Expert code reviewer for TypeScript + React 19 applications. Use when reviewing React code, identifying anti-patterns, evaluating state management, or assessing code maintainability. Triggers: code review requests, PR reviews, React architecture evaluation, identifying code smells, TypeScript type safety checks, useEffect abuse detection, state management review.
Generate or refactor Jetpack Compose screens from short specs or existing files, wire Navigation Compose routes/args/deep links, and connect MVVM + UiState + events with previews and strings. Use when adding or updating Compose UI, integrating new screens into NavGraph, or aligning Compose screens with existing theme/resources while preserving behavior.
Load when editing .tsx, .jsx files or working in components/, pages/, store/, hooks/. Provides React, TypeScript, Zustand state management, and WebSocket client patterns.
Review React components using Mantine UI library for accessibility, Styles API correctness, component patterns, and common pitfalls. Use when reviewing Mantine code or before merging Mantine-based PRs.
Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
Auto-detects project language and framework from package.json, pyproject.toml, Cargo.toml, go.mod, and other configuration files with comprehensive pattern matching based on 17,253+ production code examples.
AI outputs YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop. Use when auditability is critical, generated code review needed, or deterministic execution required. YAML serves as intermediate representation. Triggers on "auditable generation", "YAML output", "deterministic execution", "code review", "vibe coding".
State-of-the-art debugging agent with hypothesis-driven analysis, automatic code instrumentation, git worktree isolation, and browser automation. Use when debugging errors, stack traces, unexpected behavior, performance issues, failed tests, race conditions, or hard-to-reproduce bugs.
Create AI-assisted code reviews on GitHub, GitLab, or Forgejo. Use when asked to review a PR/MR, analyze code changes, or provide review feedback.
Dual-AI code validation using both Claude and Google Gemini to catch 20% more issues. Validates React Native screens for security vulnerabilities, performance anti-patterns, accessibility gaps, and best practices. Use when user says "validate with Gemini", "cross-validate", "AI review", or before deploying code to production.
Project conventions for git commits, branch naming, and code style. Use when committing code, creating branches, or reviewing code style.
Perform comprehensive code reviews with actionable feedback. Use when reviewing pull requests, checking code quality, analyzing changes, or when the user mentions "review", "PR", "pull request", "check code", "code quality".
Reviews code changes for bugs, style issues, and best practices. Use when reviewing PRs or checking code quality.
Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-intel.mjs before reading files.
Evaluate how easy it is for new engineers to work in a codebase. Use when assessing code quality, onboarding friction, or technical debt. Triggers on "code quality", "maintainability", "developer experience", "DX review", "onboarding", "cognitive load", "code smell", "refactoring", "tech debt".
John Carmack-level implementation review via RepoPrompt or Codex. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.
Automate detection and removal of duplicate files/functions in TypeScript, JavaScript, and Python projects. Safely refactor imports, validate with tests, and deploy changes with zero risk of breaking the system.
Expert system for identifying deprecated patterns, suggesting refactoring to modern standards (Python 3.12+, ES2024+), checking test coverage, and leveraging AI-powered tools. Proactively applied when users request refactoring, updates, or analysis of legacy codebases.
Apply project coding standards, conventions, and best practices. Activate when writing or reviewing code.
Analyzes code quality, identifies bugs, suggests improvements, and checks adherence to best practices. Use when the user asks for code review, code analysis, quality check, or mentions reviewing code.
Reviews code changes against Zenable conformance requirements using hybrid LLM-as-judge and deterministic validation. Automatically invoked when making code changes or at development milestones. Use for security compliance, quality checks, and policy enforcement.
Systematic code review guidelines and checklist. Use this skill when reviewing code, conducting pull request reviews, or establishing code quality standards. Provides comprehensive review criteria covering functionality, design, testing, security, and documentation. Complements the code-quality agent.
