Results for “code review”

Builds Flutter apps with guides for everything specific to Flutter and Dart — layouts, responsive UI, forms, animations, theming, declarative routing with go_router, widget previews and home screen widgets; HTTP, JSON serialization, local databases and caching; plugins, platform channels and native views; isolates and app size; accessibility and localization; Effective Dart, Dart 3 features and pattern matching; and macOS setup. Use when writing or changing Flutter UI, data or native integration code, or when the user asks how to do something in Flutter, even if they do not name the topic.

The English summary is being prepared. Showing the original description.

Use this skill whenever the user asks to inspect, audit, review, assess, or evaluate a codebase/project for maintainability, extensibility, architecture, reliability, security, testing, engineering quality, or AI-agent/prompt/tooling risks. Also use this when invoked by `/inspect`. It performs a read-only, evidence-backed, multi-agent project inspection with complete file coverage, per-dimension scoring, blunt technical findings, and explicit degraded-mode disclosure.

The English summary is being prepared. Showing the original description.

3D typography: production-level SDF, Unicode, DOM overlay legibility. Use when implementing, reviewing or testing 3d typography for React, Vite, Next.js or Perfect_AI projects.

The English summary is being prepared. Showing the original description.

建設的なフィードバックを提供し、早期にバグを発見し、チームの士気を維持しながら知識共有を促進する効果的なコードレビュー実践をマスター。プルリクエストのレビュー、レビュー基準の確立、開発者のメンタリング時に使用。

The English summary is being prepared. Showing the original description.

技術記事の品質を「伝説の編集者」の視点で厳格にレビューするためのスキル。記事のドラフトが完成した際、既存記事のブラッシュアップ、または「この記事どうかな？」という漠然とした相談に対しても、このスキルを積極的に使用してください。5つの品質の柱（論理性、実用性、読みやすさ、独自性、明確性）に基づいた厳格な採点と、AI臭さを徹底的に排除した「魂の宿る記事」への改善案を提供します。

The English summary is being prepared. Showing the original description.

Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.

The English summary is being prepared. Showing the original description.

Use for any code, documentation, config, dependency, test, review, or maintenance task in the Nauthilus repository that needs worktree hygiene, the project documentation map, focused reproducer-first debugging, Makefile-driven validation, and evidence-backed closeout.

The English summary is being prepared. Showing the original description.

Use for any code, documentation, config, dependency, test, review, or maintenance task in the Nauthilus repository that must follow AGENTS.md, POLICY.md, focused reproducer-first debugging, strict DRY/OOP boundaries, English comments, GOEXPERIMENT=runtimesecret test discipline, Makefile-driven validation, prompt-sync checks, and dirty-tree preservation.

The English summary is being prepared. Showing the original description.

Review FriendlyBet privacy, RLS security, auth, recovery codes, session storage, data minimization, public snapshots, share surfaces, legal/gambling wording, real-money risk, and compliance-sensitive product changes. Use when a task changes data access, user identity, public sharing, money-like language, security posture, or legal risk.

The English summary is being prepared. Showing the original description.

Review FriendlyBet quality, regression risk, test plans, release readiness, version bump discipline, scoring/locking correctness, provider fallback behavior, and dirty-worktree safety. Use before shipping app code, scoring changes, migrations, sports integrations, copy updates, PWA cache changes, or any risky user-facing flow.

The English summary is being prepared. Showing the original description.

Plan or review FriendlyBet architecture, implementation, schema, data flows, scoring, provider integrations, static/PWA behavior, Supabase/RLS impact, migrations, automation, and technical sequencing. Use when a task asks how to build, refactor, generalize, integrate, test, or safely ship FriendlyBet code.

The English summary is being prepared. Showing the original description.

Orchestrate concurrent analysis or implementation across independent domains. Use when a task can be decomposed into independent workstreams (e.g., via simultaneous tool calls or background processes) — spec writing, code review, security audit, feature implementation.

The English summary is being prepared. Showing the original description.

Structured methodology for adversarial thinking — generating attack scenarios, abuse cases, race conditions, and security edge cases against specs and implementations. Produces spec-level gap items, not code-level fixes.

The English summary is being prepared. Showing the original description.

Type-safe URL query state management with nuqs 2.x. Use when writing or reviewing code that uses useQueryState, useQueryStates, URL search params, query parameters, nuqs parsers, createLoader, createSearchParamsCache, createSerializer, or URL state in Next.js, React, Remix, React Router, or TanStack Router.

The English summary is being prepared. Showing the original description.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

The English summary is being prepared. Showing the original description.

Use when working with Budibase — budibase low-code platform management covering application inventory, table and datasource health, screen layout analysis, automation monitoring, and user role auditing. Use when reviewing internal app configurations, investigating data connectivity issues, monitoring automation runs, or auditing user access controls.

The English summary is being prepared. Showing the original description.

REQUIRED --repo flag for all commands, helper functions for code review comments, suggestion block syntax rules

The English summary is being prepared. Showing the original description.

Use when working with Aws Cdk — aWS CDK infrastructure-as-code management. Covers synth, diff, deploy, bootstrap, context values, construct inspection, and stack dependencies. Use when managing CDK applications, reviewing synthesized templates, comparing deployments, or debugging construct issues.

The English summary is being prepared. Showing the original description.

Use when working with Appsmith — appsmith low-code platform management covering application inventory, workspace organization, datasource health, page and widget analysis, and user access auditing. Use when reviewing internal tool configurations, investigating datasource connectivity, monitoring application deployments, or auditing workspace permissions.

The English summary is being prepared. Showing the original description.

REQUIRED helper functions (never raw curl), workspace/repo_slug patterns, suggestion block syntax for code review

The English summary is being prepared. Showing the original description.

Use when working with Snyk — snyk security scanning and vulnerability analysis. Covers dependency vulnerability scanning, container image scanning, IaC security scanning, code analysis, license compliance, and fix recommendations. Use when scanning for vulnerabilities, analyzing dependency risks, reviewing container security, or auditing IaC configurations.

The English summary is being prepared. Showing the original description.

Use when working with Checkov — checkov infrastructure-as-code security scanning. Covers Terraform, CloudFormation, Kubernetes, and Dockerfile scanning, policy management, custom checks, compliance frameworks, and suppression management. Use when scanning IaC for security misconfigurations, evaluating compliance, managing custom policies, or reviewing scan results.

The English summary is being prepared. Showing the original description.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

The English summary is being prepared. Showing the original description.

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

The English summary is being prepared. Showing the original description.