design

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

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/design/SKILL.md

Quality

Content

61%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 concise, well-sectioned design-guidance skill that assumes Claude's competence and points to one-level-deep external references. It is weakest on actionability and workflow clarity, offering principle-level directives rather than concrete examples or validation checkpoints.

Suggestions

Add one or two concrete inline examples (e.g., a semantic token name like `--surface-primary` vs a raw hex, or a primitive choice like 'use Table over a custom grid') to lift actionability.

Turn the operating principles into an explicit decision sequence with a checkpoint (e.g., 'after choosing a primitive, verify a variant/prop fits before considering a custom override').

Fix typos ('node_modeules', 'Guidlines') and tighten the 'where to find' list so the reference entry points read as deliberate navigation rather than a dump.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, using tight bullets and numbered principles with no padding about concepts Claude already knows; minor redundancy between the 'where to find', 'when-to-reference', and 'operating principles' lists keeps it just below the fully lean 5 anchor.	4 / 5
Actionability	Gives actionable directives ('Use Aura primitives before custom UI', 'apply semantic tokens (no raw values)', 'check variants/props first') but stays at principle level without concrete examples of which primitives/tokens to pick, fitting 'some concrete guidance but incomplete; missing key details'; not a 4 because no specific code, token names, or component examples are provided inline.	3 / 5
Workflow Clarity	The operating principles form a rough decision sequence (primitives -> tokens -> variants/props -> accessibility -> links) but there are no explicit validation checkpoints or feedback loops; matches 'steps listed but validation gaps; checkpoints missing or implicit', and the operation is not destructive/batch so the 3-cap does not additionally bind.	3 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections (Role, when-to-reference, Operating principles) with one-level-deep references to external resources (DESIGN.md, Storybook, docs site); no bundle files exist to verify, and minor organization gaps (the 'where to find' list reads as a dump with typos) keep it just below the 5 anchor.	4 / 5
	Total	14 / 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 clearly scopes a niche (Aura design system for Flows/Fusion apps) and lists several decision-level actions, but it lacks an explicit 'Use when...' trigger clause, which caps completeness and limits natural trigger discoverability. Actions are abstract rather than concrete operations.

Suggestions

Add an explicit 'Use when...' clause listing concrete triggers (e.g., 'Use when building or styling UI in Flows or Fusion apps, choosing components/tokens, or writing user-facing copy').

Replace abstract action phrasing with more concrete operations (e.g., 'select the right primitive, apply semantic tokens instead of raw values, structure consistent loading/error/empty states').

Include common natural synonyms users might say (e.g., 'Aura components', 'design tokens', 'Fusion widgets') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Aura, Flows/Fusion apps) and three actions ('selecting primitives, keeping token usage consistent, and applying reliable layout/copy/state patterns'), but the actions are abstract decision-level phrasing rather than concrete operations, fitting the 'names domain and 1-2 concrete actions, not comprehensive' anchor; not a 4 because the actions lack the concrete specificity of the 'fills forms, converts pages' example.	3 / 5
Completeness	Provides a clear 'what' (Aura guidance for primitives, tokens, layout/copy/state patterns) but no 'Use when...' or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 3, matching 'clear what but when is missing or only weakly implied.'	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('Aura', 'primitives', 'token usage', 'Flows and Fusion apps') a user in this ecosystem might say, but is jargon-heavy and missing common natural variations or synonyms; fits 'some relevant keywords but missing common variations' rather than the 4 anchor's broad coverage.	3 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('Aura' design system in 'Flows and Fusion apps'), making it mostly distinct with only minor overlap risk against a generic UI/styling skill; not a 5 because the absence of explicit 'Use when' triggers slightly raises conflict risk.	4 / 5
	Total	13 / 20 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
Path: skills/design/SKILL.md
Commit: c87160a

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.