review▌

Simple, pragmatic, opinionated. Only what matters for writing production-grade python code.

Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement.

You are an expert resume reviewer specializing in Product Management careers. Your role is to provide comprehensive, personalized, and actionable feedback on PM resumes based on industry best practices.

Adversarial code review using opposite-model reviewers to challenge work from distinct critical lenses. \n \n Spawns 1–3 reviewers (Skeptic, Architect, Minimalist) on the opposing model's CLI to avoid same-model bias and ensure genuine adversarial critique \n Reviewers attack based on brain principles and assigned lenses; produces a synthesized verdict without auto-applying changes \n Scales reviewer count by change size: 1 reviewer for <50 lines, 2 for 50–200 lines, 3 for 200+ lines or 5+

Evaluates Next.js App Router code against best practices for Server Components, Client Components, Server Actions, caching strategies, and production-readiness criteria. Produces actionable findings categorized by severity with concrete code examples. Delegates to typescript-software-architect-review agent for architectural analysis.

Structured code review for security, performance, correctness, and maintainability across PR diffs and file changes. \n \n Audits security risks including SQL injection, XSS, CSRF, authentication flaws, and credential exposure \n Identifies performance issues like N+1 queries, memory leaks, algorithmic complexity, and resource leaks \n Checks correctness for edge cases, race conditions, error handling, and type safety gaps \n Works standalone with diffs and file paths; integrates with source con

Expert code review of current git changes with a senior engineer lens. \n \n Detects SOLID violations (SRP, OCP, LSP, ISP, DIP), architecture smells, and proposes incremental refactors with clear rationale \n Scans for security risks including injection, XSS, AuthZ gaps, race conditions, and unsafe deserialization with exploitability assessment \n Identifies removal candidates and unused code with safe deletion vs. deferred plans and concrete follow-up checkpoints \n Flags code quality issues: e

Structured code review framework covering quality, security, performance, and testing standards. \n \n Provides eight-step review methodology: context understanding, high-level architecture assessment, detailed code inspection, security audit, performance analysis, testing validation, documentation check, and constructive feedback delivery \n Covers SOLID principles, naming conventions, error handling, input validation, authentication/authorization, SQL injection and XSS prevention, and resource

最少需要：

Perform comprehensive code reviews of GitLab merge requests, providing actionable feedback on code quality, security, performance, and best practices.