code-quality

MUST be used whenever reviewing a Flows app for code quality, maintainability, or clean code issues — before a PR review, after a feature is complete, or when the user asks for a code review. Do NOT skip linting steps. Triggers: code quality, code review, clean code, refactor, maintainability, technical debt, any type, naming, dead code, duplication, DRY, single responsibility, component size, lint, linting, TypeScript strict, dependency injection, file structure.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable code-review skill with clear sequencing and a lint/type gate up front. Its main weaknesses are tutorial-style prose that pads the context window and a monolithic structure that forgoes progressive disclosure despite its length.

Suggestions

Move the detailed pattern guides (2a–2d TypeScript patterns, naming table, dead-code rules) into reference files under ./references/ and keep SKILL.md as a concise overview with one-level-deep links.

Cut explanatory sentences that restate well-known concepts (e.g. why discriminated unions are good, what branded types are) and keep only the rule plus the executable search/fix commands.

Replace the PowerShell block in Step 8 with the bash/grep idiom used everywhere else so every command runs in the same shell environment.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable commands and code, but it interleaves tutorial-style explanation of concepts Claude already knows (e.g. 'Fewer reachable states = easier code to read and change', 'brand primitives so they can't be mixed up') that could be trimmed.	2 / 3
Actionability	Packed with copy-paste-ready bash/grep commands and concrete TypeScript examples (e.g. `grep -rn --include="*.ts" ... -E ": any\|as any\|<any>" src/`, branded-type and discriminated-union code) that Claude can execute directly.	3 / 3
Workflow Clarity	Ten steps are clearly sequenced with an explicit validation gate in Step 1 ('Fix all errors before proceeding — lint errors are not negotiable'; type errors 'must be fixed') before continuing to manual review, and Step 10 enforces reporting every step.	3 / 3
Progressive Disclosure	It is well organized into labeled sections, but at ~400 lines it is a monolithic single file with no bundle references; detailed material (TS pattern guide, naming table, dead-code rules) that could live in separate reference files is all inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 description: it clearly states purpose and trigger conditions with an extensive natural-term trigger list and a well-scoped niche. The only weakness is that the capability description rests on a single review action rather than enumerating several concrete operations.

Suggestions

Enumerate the concrete review actions the skill performs (e.g. 'runs the linter, flags `any` types, finds duplicate logic, checks component size') instead of relying on the single verb 'reviewing'.

Trim the trigger list slightly or group synonyms (e.g. 'lint/linting', 'duplication/DRY') to reduce redundancy without losing coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('reviewing a Flows app') and several review concerns (code quality, maintainability, clean code), but the action set is essentially a single verb ('reviewing') applied to multiple concerns rather than a list of multiple distinct concrete actions like extract/fill/merge.	2 / 3
Completeness	It states what the skill does (review Flows apps for quality/maintainability) and when to use it ('whenever reviewing ... before a PR review, after a feature is complete, or when the user asks for a code review') plus an explicit Triggers list, satisfying both what and when.	3 / 3
Trigger Term Quality	An explicit 'Triggers:' clause lists many natural terms a user would say — 'code quality, code review, clean code, refactor, maintainability, technical debt, ... lint, linting, TypeScript strict' — giving broad coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The niche is specific to 'Flows app' code-quality review with distinct, domain-tied triggers (CDF/SDK, Flows context), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 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.