baseline-ui
tessl i github:ibelick/ui-skills --skill baseline-uiEnforces an opinionated UI baseline to prevent AI-generated interface slop.
Review Score
67%
Validation Score
11/16
Implementation Score
100%
Activation Score
7%
Generated
Validation
Total
11/16Score
Passed| Criteria | Score |
|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') |
metadata_version | 'metadata' field is not a dictionary |
license_field | 'license' field is missing |
body_examples | No examples detected (no code fences and no 'Example' wording) |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow |
Implementation
Score
100%Overall Assessment
This is an exemplary skill file that demonstrates excellent constraint-based documentation. It's highly scannable with consistent MUST/SHOULD/NEVER formatting, provides specific technical guidance without over-explaining, and organizes rules into logical categories. The two usage modes are clearly defined with expected outputs.
| Dimension | Score | Reasoning |
|---|---|---|
Conciseness | 3/3 | Extremely lean and efficient. Every rule is a single line with clear MUST/SHOULD/NEVER keywords. No unnecessary explanations of what Tailwind or React are—assumes Claude's competence throughout. |
Actionability | 3/3 | Highly actionable with specific library names, utility functions (`cn`, `clsx`, `tailwind-merge`), exact CSS properties to use/avoid, and concrete thresholds (e.g., `200ms` for feedback). The `/baseline-ui <file>` command specifies exact output format. |
Workflow Clarity | 3/3 | For a constraint-based skill (not a multi-step process), the workflow is clear: apply constraints during UI work, or review files against the checklist with specified output format (violations, reasoning, fix). The single-task nature is unambiguous. |
Progressive Disclosure | 3/3 | Well-organized into logical sections (Stack, Components, Interaction, Animation, etc.) with clear headings. At ~80 lines, appropriately self-contained with one external reference (Base UI docs) that's clearly signaled. |
Activation
Suggestions 3
Score
7%Overall Assessment
This description is too vague and jargon-heavy to be useful for skill selection. It fails to specify what concrete actions the skill performs, uses non-standard terminology ('slop'), and lacks any trigger guidance for when Claude should select it. The description would benefit from listing specific UI rules enforced and natural trigger terms.
Suggestions
- Replace vague terms with specific actions (e.g., 'Enforces consistent spacing, typography, color usage, and component patterns in UI code').
- Add a 'Use when...' clause with natural trigger terms like 'UI', 'interface', 'frontend', 'React components', 'styling', 'design consistency'.
- Define what 'opinionated baseline' means concretely - list the specific rules or standards being enforced (e.g., 'Tailwind conventions', 'accessibility standards', 'responsive design patterns').
| Dimension | Score | Reasoning |
|---|---|---|
Specificity | 1/3 | The description uses vague language like 'opinionated UI baseline' and 'interface slop' without specifying concrete actions. It doesn't explain what the skill actually does (e.g., applies specific styles, validates components, enforces spacing rules). |
Completeness | 1/3 | Missing both clear 'what' (no specific actions listed) and 'when' (no explicit trigger guidance or 'Use when...' clause). The description fails to answer either question adequately. |
Trigger Term Quality | 1/3 | Contains no natural keywords users would say. Terms like 'opinionated UI baseline' and 'interface slop' are jargon that users wouldn't naturally use when requesting help with UI work. |
Distinctiveness Conflict Risk | 2/3 | The phrase 'UI baseline' and 'AI-generated interface' provides some domain specificity around UI/interface work, but 'slop' is vague and could overlap with general code quality or design system skills. |