CtrlK
BlogDocsLog inGet started
Tessl Logo

dark-blue-contrasting-clean

Create a dark-blue clean design system with strong contrast, cobalt gradient feature blocks, crisp framed structure, and restrained premium glow.

51

Quality

55%

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/dark-blue-contrasting-clean/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.

A compact, well-organized design-direction body whose guidance is concrete at the structural level but lacks executable specifics (color values, typography stacks, spacing tokens), and whose 'Workflow' section is an empty header. The verbatim repetition of the description in 'Use When' wastes tokens without adding information.

Suggestions

Fill or remove the empty '## Workflow' section — give a sequenced build order (page shell and framing rails, then cobalt feature block, then index/footer zones) so a single pass is unambiguous.

Add concrete design tokens: example hex values for the navy base, cobalt feature block, and pale-blue support text, plus named font weights/sizes, so guidance is executable rather than descriptive.

Delete the verbatim copy of the frontmatter description in 'Use When' and merge its content with 'Scope', which already covers the same trigger and positioning information.

DimensionReasoningScore

Conciseness

The body is mostly lean bullet-style guidance with no over-explanation of known concepts, but the 'Use When' section repeats the frontmatter description verbatim, 'Scope' overlaps it, and '## Workflow' is a completely empty header. That waste is more than anchor 4's 'minor instances that could be trimmed' but well short of anchor 2's pervasive padding.

3 / 5

Actionability

Concrete structural guidance is present ('border-gradient wrappers', 'border-x container lines', 'small corner squares', 'high-impact contrast block, then quieter index areas'), but nothing is executable to spec — no hex or RGB color values, font stacks, spacing scale, or code snippets. Anchor 3 ('some concrete guidance but incomplete, missing key details') fits; it exceeds anchor 2's high-level-hints level because specific patterns and treatments are named.

3 / 5

Workflow Clarity

This is a single-purpose aesthetic skill (no destructive/batch operations, so no hard cap), but the '## Workflow' section is literally empty and the guidance is thematic rather than sequenced — there is no build order and no checkpoints such as verifying contrast or readability. The simple-skill score of 5 requires an unambiguous single action with clear organization; the dead header and unordered guidance place it at anchor 3.

3 / 5

Progressive Disclosure

The body is under 50 lines, needs no external references, references none (no references/scripts/assets bundle exists), and is organized into cleanly headed sections (Use When, Scope, Visual target, Implementation guidance, Recommended patterns, Tuning knobs, Avoid). This matches the rubric's exception for short simple skills: well-organized sections alone earn a 5.

5 / 5

Total

14

/

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 communicates a specific aesthetic direction but is written as an output spec rather than a capability-plus-trigger description. It lacks any 'Use when...' guidance and omits the natural trigger phrasings users would say, leaving completeness and trigger-term quality at mid-scale.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks for a dark mode, navy, or premium dark-blue design system, landing page, or UI theme.'

Include natural trigger synonyms users would actually say — 'dark mode', 'navy theme', 'blue-led landing page', 'premium dark UI' — alongside the existing stylistic terms.

Reframe some output attributes as capability actions (e.g. 'Build dark navy page shells with cobalt gradient feature blocks and framed rails') so the 'what' reads as things the skill does rather than traits it describes.

DimensionReasoningScore

Specificity

Names the domain ('dark-blue clean design system') and concrete stylistic components ('cobalt gradient feature blocks', 'crisp framed structure', 'restrained premium glow'), but the only action is 'Create' — the remaining phrases are attributes of the output rather than capabilities. It does not list several distinct actions, so it sits at 'domain plus 1-2 concrete actions' rather than anchor 4.

3 / 5

Completeness

It clearly answers 'what' (create a dark-blue design system with the listed traits) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3. This exactly matches anchor 3: clear 'what', 'when' missing.

3 / 5

Trigger Term Quality

Some natural terms are present ('dark blue', 'clean', 'contrast', 'gradient', 'premium'), but the phrases a user would naturally say are missing — 'dark mode', 'navy', 'landing page', 'hero section', 'blue theme'. Anchor 3 ('some relevant keywords but missing common variations or synonyms') is the closest fit; it is above anchor 2 because the included terms are domain-relevant, not generic.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct — dark navy surfaces with cobalt contrast blocks, framed structure, and restrained glow clearly separates it from light sky-blue or neon sci-fi systems. Minor overlap risk remains with other generic dark-theme design skills because the description includes no negative triggers ('not dark mode dashboards', etc.), keeping it below anchor 5.

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.