CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

common-ui-design

Design distinctive, production-grade frontend UI with bold aesthetic choices. Use when building web components, pages, interfaces, dashboards, or applications in any framework (React, Next.js, Angular, Vue, HTML/CSS).

Quality

81%

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

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.

The body is a well-structured, token-efficient overview that defers concrete palettes, CSS patterns, and the full refinement protocol to real, one-level-deep reference files — progressive disclosure is exemplary. Actionability and workflow clarity are strong, with concrete numeric thresholds and an explicit critique loop, held back only by small redundancies, absent inline examples, and implied phase transitions. No basic-concept padding or time-sensitive content is present.

DimensionReasoningScore

Conciseness

The body is dense directive prose with no explanations of concepts Claude already knows, but the polish-default rule and the delivery-receipts/false-equivalence points each appear twice (Phase 0 and Rendered Critique vs. Anti-Patterns), and a few aphorisms ("Intentionality over extreme novelty") could be trimmed — efficient with minor slack, not fully lean.

4 / 5

Actionability

For an instruction-only skill the guidance is mostly actionable: concrete contrast thresholds ("normal text ≥ 4.5:1, large text ≥ 3:1"), an explicit token role list, enumerated interactive states, and the "Observation → Impact → Smallest Change → Preserve Constraint" loop. It stays below the top anchor because no worked example is inline and no method is given for verifying composited contrast.

4 / 5

Workflow Clarity

A clear ordered process is present (Phase 0 pre-code questions → foundations → rendered critique) with an explicit feedback loop and defect/context/taste classification as checkpoints. It misses the top anchor because the transitions between foundations, implementation, and critique are implied rather than an explicit numbered sequence.

4 / 5

Progressive Disclosure

A lean ~54-line overview with three well-signaled, one-level-deep references (tones.md, motion.md, human-direction.md), all verified to exist as substantive files with no nested references; references are linked inline at point of need ("load when implementing animations") and again in a References section.

5 / 5

Total

17

/

20

Passed

Description

78%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 solid description with an explicit and well-phrased trigger clause covering frameworks and artifact types. Its main weakness is the "what" half, which leans on abstract qualifiers ("distinctive", "bold aesthetic choices") instead of naming the concrete design capabilities the skill provides. Third-person-imperative voice is used consistently, matching the good examples.

Suggestions

Replace abstract qualifiers with concrete capability verbs in the first sentence, e.g. "Define role-based color tokens, pair display/body typography, and verify WCAG contrast for frontend UI" so users know what the skill actually does.

Add missing natural trigger phrases to the 'Use when' clause, such as "landing page", "redesign", or "make it look good", which users commonly say when they need this skill.

DimensionReasoningScore

Specificity

The description names the domain ("frontend UI") and one main action ("Design"), but the modifiers "distinctive, production-grade... bold aesthetic choices" are abstract qualifiers rather than additional concrete capabilities, matching the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

It clearly answers "what" ("Design distinctive, production-grade frontend UI") and "when" with an explicit "Use when building..." clause listing concrete trigger phrases and frameworks, matching the top anchor exactly.

5 / 5

Trigger Term Quality

"building web components, pages, interfaces, dashboards, or applications in any framework (React, Next.js, Angular, Vue, HTML/CSS)" gives good natural keyword coverage including framework names, but misses common user phrases like "landing page", "redesign", or "style", so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Framework-scoped UI-building triggers make it mostly distinct from other skills, but terms like "dashboards" and "interfaces" carry minor overlap risk with visualization or general web-development skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

HoangNguyen0403/agent-skills-standard

Path

.github/skills/common/common-ui-design/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.