📁文件系统 MCP 推荐

Writes Playwright e2e tests for ComfyUI_frontend. Use when creating, modifying, or debugging browser tests. Triggers on: playwright, e2e test, browser test, spec file.

Sub-skill of automation: Available Skills.

API — Headless CMS — 124 abstractions. Entry, model, and group event handlers and use cases.

api/mailer — 11 abstractions.

API — Tenant Manager — 9 abstractions. Tenant management event handlers and use cases.

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

Write and review XML API documentation following .NET guidelines. Triggers: "document class", "add XML docs", "write XML documentation", "add triple-slash comments", "review documentation quality", "check docs for errors", "fix doc issues", "fill in missing docs", "remove To be added placeholders", API documentation requests.

Class-level workflow for browser automation, API reverse-engineering, macOS UI automation, tmux/interactive CLI control, MCP tool calling, camera capture, and direct tool/API replacement of fragile UI flows. Use when asked to automate websites/apps, learn private site APIs from traffic, drive interactive CLIs, call MCP servers/tools, capture camera frames, or control macOS UI.

Apply subtle gradient-border treatments for premium web surfaces. Use when cards, pricing panels, nav bars, modals, buttons, or hero surfaces need a refined edge highlight without a loud glow.

Design Datadog monitors that catch real production issues without paging on noise. Covers SLO-based monitoring with multi-window multi-burn-rate alerts, the decision between threshold/anomaly/forecast/outlier/composite monitor types, tag-driven routing, downtime windows, monitor template inheritance per service tier, notification message engineering, and runbook linking. Acts as a senior SRE who has owned 4,000+ Datadog monitors and pruned them down to 600 monitors that still catch every real incident. Knows the Datadog billing levers (custom metrics, indexed logs, ingested traces), how `from`/`group_by` interact with no-data evaluation, the difference between simple alerts and multi-alerts, and which monitor types are silently expensive. Use when monitors are paging on cosmetic blips, when a service tier needs a coherent monitor set, when SLOs need turning into burn-rate alerts, or when monitor sprawl is unmanageable. Triggers on "datadog", "datadog monitor", "monitor design", "slo", "burn rate", "anomaly mo

Deploy and operate Node, Python, Go, Rust, Elixir, and Docker apps on Fly.io with production-grade fly.toml authoring, Machines API orchestration, region selection (latency vs sovereignty vs egress), Fly Postgres clustering, LiteFS for SQLite replication, Upstash Redis bindings, Tigris object storage, persistent volumes, WireGuard private networking with 6PN, secrets via flyctl, blue/green deploys via auto-stopping machines, scale-to-zero strategies, scheduled scaling, preview deploys per PR, multi-region replicas, hot-config reload, machine SSH, log shipping to Better Stack/Axiom/Datadog/Logtail, and aggressive cost tuning. Triggers on "fly.io", "flyctl", "fly machines", "fly.toml", "fly postgres", "litefs", "tigris", "upstash on fly", "fly deploy", "migrate from heroku", "migrate from render", "migrate from railway", "scale to zero", "fly regions", "fly volumes", "fly wireguard", "6pn", "fly secrets".

Generates self-contained HTML/CSS animations of app features for walkthroughs, demos, and onboarding. Researches the target app via Chrome, interviews the user, generates a structured brief and animation HTML file, then enters an iterative freeze-inspect-feedback review loop until the user approves. Use when the user says "css animation", "animate this feature", "create a css walkthrough", "animation walkthrough", or wants to create a CSS-based visual demo of an app feature.

Key facts and links for Next.js 16. Use for planning, writing, and troubleshooting Next.js 16 changes.

Analyze Fabric Data Warehouse performance via CLI using sqlcmd and queryinsights views. Diagnose slow queries, SQL pool pressure, cache coldness, and recommend clustering keys. Triggers: "DW slow query analysis", "slowest queries warehouse", "queryinsights long running", "warehouse CPU resource consumers", "SQL pool pressure window", "pressure events warehouse", "DW cache warmth cold start", "cache warmth analysis", "warehouse cluster key recommendation", "cluster tables performance", "DW performance baseline comparison", "performance degraded warehouse", "warehouse user query patterns", "queryinsights diagnostics", "DW optimization sqlcmd".

Run a repeatable RDF4J performance loop against one JMH benchmark in Docker with Linux Java 26 and JFR CPU-time profiling. Use when working in this repo on benchmark-guided performance changes, hotspot triage, JFR reading, CPU bottleneck analysis, or repeated baseline, fix, and rerun loops. Trigger on requests mentioning benchmark, profiling, JFR, hotspot, perf loop, CPU bottleneck, or Docker benchmark runs in RDF4J.

Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.

You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Use when routes, controllers, services, repositories, express middleware, or prisma database access.

You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.

Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker images that accept well-defined JSON input, perform an action, and optionally produce structured JSON output.

TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.

Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Use when writing new React components or Next.js pages, implementing data fetching (client or server-side), or reviewing code for performance issues.

Deploy to Cloudflare Workers, Netlify, Vercel, Node.js/Docker, Bun, Railway. Selective SSR (ssr option per route), SPA mode, static prerendering, ISR with Cache-Control headers, SEO and head management.

Documents how to use Chrome DevTools MCP to navigate authenticated web pages, extract data (tokens, configuration values), take screenshots, and handle login flows. Use when you need to interact with Buildkite, AWS Console, or other authenticated web UIs via the Chrome browser. Triggers when users ask about "browser auth", "extract token from browser", "navigate to buildkite", "chrome mcp", or need to scrape data from authenticated pages.

Use when the user asks to write SQL queries, optimize database performance, generate migrations, explore database schemas, or work with ORMs like Prisma, Drizzle, TypeORM, or SQLAlchemy.

Use when the user asks to create ERD diagrams, normalize database schemas, design table relationships, or plan schema migrations.

Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: create a tour, onboarding tour, architecture tour, PR review tour, explain how X works, vibe check, RCA tour, contributor guide, or any structured code walkthrough request.

Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Use when: user wants to optimize a Dockerfile, create or improve docker-compose configurations, implement multi-stage builds, audit container security, reduce image size, or follow container best practices. Covers build performance, layer caching, secret management, and production-ready container patterns.

Kubernetes expert for cluster ops, manifests, kubectl debugging, RBAC, networking, workloads, storage. Auto-loads when kubectl/k8s mentioned with an action verb. Do NOT trigger on incidental "service"/"pod"/"cluster" or Terraform/Helm-only questions. Keywords kubernetes, kubectl, k8s, deployment, ingress, gateway api, networkpolicy, rbac, kustomize.

Testing patterns for NIC including Go table-driven tests, snapshot tests, and Python integration tests. Use when writing unit tests, snapshot tests, policy tests, template tests, Helm tests, or pytest integration tests for the Ingress Controller.

Skill for writing Dockerfiles based on user requirements.

Automate browser interactions using the Browserbase browse CLI. Use when a task requires navigating websites, reading page state, clicking elements, filling forms, or validating browser results with the browse command.

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

Generate CSS code while strictly avoiding the use of the universal selector (*) to prevent performance issues and unintended style inheritance.

Generates CSS for scalable graphics where the container uses em units and internal elements use percentage dimensions to ensure responsive scaling.

Bring src/mobile-experimental Avalonia/MAUI mobile apps to feature and behavior parity with src/mobile/ios while preserving native platform feel. Use when comparing the Swift iOS app against XerahS.Mobile.Ava, XerahS.Mobile.Maui, or the experimental iOS share extension, implementing parity gaps, or validating Android/iOS experimental mobile flows.

Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief", "ilang brief", "structured brief".

Bring src/mobile/android to feature and behavior parity with src/mobile/ios while keeping each app native. Use when comparing iOS Swift/SwiftUI/UIKit mobile behavior against Android Kotlin/Jetpack Compose behavior, implementing missing Android features, or validating parity with the Test Android Apps emulator QA workflow.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

Vitestテスト設計と品質基準を適用。カバレッジ要件とモック使用ガイドを提供。ユニットテスト作成時に使用。

Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.

Refactor existing code without changing behavior — split oversized files, extract duplicates, simplify over-engineered patterns. Use when files exceed size thresholds, code is duplicated 4+ times, or has speculative abstractions, dead options, or wrapper indirection. Triggers "refactor", "split", "deduplicate", "simplify", "untangle", "clean up". Complements built-in `simplify` (which only reviews recent diffs).

Multi-Cursor orchestration for parallel task execution and AI council deliberation. Use when needing to run multiple Cursor agents in parallel, coordinate complex multi-step coding tasks, get diverse perspectives from different AI models (Opus/Sonnet/GPT) on technical decisions, or synthesize multi-agent discussions into actionable recommendations.

Use Cursor safely across editor, CLI, rules, background agents, Bugbot, and MCP workflows with repo-aware context and reviewable execution.

Testing mastracode TUI features interactively in Konsole. Covers model configuration, thread lifecycle, task state isolation, and common blockers.