CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

baseline-ui

Baseline UI rules to prevent design slop. Use for UI design or review.

Quality

74%

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 ./.agents/skills/04-develop/01-ui-skills-dot-com/baseline-ui/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 exemplary lean rulebook: dense, specific, well-sectioned, with explicit verification commands and a clear review output contract. Its only weaknesses are small specificity gaps (unspecified z-index scale, no code examples) and a missing error-recovery step after a NO-GO verification result.

DimensionReasoningScore

Conciseness

The body is pure imperative rules with zero padding — e.g., "NEVER use `h-screen`, use `h-dvh`" and "MUST use `text-balance` for headings and `text-pretty` for body/paragraphs" — and explains nothing Claude already knows. Every token earns its place.

5 / 5

Actionability

Guidance is highly concrete: specific classes (`h-dvh`, `tabular-nums`, `size-*`), libraries (`motion/react`, `cn`), thresholds ("NEVER exceed `200ms`"), commands (`pnpm lint`, `pnpm test`, `pnpm build`, `pnpm verify`), and a defined review output format (violation + why + fix). Minor gaps keep it below fully executable: the "fixed `z-index` scale" is never specified and there are no copy-paste code examples.

4 / 5

Workflow Clarity

Both usage modes are unambiguous (apply constraints to UI work; for review, output violations with snippet + fix) and the Verify section provides explicit commands with a GO/NO-GO checkpoint. It falls short of a 5 because there is no error-recovery loop (what to do on NO-GO) and the body is longer than the simple-skill threshold.

4 / 5

Progressive Disclosure

No bundle files exist and the ~84 lines of rules are appropriately inline under clear section headers (Stack, Components, Interaction, Animation, Typography, Layout, Performance, Design), with one clearly signaled external link to Base UI. Minor gaps — e.g., the unspecified z-index scale and 'Source: ui-skills.com' attribution — keep it from a 5, and the under-50-line simple-skill exception does not apply.

4 / 5

Total

17

/

20

Passed

Description

53%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 is concise and has an explicit use clause, but it names the domain without listing concrete capabilities, and its trigger terms are too broad to distinguish it from other UI/frontend skills. Broadening the trigger vocabulary and naming one or two concrete actions would materially improve it.

Suggestions

Add 1-2 concrete actions to the description, e.g., 'Enforces UI baseline rules (animation, typography, accessibility, layout) when building or reviewing interfaces' instead of the generic 'Baseline UI rules'.

Expand trigger terms with natural synonyms users would say: 'Use for UI design, frontend work, interface reviews, component styling, or when the user mentions Tailwind, design slop, or UI polish.'

Sharpen the 'when' clause to be more specific about review mode, e.g., 'Use when creating or reviewing React + Tailwind UI code', to reduce overlap with general design or data-visualization skills.

DimensionReasoningScore

Specificity

"Baseline UI rules to prevent design slop" names the domain but lists no concrete actions or capabilities, matching 'Names the domain but actions are minimal or generic'. It is not a 3 because no specific actions (e.g., apply constraints, review files for violations) are actually enumerated.

2 / 5

Completeness

Both parts are present: 'what' ("Baseline UI rules to prevent design slop") and an explicit 'when' ("Use for UI design or review"), but the 'when' is broad and could be more specific. It is not a 5 because the trigger guidance lacks concrete trigger phrases, and not a 3 because an explicit 'Use for...' clause exists.

4 / 5

Trigger Term Quality

"Use for UI design or review" includes the natural phrase 'UI design', but common variations users would say — frontend, interface, components, styling, Tailwind — are missing. Good keyword coverage is not reached, so it sits at 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

"prevent design slop" carves a recognizable niche, but "Use for UI design or review" is broad and would overlap with general frontend, styling, and design-review skills. This matches 'Somewhat specific but could still overlap with similar skills'.

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

marchatton/agent-skills

Path

.agents/skills/04-develop/01-ui-skills-dot-com/baseline-ui/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.