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

86%

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

Quality

Content

77%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 content is highly actionable and well-sequenced with strong validation checkpoints, but it is long and inlines substantial reference material (grep recipes, naming tables, code patterns) that could be offloaded to bundle files for better token efficiency. Splitting detailed lookup material into references/ would improve progressive disclosure.

Suggestions

Move the reusable grep/node one-liners and the naming-convention table into a references/ file (e.g. references/checks.md) and link to it, keeping SKILL.md as a lean overview-plus-checklist.

Trim explanatory prose that re-teaches known concepts (e.g. the rationale for branded types, discriminated unions, and DI) down to a one-line 'why' since Claude already knows these patterns.

Note Step 8 mixes PowerShell and bash blocks inconsistently; standardize on one shell or split platform-specific scripts into separate reference files to avoid confusion.

Dimension	Reasoning	Score
Conciseness	The body is densely packed with executable grep/node commands and code examples that earn their place, but it also re-explains concepts Claude already knows (e.g., 'Fewer reachable states = easier code to read and change', explanatory prose around branded types, DI rationale) that could be trimmed.	3 / 5
Actionability	Every step provides copy-paste-ready bash/grep/node commands plus concrete TypeScript before/after code examples covering the common cases, making the guidance fully executable.	5 / 5
Workflow Clarity	A clearly ordered 10-step sequence with an explicit validation checkpoint (lint + tsc in Step 1 must pass before proceeding) and a hard-gate feedback rule for dead code, plus a structured report template; error-recovery guidance is present throughout.	5 / 5
Progressive Disclosure	The skill has no references/ or scripts/ bundle and inlines all detailed material (grep recipes, code samples, naming tables) into one ~330-line SKILL.md with no one-level-deep references, so structure exists but content that could be split is inline and navigation is single-file only.	3 / 5
	Total	16 / 20 Passed

Description

96%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 is comprehensive, explicit, and trigger-rich, clearly stating both what the skill does and when to use it with concrete timing and keywords. Minor overlap risk exists with generic code-review skills, but the Flows-app scoping keeps it largely distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—linting, type-safety, component size, DRY, dependency injection, naming, dead code—and specific sub-techniques (branded types, discriminated unions), giving comprehensive coverage.	5 / 5
Completeness	Clearly states what (reviewing a Flows app for code quality/maintainability/clean code issues) and when with concrete trigger phrases and timing ('before a PR review, after a feature is complete, or when the user asks for a code review').	5 / 5
Trigger Term Quality	Extensive natural keyword coverage including synonyms and acronyms users say: 'code review', 'clean code', 'refactor', 'technical debt', 'DRY', 'lint', 'TypeScript strict', 'dead code', 'naming', 'duplication', 'single responsibility'.	5 / 5
Distinctiveness Conflict Risk	Scoped to a Flows app code-quality review with distinct triggers, but 'code review', 'refactor', 'maintainability' overlap with general code-review skills; niche is mostly distinct with minor overlap risk.	4 / 5
	Total	19 / 20 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
Path: skills/code-quality/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.