local-pr-reviewer-setup
Setup and usage guide for local-pr-reviewer - a local PR review tool for AI coding agents. Enables users to review code changes via a web UI and send comments back to their AI coding session.
Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
Setup and usage guide for local-pr-reviewer - a local PR review tool for AI coding agents. Enables users to review code changes via a web UI and send comments back to their AI coding session.
Audits MCP servers for security vulnerabilities, missing validation, error handling issues, and production readiness. Use when reviewing MCP PRs or auditing server quality.
Create an executable plan with steps, dependencies, verification criteria, checkpoints, and rollback strategies. Use when preparing changes, designing workflows, or structuring multi-step operations before exec...
Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, archite...
Containerizes applications with Docker, docker-compose, and Helm charts. Use when creating Dockerfiles, docker-compose configurations, or Helm charts for Kubernetes. Includes Docker Hardened Images (95% fewer C...
Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing proposals, auditing security, stress-testing logic, or validating assumptions.
Execute a validated plan with checkpoints, verification, and rollback capability. Use when implementing changes, applying fixes, running multi-step mutations, or executing approved workflows.
Detect whether a specific world state, environmental condition, or system context exists. Use when checking environment status, validating system state, confirming deployment context, or verifying runtime condi...
MCPツール記述における段階的開示(Progressive Disclosure)パターンのガイド。ツール説明の最適化、コンテキスト効率の向上、LLMトークン消費の削減を目的とします。
iOS debugging expert for troubleshooting and profiling. Use when working with Instruments, Time Profiler, Memory Graph, LLDB, breakpoints, console logging, or performance analysis.
使用 Chrome DevTools MCP 自动浏览官方文档并查找内容。当用户使用 /docs 命令、请求查询官方文档、需要在文档网站中搜索特定API/功能说明、或提到"查一下文档"、"看看官方文档"、"文档中怎么说"时触发。支持任意URL的官方文...
Investigate cluster incidents and issues in isolation. Use for deep debugging, incident response, or when you need focused investigation without polluting main context.
Next.js performance optimization guidelines (Vercel official patterns)
codereview / code review / 代码审查 - Go 代码审查技能,专注于性能、并发安全、安全性和可读性四大核心维度。
Senior Swift/SwiftUI performance expert for code optimization and review. Use when analyzing Swift code for performance issues, hangs, lag, memory leaks, main thread blocking, slow UI, or when the user asks to...
Swift architecture expert for app structure and patterns. Use when working with MVVM, @Observable, ObservableObject, dependency injection, state management, or designing app architecture.
Fast codebase search via WarpGrep (20x faster than grep)
Senior Swift/SwiftUI code reviewer that analyzes feature flows, logic, and code quality. Use when reviewing Swift code, checking if features work correctly, finding bugs, or asking for code improvements. Perfor...
Guidelines for OpenTelemetry instrumentation, observability strategy, and standards.
React + Vite performance optimization and best practices guidelines
iOS accessibility expert for inclusive app design. Use when working with VoiceOver, Dynamic Type, accessibility labels, traits, hints, color contrast, or assistive technologies.
Swift concurrency expert for async programming. Use when working with async/await, actors, Task, TaskGroup, MainActor, Sendable, continuations, or managing concurrent operations.
Question my plan, probe assumptions, find gaps, challenge design. Use when you have a plan that needs scrutiny, want to surface edge cases, or need help finding what you missed.
Guidelines for React Hooks, memoization, and component composition.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.