aura-review

Checks how well an app uses Aura, Cognite's design system: what fraction of its components are Aura vs. custom-built, whether any custom components should really have been an existing Aura component, and whether Aura components got styled in ways that break the design system's own rules. Runs fully automatically by scanning the app's source and checking it against Aura's docs — no back-and-forth, so it also works unattended in CI. Writes a plain-language report to aura-review/report.md and a machine-readable aura-review/stats.json. Use when asked to run an Aura audit, check Aura compliance, or score how compliant an app is with the Aura design system.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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.

A well-structured, highly actionable audit workflow with clear sequencing, explicit validation checkpoints, and appropriate separation of the deterministic scan into a bundled script. The main weakness is occasional over-explanation of design rationale that could be tightened.

Suggestions

Tighten the auraCoveragePct rationale in Step 1/Step 2 — the repeated justifications for distinct-count vs occurrence-count and the KCIH ticket reference add length without aiding execution.

Trim meta-commentary like 'This step is deliberately the most expensive per-finding — it's also the one guarding against the exact failure mode...' to a single sentence so it earns its tokens.

Condense the repeated 'deliberately' design-choice explanations across Steps 1–3 into one rationale note rather than restating at each step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and purposeful, but several stretches of design rationale (the long auraCoveragePct justification, repeated 'deliberately' explanations, the KCIH ticket reference) explain non-obvious decisions at more length than needed and could be trimmed.	4 / 5
Actionability	Provides a fully executable scan command with NODE_PATH and tsx/npx fallback, exact prerequisite file paths, concrete grep targets, and exact copy-paste-ready JSON and markdown output schemas with stable field names.	5 / 5
Workflow Clarity	A clearly sequenced Step 0–6 workflow with explicit prerequisite checks, a deterministic scan, numbered judgment sub-steps, and built-in validation feedback ('do not guess', 'only flag what is documented', drop undocumented escape-hatch findings).	5 / 5
Progressive Disclosure	A single self-contained SKILL.md with clear section headers and one well-signaled one-level-deep bundle reference (scripts/scan-aura-usage.ts, invoked in Step 1), with the mechanical scan appropriately split into the script and judgment logic kept in the body.	5 / 5
	Total	19 / 20 Passed

Description

92%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.

A strong, concrete description that clearly states both what the skill does and when to use it, with a distinct niche and natural trigger phrases. Its only weakness is somewhat narrow trigger-term variation rather than broad synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — coverage fraction of Aura vs custom components, whether custom components should have been Aura, and whether Aura components break the design system's styling rules, plus writing a report and stats.json; comprehensive coverage with no real gaps.	5 / 5
Completeness	Explicitly answers both what (checks usage fraction, custom-vs-Aura, styling-rule breaks; writes report.md and stats.json; runs unattended in CI) and when ('Use when asked to run an Aura audit, check Aura compliance, or score how compliant an app is...').	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('run an Aura audit', 'check Aura compliance', 'score how compliant an app is with the Aura design system'), but the terms are narrow with little synonym/variation coverage rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche — Aura, Cognite's design system — with distinct, domain-locked triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 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/aura-review/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.