Code review team skill for orchestrating comprehensive code reviews using specialized parallel agents
npx claudepluginhub bennettaur/llmenv --plugin code-review-team-coreReview the current branch's code changes for adherence to best practices specific to the detected tech stack. Applies a strict priority hierarchy: codebase conventions first, then framework, then language, then general engineering. Use after code changes, before PR submission.
Review the current branch's code changes for readability, naming conventions, comment quality, abstraction levels, and AI slop detection. Ensures code tells a clear story and is accessible to team members including beginners.
Identify dead code, unused functionality, and cleanup opportunities in the current branch's changes. Finds unused variables, functions, unreachable code paths, commented-out code, and orphaned tests.
Orchestrate comprehensive code review by running specialized review skills in parallel as forked subagents. Use when: (1) User explicitly requests code review, (2) Before creating a pull request, (3) After completing a feature or major implementation, (4) When user indicates they're done with changes and ready to submit/merge. This skill coordinates multiple review subagents (code quality, security, performance, testing, documentation, clarity) to provide thorough feedback.
Review whether project documentation (README, docs/, CHANGELOG) accurately reflects the current branch's code changes. Identifies gaps and suggests updates for business logic changes, API modifications, new features, and behavior changes.
Review the current branch's code changes for LLM integration best practices, prompt security, and AI safety patterns. Covers prompt injection defenses, structured outputs, context management, tool safety, and prompt caching optimization.
Analyze the current branch's code changes for performance optimization opportunities. Identifies N+1 queries, inefficient algorithms, caching opportunities, parallelization candidates, and data structure improvements.
Detect scope drift in the current branch's changes by evaluating whether each change serves the original goal. Classifies changes as Direct, Necessary Consequential, Beneficial but Unrelated, or Unnecessary Drift. Requires the original prompt or plan as context.
Review the current branch's code changes for security vulnerabilities and privacy risks. Covers authentication/authorization flaws, OWASP Top 10, PII logging, data protection, and common injection attacks.
Verify test coverage and quality for the current branch's code changes. Prioritizes integration tests over unit tests, tests behavior not implementation, and minimizes mocking. Identifies coverage gaps and missing test cases.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.