building-components

Guide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs, setting up design tokens, publishing to npm/registry, or writing component documentation.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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 efficient, well-organized index that exemplifies progressive disclosure, but it provides no inline executable guidance or workflow, leaving the reader to consult references for any concrete instruction. Actionability and workflow clarity are the weak points.

Suggestions

Add a short 'Quick start' section with at least one small executable snippet (e.g., a minimal component scaffold or a design-token definition) so the body is actionable without forcing every reader into a reference file.

Include a brief recommended workflow or checklist for the most common task (e.g., build -> add accessibility -> compose -> publish) with any validation step, rather than only a flat file index.

Add light routing guidance mapping common requests to the right reference (e.g., 'For as-child pattern, start with as-child.mdx then polymorphism.mdx') to give the index a usable sequence.

Dimension	Reasoning	Score
Conciseness	The body is a lean trigger list plus a one-line-per-file reference index with no padding and no explanation of concepts Claude already knows; every token earns its place, matching the lean level-3 anchor.	3 / 3
Actionability	The body contains no code, commands, or concrete how-to guidance — it only lists use-cases and points to reference files, matching the 'describes rather than instructs' level-1 anchor and falling below the incomplete-guidance level-2 anchor.	1 / 3
Workflow Clarity	There is no multi-step sequence or validation checkpoint, only a flat file index; it is organized but lacks any process guidance, so it sits at level 2 rather than 3 (no clear sequence) and above 1 (intent and structure are present).	2 / 3
Progressive Disclosure	A concise overview with 15 well-signaled one-level-deep references, each annotated and all verified to exist in ./references/, matching the clear-overview-with-navigable-references level-3 anchor.	3 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person, and explicitly pairs capabilities with natural 'Use when...' triggers, covering what and when without padding. It is clearly scoped to UI component work and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "building new components", "implementing accessibility", "creating composable APIs", "setting up design tokens", "publishing to npm/registry", "writing component documentation" — matching the multiple-specific-actions anchor rather than the partial coverage at level 2.	3 / 3
Completeness	Explicitly answers both what ("Guide for building modern, accessible, and composable UI components") and when ("Use when building new components..."), satisfying the explicit-trigger requirement that caps level 2 when missing.	3 / 3
Trigger Term Quality	Uses natural terms a user would say ("building new components", "accessibility", "design tokens", "npm/registry", "component documentation") with good coverage of common phrasings, beyond the single-keyword level-2 anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a clear UI-component-building niche with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor rather than the overlapping level-2 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: databricks/devhub
Commit: 131db95

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.