আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Homeostatic sensor validating all requirements have design coverage. Checks for requirements without components, APIs, or data models. Quality gate before Code stage. Use to ensure design completeness.
Apply professional documentation standards. Use when writing README files, commit messages, code comments, technical docs, or any user-facing text. Enforces evidence-based claims, no marketing language.
Coding style and structural conventions for this codebase.
Comprehensive rules for Go development, covering gRPC, error handling, domain-driven design, logging, and infrastructure configuration. Use these rules when writing, reviewing, or refactoring Go code.
Validates markdown files with YAML frontmatter against JSON Schema definitions.
Standards for identifying, prioritizing, and verifying JavaScript code maintenance and refactoring work
Validates TypeScript/React code against dev_instruction_v3.md standards. Checks for anti-patterns like export default, onClick usage, wrapper components, and any types. Use before committing or during code review.
Use this agent when you have written or modified code and need a comprehensive review for quality, security, and maintainability. This agent should be used proactively after completing any coding task, whether it's implementing new features, fixing bugs, or refactoring existing code
Use for quick self-review of small changes. For comprehensive review or cross-domain changes, dispatch @code-reviewer agent instead.
Java code maintenance standards including prioritization, refactoring triggers, and compliance verification
Review code for Clean Code principles focusing on meaningful variable names, function length, and redundant comments. Use when the user requests code review with /review-code command, asks to check code quality, or wants to ensure code follows Clean Code principles. Supports JavaScript, Python, and Java with language-specific rules.
Enforce high-quality Rust coding standards including toolchain usage, core semantics, API design, and linting rules. This skill should be used when writing, reviewing, or refactoring Rust code to ensure it meets production-grade quality.
Enforce Clean Architecture with strict dependency direction, domain/application/adapter/infrastructure layering, and file/function size limits when the user asks to build a feature, refactor a module, add a full-stack capability, or improve architecture quality. Require a proposed `tree` structure before coding and include a self-review that checks for architectural leaks, boundary violations, and limit compliance after code is produced.
Review code for quality, security, performance, and consistency with team standards. Use when reviewing PRs, preparing code for review, or auditing existing code.
Runme.dev形式の実行可能マークダウン作成・編集用規約。 使用タイミング: (1) マークダウンファイルに実行可能なコードブロックを追加（verify.md, README.mdなど） (2) Runme.devセル設定の追加・編集（name, cwd, excludeFromRunAllなど） (3) runme fmtでフォーマット適用 (4) 既存Runmeファイルの修正・改善
WordPress theme and plugin README auditor that verifies accuracy, removes exaggerated claims, and ensures maintainability. Use when reviewing or updating README files for WordPress projects (themes, child themes, plugins) to ensure all claims are verifiable against the actual codebase and that documentation remains accurate over time.
コードレビューを実施するスキル（SDD仕様書整合性・コーディング規約・セキュリティ・テスト品質）
Analyze and reduce cognitive load in code by identifying complex conditionals, deep nesting, shallow modules, excessive abstractions, and architectural over-engineering. Use when reviewing code quality, refactoring for maintainability, or simplifying systems. Keywords: cognitive load, complexity, refactor, simplify, maintainability, readability, mental overhead, abstraction, architecture review
Assist with automated, safe, and explainable Python refactorings. Detects simple anti-patterns and offers AST-based transformations with patches and unit-test friendly changes.
Generates .prettierrc configuration file for code formatting with Prettier. Defines formatting rules for consistent code style across the project.
