CtrlK
BlogDocsLog inGet started
Tessl Logo

design-taste-frontend

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

52

Quality

56%

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 ./workshops/soccer-analytics-agent/.claude/skills/taste-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 an impressively concrete rulebook — nearly every directive carries an executable class, parameter, or URL, and it closes with a validation-style pre-flight checklist. Its main weaknesses are length-driven redundancy (motion rules stated twice across Sections 4 and 9) and a total absence of progressive disclosure: a 227-line monolith whose inspiration catalog and Bento spec belong in one-level-deep reference files.

Suggestions

Split the Creative Arsenal catalog (Section 8) and the Bento paradigm (Section 9) into one-level-deep reference files (e.g. references/inspiration.md, references/bento.md), keeping only a summarized index plus 'See [FILE](FILE)' links in SKILL.md.

De-duplicate the motion rules: Section 4 and Section 9 both specify spring parameters, perpetual loops, and layout/layoutId — state them once and have Section 9 reference the earlier rule set.

Trim padded emphasis ('BANNED', 'CRITICAL', 'MUST' repeated many times) and redundant restatements (e.g. Inter/font bans appearing in both Sections 3 and 7) to cut token cost without losing guidance.

DimensionReasoningScore

Conciseness

The body is directive-dense and assumes Claude's knowledge of React, Tailwind, and Framer Motion without re-explaining them, but at ~227 lines it carries notable redundancy: Section 4 and Section 9 both restate spring physics ('type: "spring", stiffness: 100, damping: 20'), perpetual micro-interactions, and layout/layoutId, while Sections 3 and 7 overlap on anti-slop typography and color rules. Mostly efficient but could be tightened, matching the 3 anchor rather than 4.

3 / 5

Actionability

Guidance is highly concrete and executable: exact Tailwind classes ('min-h-[100dvh]', 'grid grid-cols-1 md:grid-cols-3 gap-6', 'rounded-[2.5rem]'), specific spring parameters, concrete placeholder URLs ('https://picsum.photos/seed/{random_string}/800/600'), and a mandatory package.json dependency check before imports. It falls short of the 5 anchor because no complete copy-paste-ready component example is provided, but it is well above the pseudocode level of 3.

4 / 5

Workflow Clarity

The skill is rule-based rather than a destructive multi-step process, and it supplies both sequencing (numbered Sections 1-10, baseline dials driving later logic) and checkpoints: a mandatory dependency-verification gate before any import and a final pre-flight checklist ('FINAL PRE-FLIGHT CHECK') covering viewport stability, cleanup, and state coverage. Minor validation gaps (no explicit verify/retry loop after the checklist) keep it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the entire body is one monolithic file with clear section headers. Content that clearly belongs in separate reference files — the ~60-line Creative Arsenal catalog, the AI Tells list, and the full Bento paradigm spec — is inlined in SKILL.md. Structure is present, but the split is missing, matching the 3 anchor ('some structure; content that should be separate is inline').

3 / 5

Total

14

/

20

Passed

Description

50%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 reads like a persona tagline rather than a skill description: it establishes a 'what' at a moderate level of specificity but provides no 'when to use' trigger guidance, which both caps completeness and leaves trigger-term and distinctiveness coverage thin. Rewriting it around concrete capabilities plus explicit trigger conditions would move every dimension up.

Suggestions

Replace the persona framing ('Senior UI/UX Engineer. Architect digital interfaces...') with concrete third-person actions, e.g. 'Generates premium React/Tailwind interfaces with motion, design-variance, and density dials...'.

Add an explicit 'Use when...' clause, e.g. 'Use when building or restyling web UIs, landing pages, dashboards, or component libraries, or when the user asks for modern, high-end frontend design.'

Include natural trigger terms users actually say (UI design, frontend, landing page, dashboard, React component, Tailwind) to improve trigger-term coverage and reduce overlap with generic frontend skills.

DimensionReasoningScore

Specificity

The description names the domain ('UI/UX Engineer', 'digital interfaces') and a couple of semi-concrete actions ('Enforces metric-based rules', 'CSS hardware acceleration'), but phrases like 'balanced design engineering' and 'overriding default LLM biases' are abstract. It lists 1-2 concrete actions without comprehensive coverage, matching the 3 anchor and falling short of the 4 anchor's 'several specific actions'.

3 / 5

Completeness

The 'what' is reasonably clear (architect digital interfaces under metric-based design rules), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

'UI/UX', 'digital interfaces', 'CSS', and 'component architecture' are relevant keywords a user might say, but common natural variations like 'design a UI', 'build a landing page', 'dashboard', 'frontend', or 'React' are missing. Some relevant keywords exist but synonyms and variations are absent, fitting the 3 anchor.

3 / 5

Distinctiveness Conflict Risk

The design-quality niche ('UI/UX Engineer', 'metric-based rules') is somewhat specific and distinguishable from document or data skills, but 'Architect digital interfaces' is broad enough to overlap with general frontend, styling, and web-app skills. With no trigger phrases to disambiguate, it fits the 3 anchor ('somewhat specific but could still overlap').

3 / 5

Total

12

/

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
oracle-devrel/oracle-ai-developer-hub
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.