code-review
Conduct thorough code reviews for pull requests and pre-commit changes
Conduct thorough code reviews for pull requests and pre-commit changes
Programming language guidelines for Dutch government software. Use when choosing programming languages, setting up development environments, or following language-specific best practices for government projects.
Defines project-wide code conventions for magic number elimination, constant usage, performance optimization, and coordinate system separation. Use when implementing, testing, or reviewing code to ensure consistency across the codebase.
Use when reviewing frontend design quality without a reference. Identifies UX issues, accessibility problems, and visual inconsistencies with actionable fix suggestions.
This skill should be used when the user asks about "err113", "wrapcheck", "errorlint", "sentinel errors", "error wrapping", "errors.Is", "errors.As", "dynamic errors", or needs guidance on idiomatic Go error handling. Provides patterns for fixing error-related lint violations.
Harsh code reviewer with functional programming bias. Blocks PRs to teach.
Guide for writing clean, maintainable, professional code. Covers meaningful naming, function design, formatting, error handling, comments, and code smells.
Perform comprehensive code review with quality, security, and performance analysis
Write self-documenting code with clear structure and naming, using minimal but helpful comments only when necessary to explain complex logic. Use this skill across all code files when deciding whether to add comments or how to structure code for clarity. Use when refactoring code to be more self-explanatory, when removing outdated or temporary comments, when writing evergreen informational comments that remain relevant over time, or when choosing between adding a comment versus improving variable/function names. Apply when working with any programming language (.ts, .js, .py, .java, .go, .tsx, .jsx, .vue) to maintain clean, understandable code without over-commenting.
Detects duplicate implementations, SSoT violations, and banned patterns. Use before any code change that adds new logic, config, or constants.
Use this skill to validate that Markdown files are in standard locations. Scans for .md files outside of predefined allowed directories and outputs warnings to prevent documentation sprawl. Triggers include "validate docs", "check markdown locations", or as part of quality checks.
Comprehensive C# code validation, static analysis, and best practices verification for .NET applications. Use when validating C# code, checking SOLID principles, reviewing async/await patterns, verifying nullable reference types usage, checking Entity Framework queries, ensuring security best practices, or reviewing .NET code quality and architecture.
Skills/Rulesの改善提案と更新。同じ指示の繰り返し検出時、新パターン発見時、明示的な「ルール化して」指示時に使用。
Apply Moodle coding standards (PSR-12 with exceptions) to PHP code. Validates style, naming conventions, PHPDoc, and type hints.
Runs production readiness validation checks. Includes TypeScript, linting, tests, coverage, security, and dead code detection.
Review functional area and component documentation to check that it adheres to repo standards.
Performs thorough code review with focus on correctness, security, performance, and maintainability. Provides actionable feedback with specific line references.
Identify and remove unused code, commented blocks, unreachable code, and unused imports. This skill should be used during Phase 1 cleanup tasks to improve codebase maintainability.
Validate CLAUDE.md structure, formatting, and quality. Use when checking context files for compliance, ensuring proper structure, or verifying before commits.
驗證 maihouses 專案的 TypeScript/React 代碼品質,確保符合 CLAUDE.md 的最高規格標準。當修改或審查代碼時自動使用。
Policy สำหรับ enforce code quality ผ่าน linting, testing, และ type checking ใน CI pipeline
Run configuration handling for persistent command configuration storage
Scan a repo using its checked-in Semgrep configuration (local rules only), triage findings, and either fix the most severe issues or open a report-style PR. Use when a repo already has Semgrep config and rules committed; stop if no Semgrep config is present.
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation