CtrlK
BlogDocsLog inGet started
Tessl Logo

image-first-grid-layout

Create an image-led grid design system with full-bleed photography, structural guide lines, anchored content blocks, and restrained technical overlays.

48

Quality

51%

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 ./agent-skills/web-design/image-first-grid-layout/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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.

This is a well-scoped, readable design-direction skill with specific pattern vocabulary and a useful Avoid section, but it is weakened by an empty Workflow section, a duplicated Use When section, and substantial overlap between Implementation guidance, Recommended patterns, and Tuning knobs. The absence of any sequencing or verification step makes it advisory rather than operational.

Suggestions

Fill the empty '## Workflow' section with an ordered sequence (e.g. select image and washes, establish grid rails, anchor primary copy column, place secondary blocks, layer technical atmosphere, verify image dominance) so the direction can be executed in order.

Remove the '## Use When' section that duplicates the frontmatter description verbatim, and consolidate the repeated gradient/rail/overlay guidance spread across Implementation guidance, Recommended patterns, and Tuning knobs into one section.

Add at least one concrete, executable reference — a minimal CSS grid/overlay markup snippet or a worked example layout — so the qualitative directives ('just visible enough', 'confident sans-serif') have a concrete anchor.

DimensionReasoningScore

Conciseness

The body is mostly lean design direction with no explanation of concepts Claude already knows, but it carries clear redundancy: '## Use When' restates the frontmatter description verbatim, '## Workflow' is an empty heading, and '## Implementation guidance', '## Recommended patterns', and '## Tuning knobs' each restate the same ideas (dark gradients, guide rails/markers, translucent buttons, overlay darkness) two to three times. This matches anchor 3 (mostly efficient but could be tightened) rather than 4, where only minor instances of over-explanation would remain.

3 / 5

Actionability

The guidance includes genuinely concrete specifics — 'layered left-to-right and bottom-up dark gradients', 'tiny square markers', 'split-column scaffold', 'additive blend mode', 'translucent dark fills, thin borders' — but it stops short of executable instruction: no example markup or CSS grid recipe, no concrete measurements or breakpoints, and many directives are qualitative ('should feel', 'just visible enough'). This fits anchor 3 (some concrete guidance but incomplete, missing key details) rather than 2, because the pattern descriptions are specific enough to act on directly, and rather than 4, because there are no copy-paste-ready examples covering common cases.

3 / 5

Workflow Clarity

The '## Workflow' section is literally empty, so the skill's intended sequencing is never delivered; what remains is parallel advisory sections (Scope, Visual target, Implementation guidance, Patterns, Tuning, Avoid) with no explicit order of application and no checkpoints for verifying the composition reads correctly. This matches anchor 2 (rough sequence present — scope, then visual target, then implementation — but poorly defined steps, validation absent). It does not reach 3, which requires listed steps with an actual sequence; the only step-like section is empty.

2 / 5

Progressive Disclosure

The body is roughly 50 lines with well-labeled sections and no external bundle files, so single-file structure is appropriate and nothing needs to be split out; navigation is easy. It falls short of 5 because of structural defects — an empty '## Workflow' heading and a '## Use When' section that duplicates the description add noise rather than organize content, leaving minor organization gaps per anchor 4.

4 / 5

Total

12

/

20

Passed

Description

55%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 does a solid job on the 'what', enumerating concrete, domain-appropriate components in third person without fluff. Its main weakness is the complete absence of any 'use when' trigger guidance and of common natural synonyms (hero image, landing page, background image), which limits both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a landing page or hero section built around a large background/hero image, cinematic full-bleed layout, or image-first grid composition.'

Include natural synonyms users would actually say — 'hero image', 'landing page', 'background image', 'cinematic layout' — alongside the current technical vocabulary.

Sharpen distinctiveness by contrasting with adjacent cases, e.g. 'not a gallery or card-grid layout', so it does not fire for generic design-system or branding requests.

DimensionReasoningScore

Specificity

The description lists several concrete deliverables — "full-bleed photography, structural guide lines, anchored content blocks, and restrained technical overlays" — comparable to the anchor-4 example of several specific actions with minor gaps. It falls short of 5 because it is a single composite 'Create' action rather than comprehensive coverage of multiple distinct actions, and above 3 because it goes well beyond naming the domain with 1-2 actions.

4 / 5

Completeness

It has a clear 'what' (create an image-led grid design system with enumerated components) but no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description. The judging guidelines explicitly cap completeness at 3 for a missing 'when' clause, which matches anchor 3 exactly. It cannot be 4 because 'when' is not merely implicit — it is entirely absent.

3 / 5

Trigger Term Quality

Terms like "image-led grid design system", "full-bleed photography", and "grid" are relevant domain keywords a design-oriented user might say, but common natural variations are missing — "hero image", "landing page", "background image", "cinematic layout". This matches anchor 3 (some relevant keywords but missing common variations or synonyms), not 4, since the missing terms are among the most likely user phrasings rather than a few edge synonyms.

3 / 5

Distinctiveness Conflict Risk

"image-led grid" with "full-bleed photography" carves out a reasonably distinct niche, but "design system" is a broad phrase that overlaps with general branding, design-guideline, and layout skills, and with no 'use when' phrasing the trigger boundary is undefined. This fits anchor 3 (somewhat specific but could still overlap with similar skills) better than 4, which requires mostly distinct triggers with only minor overlap risk.

3 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MengTo/Skills
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.