CtrlK
BlogDocsLog inGet started
Tessl Logo

design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

44

Quality

45%

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/taste-skill-v1/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 rich, highly actionable set of opinionated frontend-design directives with concrete class strings, values, and a closing pre-flight checklist. Its main weaknesses are verbosity (a catalog of familiar UI patterns and repeated rules) and total absence of progressive disclosure — everything lives in one 220-line file.

Suggestions

Move the Section 8 Creative Arsenal pattern catalog into a separate REFERENCES.md, keeping only a one-line pointer and the most essential anti-slop rules inline.

De-duplicate rules repeated across sections (Inter ban, spring physics, RSC isolation) so each directive appears once.

Add a short ordered workflow at the top (baseline → architecture → directives → pre-flight) to make the intended sequence explicit beyond the section numbering.

DimensionReasoningScore

Conciseness

The core directives are specific and opinionated, but the ~220-line body is padded with redundant emphasis (rules repeated across sections, e.g. the Inter ban and spring-physics values) and a large catalog of well-known UI patterns in Section 8 that Claude already knows.

2 / 3

Actionability

Guidance is highly concrete and copy-paste-ready: exact Tailwind class strings (`min-h-[100dvh]`, `shadow-[0_20px_40px_-15px_rgba(0,0,0,0.05)]`), install commands (`npm install package-name`), and precise motion values (`stiffness: 100, damping: 20`) — actionable per the instruction-skill note even without full code blocks.

3 / 3

Workflow Clarity

Content is organized into numbered sections with a final validation checkpoint (Section 10 pre-flight checklist), but it reads as a reference manual rather than a clearly sequenced multi-step workflow with feedback loops between stages.

2 / 3

Progressive Disclosure

The skill is a single monolithic SKILL.md with no bundle files or external references, and large inline catalogs (Section 8 Creative Arsenal, Section 9 Bento Paradigm) that could be split into separate reference files; section organization is decent but nothing is offloaded.

2 / 3

Total

9

/

12

Passed

Description

25%

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 functions as a versioning/deprecation notice rather than a capability statement: it explains when to prefer v1 over v2 but never says what the skill does or offers natural trigger terms. It is distinctive in intent but sparse and jargon-heavy in execution.

Suggestions

Add a concrete capability clause naming what the skill does (e.g., 'Generates high-agency, anti-slop frontend designs') before the versioning context.

Include natural trigger terms users would say (e.g., 'design taste', 'frontend aesthetic', 'anti-AI-slop UI') rather than only install names.

Restructure as 'what it does' + 'Use when...' so both halves are explicit, keeping the v1-vs-v2 guidance as a trailing note.

DimensionReasoningScore

Specificity

The description states only versioning/provenance metadata ("The original v1 taste-skill, preserved for projects depending on its exact behavior") and lists no concrete capabilities or actions the skill performs; per the guideline not to infer capabilities, nothing actionable is explicitly stated.

1 / 3

Completeness

An explicit when-clause is present ("Use this v1 install name only if you need exact backward compatibility"), but the what is only weakly conveyed via the name "taste-skill" with no statement of what the skill actually does.

2 / 3

Trigger Term Quality

The text contains only technical install names like `design-taste-frontend` and `design-taste-frontend-v1` plus "backward compatibility" — no natural keywords a user would actually say when they need this skill.

1 / 3

Distinctiveness Conflict Risk

It explicitly disambiguates from the v2 sibling ("The current default is `design-taste-frontend` (v2 experimental)"), carving out a backward-compat niche, but the underlying design-taste triggers overlap heavily with the v2 default so conflict risk remains.

2 / 3

Total

6

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.