/skills/imagegen-frontend-web/SKILL.md

The canonical home for this skill is imagegen-frontend-web in Leonxlnx/taste-skill

SKILL.md
Quality
Evals
Security

Quality

Content

56%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 highly actionable with a clear sequenced workflow and validation checklist, but it suffers from heavy cross-section repetition that hurts conciseness and is a monolithic wall of text with no external references, limiting progressive disclosure.

Suggestions

Consolidate the one-image-per-section rule and the left-text/right-image hero bias into a single authoritative section and cross-reference it instead of restating each 4-5 times.

Split the large catalogs (§11 component set, §15 default section packs, §20 example interpretations) into separate reference files linked one level deep from SKILL.md.

Fix the §19 step numbering (duplicate '5.', missing '6.') so the workflow sequence is unambiguous.

DimensionReasoningScore

Conciseness

The ~980-line body noticeably repeats the same core rules across many sections — the one-image-per-section rule appears in the HARD OUTPUT RULE, §5, §16, §17, and §19, and the left-text/right-image hero bias is restated in the HERO COMPOSITION BIAS header, §2, §4, §17, and §19 — making it padded rather than lean.

2 / 5

Actionability

Concrete, specific guidance throughout — exact composition anchors, background modes, CTA styles, hero scales, palette rules, default 4/8/12-section packs, and three fully worked example interpretations — with only minor gaps where directives stay subjective ('feel premium', 'feel intentional').

4 / 5

Workflow Clarity

§19 RESPONSE BEHAVIOR gives a clear sequenced workflow and §17 CLARITY CHECK provides a 21-item validation checklist with a feedback loop ('If the count is wrong, regenerate the missing sections'), but the step list has a numbering error (two '5.' steps, skipping 6) leaving minor sequence gaps.

4 / 5

Progressive Disclosure

No bundle files exist and the body is a single monolithic ~980-line document; section headers give it structure, but self-contained catalogs (the §11 component set, §15 default packs, §20 examples) are inlined rather than split into one-level-deep references, so organization is only partial.

3 / 5

Total

13

/

20

Passed

Description

71%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.

The description is specific and capability-rich with good natural trigger terms and a distinct niche, but it lacks an explicit 'Use when...' trigger clause, leaving the 'when' only weakly implied and capping completeness.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks for website design references, landing page mockups, or frontend comps for developers or coding models to recreate.'

Broaden trigger-term coverage with synonyms users naturally say ('web design', 'homepage', 'mockup', 'wireframe', 'UI comp').

Move the CRITICAL OUTPUT RULE out of the description and into the body; it bloats the description and competes with the capability/trigger summary.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'generate ONE separate horizontal image FOR EVERY section', 'Enforces composition variety', 'varied CTAs', 'varied hero scales (giant / mid / mini minimalist)', 'narrative concept spine, second-read moments', and 'single consistent palette' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the closing 'Optimized for landing pages, marketing sites, and product comps...' only weakly implies the 'when', so completeness is capped at 3 per the missing-trigger-clause guideline.

3 / 5

Trigger Term Quality

Includes natural terms users actually say — 'landing page', 'marketing sites', 'product comps', 'hero', 'sections', 'CTAs' — but misses common synonyms a user might voice like 'web design', 'homepage', 'mockup', or 'wireframe'.

4 / 5

Distinctiveness Conflict Risk

The niche is fairly specific — per-section horizontal frontend design reference images with art-direction discipline — distinguishing it from generic image-generation skills, with only minor overlap risk against broader web-design skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (988 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
mediago-dev/mediago
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.