CtrlK
BlogDocsLog inGet started
Tessl Logo

web-prototype-taste-editorial

Editorial-minimalist web prototype. Warm monochrome canvas, serif display + grotesque body, 1px hairline borders, muted pastel chips, generous macro-whitespace, ambient micro-motion. Distilled from Leonxlnx/taste-skill `minimalist-skill`.

60

Quality

68%

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 ./design-templates/web-prototype-taste-editorial/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, high-density design rulebook: exact values, a banned list, required components, and a validation checklist with essentially zero wasted tokens. Its main defects are the missing promised example.html template (a broken reference and the absence of a complete worked example) and the lack of an explicit build order beyond section ordering.

Suggestions

Add the referenced `example.html` to the bundle (or inline a compact HTML skeleton) so the "fully-realized template" pointer resolves.

Add a brief ordered workflow before "Hard rules" (e.g., 1. read rules/bans, 2. scaffold from example.html, 3. assemble required components, 4. run pre-flight) to give the checklist a forward sequence.

Split the long font-stack and pastel-chip value lists into a small reference file if the skill grows, keeping SKILL.md as the overview.

DimensionReasoningScore

Conciseness

Every line is a rule with a concrete value ("#FBFBFA", "letter-spacing: -0.025em", "py-24", "cubic-bezier(0.16, 1, 0.3, 1)") — no explanation of concepts Claude already knows, no padding, no filler. The one-line Source attribution is the only non-instructional text and earns its place.

5 / 5

Actionability

The guidance is unusually concrete for an instruction-only skill: exact hex values, named font stacks, pixel values, Tailwind classes, timings, and easing curves, plus a "Banned" list and required component inventory. Not a 5 because the promised fully-realized template ("See `example.html` in this directory") does not exist in the bundle, leaving no complete worked example to execute from.

4 / 5

Workflow Clarity

The single action (produce an editorial-minimalist page) is unambiguous, and the "Pre-flight" checklist provides explicit post-hoc validation (seven checkboxes covering pairing, colors, borders, asymmetry, padding, banned items). Not a 5 because there is no forward sequence telling Claude how to proceed — e.g., start from the template, then apply hard rules, then check pre-flight — and the missing example.html removes the natural starting step.

4 / 5

Progressive Disclosure

Sections are well-labeled and scannable, but the only external reference — "See `example.html` in this directory for a fully-realized template" — is a dangling pointer: no example.html and no references/, scripts/, or assets/ directories exist in the bundle. Per the rubric, progressive disclosure is scored against the actual bundle structure, so a clearly-signaled reference to a nonexistent file caps this at 3.

3 / 5

Total

16

/

20

Passed

Description

58%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 gives a vivid, concrete picture of the artifact's visual identity and stays appropriately brief, but it is entirely a "what" with no "when" — the rubric explicitly caps completeness at 3 for a missing 'Use when...' clause. Trigger vocabulary leans toward design jargon rather than natural user phrases.

Suggestions

Append an explicit trigger clause, e.g. "Use when the brief asks for a clean, editorial, or premium-SaaS look for a landing page or documentation site."

Surface natural user phrases from the body ("clean", "editorial", "premium SaaS", "documentation") into the description itself so trigger matching works from the description alone.

Move one concrete font-stack or hex example into the description to sharpen the 'what' without adding a 'Use when' dependency.

DimensionReasoningScore

Specificity

"Editorial-minimalist web prototype" names the artifact, followed by six concrete attributes ("warm monochrome canvas", "serif display + grotesque body", "1px hairline borders", "muted pastel chips", "generous macro-whitespace", "ambient micro-motion") with explicit type/color vocabulary. Not a 5 because it describes deliverable qualities rather than listing multiple concrete actions, and the specific values (hex codes, font stacks) live in the body, not the description.

4 / 5

Completeness

The "what" is clear: an editorial-minimalist styled web prototype with enumerated visual traits. But there is no "when" — no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Terms like "web prototype", "serif", "minimalist" are relevant, but most of the vocabulary ("macro-whitespace", "ambient micro-motion", "grotesque") is designer jargon users would not naturally say. The natural trigger phrases users actually use ("clean", "premium SaaS", "documentation site", "landing page") appear only in the body, not the description — so common variations and synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

"Editorial-minimalist web prototype" with its specific trait list carves out a fairly distinct niche and names its source skill, making mistaken triggering unlikely for most skills. Not a 5 because it could still overlap with sibling web-design/aesthetic skills (e.g., other taste/design-system skills where "clean" or "minimalist" styling is requested).

4 / 5

Total

14

/

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
nexu-io/open-design
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.