design

Simplified Aura guidance for selecting primitives, keeping token usage consistent, and applying reliable layout/copy/state patterns in Flows and Fusion apps.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 body is concise and well-organized as a router, but its actionability and workflow clarity depend on referenced files that are not bundled, and the inline guidance stays directional. Shipping the referenced .md files would resolve the largest gap.

Suggestions

Bundle the five referenced files (primitive-usage.md, picking-components.md, building-pages.md, handling-states.md, storybook-links.md) under references/ so the routing table resolves to real content.

Add at least one concrete inline example (a semantic-token snippet or a primitive-selection decision rule) so the body is actionable without opening a referenced file.

Fix the typo 'Guidlines' -> 'Guidelines' and confirm the node_modules DESIGN.md path is reachable, since it is presented as a canonical reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no padding about concepts Claude already knows (no explanations of what tokens or primitives are); every section earns its place, though Role and Operating Principles overlap slightly.	3 / 3
Actionability	Concrete rules exist ("apply semantic tokens (no raw values)", file-routing table) but the actual how-to detail is deferred to referenced files; the inline guidance is directional rather than fully executable, leaving key details out of the body.	2 / 3
Workflow Clarity	A numbered priority list and a decision-routing table give a light sequence, but there is no explicit multi-step workflow with checkpoints; for the deferred processes (forms, states) the sequencing lives entirely in the referenced files.	2 / 3
Progressive Disclosure	The overview plus file-routing table is well signaled and one level deep in intent, but the referenced files (primitive-usage.md, picking-components.md, building-pages.md, handling-states.md, storybook-links.md) are not present in the bundle, so navigation leads to missing content.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and well-scoped to a distinct niche, but it omits any explicit "Use when..." trigger guidance and its keywords are more technical than natural user phrasing. Adding a trigger clause would lift the two weaker dimensions.

Suggestions

Append a 'Use when ...' clause naming natural user triggers (e.g. 'Use when building or styling UI in Flows or Fusion, choosing components, or applying Aura tokens').

Add common-variation keywords users actually say (e.g. 'components', 'colors', 'spacing', 'design system') alongside the technical terms.

Keep the third-person voice but rephrase 'Simplified Aura guidance for ...' so the capability reads as concrete actions performed by the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "selecting primitives, keeping token usage consistent, and applying reliable layout/copy/state patterns" — rather than a single vague domain mention, matching the multi-action anchor.	3 / 3
Completeness	It clearly states what the skill does, but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain terms exist (primitives, token usage, Flows/Fusion apps) but they lean technical and lack natural user phrasings or common variations; no colloquial triggers are covered.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific design system (Aura) and platforms (Flows and Fusion apps), giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: cognitedata/builder-skills
Commit: ab7b5f8

Reviewed: 1 day 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.