code-standards

TypeScript, React, and JavaScript best practices enforced by Ultracite/Biome.

1.08x

Quality

55%

Does it follow best practices?

Impact

92%

1.08x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./frontend/.claude/skills/code-standards/SKILL.md

Quality

Content

65%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 tight, command-driven standards skill with genuinely useful concrete rules, weakened by a redundant Quick Fix section, an unsequenced check/fix workflow without verification, and references to rule files that are absent from the bundle.

Suggestions

Remove the 'Quick Fix' section (it repeats 'bun x ultracite fix' from Commands) or replace it with an explicit sequence: run 'check', apply 'fix', then re-run 'check' to verify nothing remains.

Ship the referenced rule files (react-functional-only.md, async-await-promises.md, no-legacy.md) in the bundle, or remove the pointers if the guidance lives only in Biome configuration.

Add one short compliant-vs-noncompliant code example (e.g. a typed React function component vs an 'any'-typed one) so the standards are directly actionable without opening external docs.

Dimension	Reasoning	Score
Conciseness	The body is lean and free of concept explanations, but the 'Quick Fix' section is fully redundant — 'bun x ultracite fix' already appears verbatim in the Commands section.	4 / 5
Actionability	Concrete executable commands, named Biome rules ('noExplicitAny', 'useTopLevelRegex'), and a specific console-logging policy make the guidance mostly executable, though no compliant-code examples are shown and the 'See rules/ directory' pointer resolves to nothing.	4 / 5
Workflow Clarity	The check/fix/doctor commands are listed but never sequenced into a workflow, and there is no verification step (e.g. re-running 'check' after 'fix' to confirm no remaining issues) — checkpoints are missing rather than merely implicit.	3 / 5
Progressive Disclosure	The body is well-sectioned and appropriately short, but its file pointers ('react-functional-only.md', 'async-await-promises.md', 'no-legacy.md', 'rules/ directory') reference files that do not exist in the bundle, leaving navigation dangling.	3 / 5
	Total	14 / 20 Passed

Description

45%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 names a clear domain and tooling, but stays at the level of a topic label rather than a capability statement. It lacks both concrete actions and any 'when to use' trigger guidance.

Suggestions

Add explicit 'Use when...' trigger guidance, e.g. 'Use when fixing lint or formatting errors, addressing code review feedback, or answering style questions in TypeScript/React/JavaScript code.'

Replace the generic 'best practices' with 2-3 concrete capabilities, e.g. 'Fixes lint/formatting issues via Ultracite (Biome), enforces React function-component and async/await patterns, bans legacy libraries.'

Include natural trigger terms users would say, such as 'lint errors', 'format code', 'code style', or 'Biome'.

Dimension	Reasoning	Score
Specificity	Names the domain ('TypeScript, React, and JavaScript') and an enforcement mechanism ('enforced by Ultracite/Biome'), but 'best practices' is generic — no concrete actions like linting, formatting, or fixing errors are stated.	2 / 5
Completeness	A 'what' is present ('best practices enforced by Ultracite/Biome') though vague, and the 'when' is entirely missing — no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3.	3 / 5
Trigger Term Quality	'TypeScript, React, and JavaScript' are terms users naturally say, but common trigger phrases users would actually use — 'lint', 'format', 'code style', 'fix lint errors' — are absent.	3 / 5
Distinctiveness Conflict Risk	The broad frontend-web scope could overlap with general coding or framework skills, though 'Ultracite/Biome' is a reasonably distinct niche marker.	3 / 5
	Total	11 / 20 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: redpanda-data/console
Path: frontend/.claude/skills/code-standards/SKILL.md
Commit: 27099a0

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.