design
Simplified Aura guidance for selecting primitives, keeping token usage consistent, and applying reliable layout/copy/state patterns in Flows and Fusion apps.
38
36%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/design/SKILL.mdQuality
Discovery
22%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 too vague and jargon-heavy to effectively guide skill selection. It lacks concrete actions, a 'Use when...' clause, and natural trigger terms that users would employ. While it references a specific technology ecosystem (Aura/Flows/Fusion), the abstract language makes it difficult to distinguish from other UI or design system skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when building or modifying Salesforce Lightning Aura components, configuring design tokens, or creating Flows and Fusion app layouts.'
Replace abstract phrases like 'applying reliable layout/copy/state patterns' with concrete actions such as 'select appropriate Aura base components, configure design tokens for consistent styling, implement state management in Lightning components.'
Include natural trigger terms users would say, such as 'Lightning component', 'Salesforce UI', 'design tokens', 'SLDS', 'aura:component', or 'Flow screen'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'selecting primitives', 'keeping token usage consistent', and 'applying reliable layout/copy/state patterns' without listing concrete actions. It names a domain (Aura/Flows/Fusion apps) but the actions are abstract and unclear. | 1 / 3 |
Completeness | The description partially addresses 'what' (guidance for Aura primitives, tokens, patterns) but is vague about it, and completely lacks a 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | It includes some domain-specific terms like 'Aura', 'Flows', 'Fusion apps', 'primitives', and 'token usage' that users in the Salesforce ecosystem might use. However, it lacks common natural language variations a user might say, such as 'Lightning component', 'design tokens', 'Salesforce UI', or 'component library'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Aura', 'Flows', and 'Fusion apps' provides some specificity to a particular framework/ecosystem, but the broad terms like 'layout/copy/state patterns' could overlap with general UI development or design system skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions primarily as a routing/index document that directs Claude to the right sub-file based on the task at hand. The file routing table is its strongest element, providing clear navigation. However, the skill lacks concrete examples, executable code, or specific actionable guidance within the body itself, relying entirely on referenced files that cannot be verified. The operating principles are sensible but abstract.
Suggestions
Add a brief concrete example showing a common decision (e.g., 'For a confirmation dialog, use `<Dialog variant="confirmation">` from primitive-usage.md — not a custom modal') to make the operating principles actionable.
Include a minimal quick-start workflow showing the typical sequence: choose primitive → apply tokens → verify in Storybook, with a concrete code snippet.
Trim the `<when-to-reference>` block — most of those triggers are obvious from the file routing table and add token overhead without new information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but the `<when-to-reference>` section is somewhat verbose, listing many scenarios that Claude could infer. The file routing table and operating principles are lean and useful, but the role section has some redundancy with the operating principles. | 2 / 3 |
Actionability | Provides clear routing to specific files and a useful decision table, but the skill itself contains no executable code, concrete examples, or copy-paste-ready guidance. It functions as a router/index, which is valid, but the operating principles are abstract ('use Aura primitives before custom UI') without concrete examples of what that looks like in practice. | 2 / 3 |
Workflow Clarity | The file routing table provides a clear decision tree for which file to consult, and the operating principles establish a priority order (check variants/props first, then document the gap). However, there's no explicit multi-step workflow with validation checkpoints for common tasks like migrating UI or choosing components. | 2 / 3 |
Progressive Disclosure | The file routing table clearly signals one-level-deep references to specific files (primitive-usage.md, picking-components.md, building-pages.md, handling-states.md, storybook-links.md). However, no bundle files were provided to verify these references exist, and the mix of referencing both bundle files and node_modules paths (DESIGN.md) without clear distinction is slightly confusing. The structure is reasonable but could be better organized with a quick-start section. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- 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.