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.

48

Quality

50%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a dense, highly actionable rulebook with concrete Tailwind/Framer specifics and a useful pre-flight checklist, but it is verbose and monolithic: large catalogs of known UI patterns and the Bento paradigm inflate the token budget and would benefit from being split into referenced files.

Suggestions

Move Section 8 (Creative Arsenal) and Section 9 (Motion-Engine Bento) into separate reference files (e.g. ARSENAL.md, BENTO.md) and link to them from SKILL.md to cut inline token load.

Tighten repeated emphatic boilerplate — consolidate the many 'strictly BANNED'/'NEVER'/'CRITICAL' repetitions into a single forbidden-patterns reference.

Add explicit feedback-loop guidance for the pre-flight check (run checklist → fix violations → re-check) to lift workflow clarity from a static checklist to a validated loop.

DimensionReasoningScore

Conciseness

The body is prescriptive rather than explanatory, but at ~227 lines it is padded with repeated emphatic language ('strictly BANNED', 'NEVER', 'CRITICAL') and large catalogs (Section 8's Creative Arsenal, Section 9's Bento paradigm) that restate UI patterns Claude already knows and could be tightened.

2 / 3

Actionability

Guidance is exceptionally concrete and copy-paste ready — exact Tailwind classes ('min-h-[100dvh]', 'shadow-[0_20px_40px_-15px_rgba(0,0,0,0.05)]'), exact Framer Motion configs ('stiffness: 100, damping: 20'), specific font and library names — far above the vague-direction anchor and not the incomplete-pseudocode anchor.

3 / 3

Workflow Clarity

There is a numbered section progression and a final pre-flight checklist that acts as a validation step, but the body is primarily a rule catalog rather than a clearly sequenced multi-step workflow with explicit feedback loops between stages.

2 / 3

Progressive Disclosure

The skill is well-organized into ten numbered sections, but no bundle files exist and the entire 227-line body — including the long Section 8 catalog and Section 9 paradigm that could be separate references — is inline in a single monolithic file rather than split into one-level-deep references.

2 / 3

Total

9

/

12

Passed

Description

35%

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 identifies a clear niche (high-agency frontend/UI engineering) and uses appropriate third-person voice, but it relies on jargon over natural trigger terms and omits any explicit 'Use when...' guidance, leaving when-to-invoke only implied.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when designing UIs, building dashboards, landing pages, or React/Next.js frontends').

Replace jargon-heavy phrases ('overriding default LLM biases', 'CSS hardware acceleration') with concrete, user-facing capability verbs.

Add common variation terms users actually say — 'frontend', 'website', 'component library', 'design system' — to broaden trigger coverage.

DimensionReasoningScore

Specificity

It names the domain ('Senior UI/UX Engineer', 'digital interfaces') and several actions ('Architect digital interfaces', 'Enforces metric-based rules'), but the actions are abstract characteristics ('balanced design engineering', 'CSS hardware acceleration') rather than the multiple concrete, granular actions a score-3 example lists.

2 / 3

Completeness

It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so the 'when to invoke' half is only implied — capping completeness at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

The phrasing is dominated by technical jargon ('overriding default LLM biases', 'CSS hardware acceleration', 'metric-based rules') and omits the natural terms a user would actually say ('design a UI', 'build a dashboard', 'landing page', 'React frontend').

1 / 3

Distinctiveness Conflict Risk

The frontend design-engineering niche is somewhat distinctive, but the broad domain ('digital interfaces', 'design engineering') and absence of explicit triggers mean it could still overlap with general web/frontend skills.

2 / 3

Total

7

/

12

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.

Validation16 / 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.