CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

industrial-brutalist-ui

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

60

Quality

75%

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 ./skills/brutalist-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 strong, concrete design-system spec that is token-efficient and highly actionable on typography, color, and layout. Its main weaknesses are the absence of a sequenced design workflow with validation checkpoints and a couple of effect recipes left at the hint level rather than executable snippets.

Suggestions

Add a short quick-start workflow that sequences the decisions (choose archetype, pick substrate palette, apply typography, apply effects) with a final validation checklist (e.g., no border-radius, no gradients, contrast check, single accent color).

Provide an executable snippet for the halftone/1-bit dithering recipe, as it is currently described only abstractly while scanlines and grid lines get concrete CSS.

Consider moving detailed effect recipes or font/color token tables into a references file, keeping SKILL.md as a lean overview with clearly signaled links.

DimensionReasoningScore

Conciseness

The body is dense with concrete values (hex palettes, em/rem ranges, font lists, exact CSS) and assumes competence, avoiding explanations of known concepts; only light rhetorical flourishes like 'The color architecture is uncompromising' and the duplicated meta section keep it from a 5.

4 / 5

Actionability

Most guidance is directly executable — exact colors, tracking/leading ranges, a scanline gradient snippet, 'display: grid; gap: 1px;', and named semantic tags — but the halftone/dithering recipe stays abstract ('pre-processing or mix-blend-mode: multiply overlays') without a concrete snippet, leaving minor gaps.

4 / 5

Workflow Clarity

Decision points exist ('Pick ONE per project and commit to it', 'Choose ONE substrate palette per project') but they are scattered across sections rather than sequenced into a workflow, and there are no validation checkpoints (e.g., contrast or border-radius audit), matching 'steps present but checkpoints missing'.

3 / 5

Progressive Disclosure

A well-organized 8-section self-contained spec with no external references, entirely appropriate for a single style guide of this size; minor gaps in that some detailed recipes (halftone, CRT effects) could be split into reference files with the body as overview.

4 / 5

Total

15

/

20

Passed

Description

70%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.

A distinctive, well-scoped description with concrete stylistic details and an explicit use-case clause, but it describes a style rather than actions and lacks the crispest 'Use when...' trigger phrasing and synonym coverage. Solidly above midpoint overall.

Suggestions

Lead with action verbs, e.g. 'Builds web interfaces in an industrial-brutalist style: ...' so the skill's capability, not just the aesthetic, is explicit.

Rewrite the trigger clause as explicit 'Use when...' guidance and add common synonyms (brutalism/brutalist, CRT, HUD, tactical, Swiss design) to broaden natural trigger coverage.

State what is produced (HTML/CSS design systems, styled components) in addition to the visual characteristics.

DimensionReasoningScore

Specificity

The description names the domain with concrete characteristics ('Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects') but never states an action the skill performs, so it sits at 'names domain and specifics' rather than 'lists several specific actions'.

3 / 5

Completeness

The what is clear (the design elements) and a when-equivalent is present ('For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints'), but it is not phrased as explicit 'Use when' trigger guidance with fuller trigger phrases, keeping it below a 5.

4 / 5

Trigger Term Quality

Natural trigger terms like 'dashboards', 'portfolios', 'editorial sites', 'Swiss', and 'military terminal' cover the common user phrasings, though synonyms such as 'brutalism', 'CRT', or 'tactical' are absent from the description text.

4 / 5

Distinctiveness Conflict Risk

'Declassified blueprints' and the Swiss/terminal fusion define a clear niche with distinct triggers; only minor overlap risk with generic web-design or brand-style skills, not enough to drop to 3.

4 / 5

Total

15

/

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

Leonxlnx/taste-skill

Path

skills/brutalist-skill/SKILL.md

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.