CtrlK
BlogDocsLog inGet started
Tessl Logo

agency-grid-layout-minimal

Create a minimal agency design system with a disciplined editorial grid, oversized typography, quiet uppercase utility labels, restrained image blocks, and subtle structural detail.

49

Quality

53%

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/agency-grid-layout-minimal/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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-sectioned, readable style-direction document that appropriately avoids code for a design skill, but it is directionally written rather than actionable: no measurable specs, an empty Workflow section, and verbatim duplication of the description inside the body. Tightening the redundancy and adding concrete values would move it up a full level.

Suggestions

Remove the empty '## Workflow' header (line 11) — either delete it or populate it with an actual ordered process (e.g., choose grid → set type scale → layout hero → frame imagery → style CTAs).

Add a few concrete values to make guidance executable: a display/body type-size ratio, a column count for the grid, a max-width for the page shell, and 1-2 neutral palette tokens.

Drop the 'Use When' bullet that duplicates the frontmatter description verbatim and replace it with genuinely new trigger context, cutting redundant 'quiet/subtle/restrained' phrasing repeated across sections.

DimensionReasoningScore

Conciseness

The bullets are directive rather than explanatory and avoid teaching concepts Claude already knows, but the body can be tightened: the 'Use When' bullet repeats the frontmatter description verbatim, and descriptors recur across sections ('quiet', 'subtle', 'restrained', 'minimal' appear in nearly every section). This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' better than the lean level-4 anchor.

3 / 5

Actionability

Some directives are pleasantly concrete ('1px gradient shells', 'thin gradient-border wrappers', 'tiny uppercase metadata', 'wide max-width page shells'), but the guidance stops short of executable specifics — no type scale numbers, grid column counts, spacing values, or palette tokens a builder could apply without interpretation. For an instruction-only skill this lands at 'some concrete guidance but incomplete' rather than 'mostly executable guidance with minor gaps'.

3 / 5

Workflow Clarity

The '## Workflow' section (line 11) is empty — a header with no content — and the remaining sections are thematic groupings rather than a sequenced process, so there is no explicit order of operations. Content exists and is readable, matching 'steps listed but sequence/checkpoints missing or implicit'; the level-4 anchor requires a clear sequence, which is absent.

3 / 5

Progressive Disclosure

This is a single-file skill under 50 lines with no bundle files (no references/, scripts/, or assets/ exist), so per the rubric guideline well-organized sections alone can support a high score. Sections are clearly labeled and scannable (Scope, Visual target, Implementation guidance, Recommended patterns, Tuning knobs, Avoid); the only structural blemishes are the empty '## Workflow' header and the redundant 'Use When' section, which keep it at 'minor organization gaps' rather than fully clean.

4 / 5

Total

13

/

20

Passed

Description

53%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 evocative about the visual direction it delivers, and it is reasonably distinct within the design-skill space. Its main weakness is the complete absence of 'when to use' trigger guidance, which both caps completeness and limits natural trigger-term coverage.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building an agency, studio, or brand-strategy website with an editorial, grid-driven layout' — this lifts completeness past the level-3 cap.

Include natural user phrasings users would actually say ('agency website', 'landing page', 'portfolio', 'editorial layout') to broaden trigger-term coverage beyond design jargon.

Consider framing the deliverable as concrete actions ('Build page layouts, style typography scales, frame image blocks') so the description reads as capabilities rather than a static style list.

DimensionReasoningScore

Specificity

The description names its domain ('minimal agency design system') and enumerates concrete design elements ('disciplined editorial grid, oversized typography, quiet uppercase utility labels, restrained image blocks'), but offers only a single action verb ('Create') rather than several distinct actions. It sits at 'names domain and 1-2 concrete actions' rather than the level-4 'lists several specific actions' anchor.

3 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause or any equivalent explicit trigger guidance in the description. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3, matching the anchor 'Has a clear what but when is missing or only weakly implied'.

3 / 5

Trigger Term Quality

Relevant keywords like 'minimal agency design system', 'editorial grid', and 'typography' are present, but common natural trigger phrases users would actually say — 'agency website', 'agency landing page', 'portfolio site', 'editorial layout' — are missing. This matches 'some relevant keywords but missing common variations or synonyms', not the fuller coverage of level 4.

3 / 5

Distinctiveness Conflict Risk

'Minimal agency design system with a disciplined editorial grid' carves out a fairly specific niche that is unlikely to fire for unrelated skills, with only minor overlap risk against the broader family of design-system and layout skills. It fits 'mostly distinct; minor overlap risk with closely related skills' better than the fully-distinct level 5 because 'design system' and 'typography' are shared vocabulary with many sibling design skills.

4 / 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.