🎨设计类 MCP / Skill 推荐

Docker containers, images, volumes, networks (CLI + Dockerode)

Backend service implementation patterns, standards, and procedures. Use for building REST/GraphQL APIs, implementing CRUD endpoints, database handling, authentication, testing strategies, external service integrations, filtering/pagination (DataGrid), logging, Docker setup, and modular architecture. Applies to Node.js, PHP, .NET, Java, and Go backends.

Kubernetes deployment patterns, Helm charts, and cluster management. Use when deploying applications to K8s, designing workload configurations, implementing scaling strategies, or managing cluster resources.

创建具有高设计品质、可交付生产的前端界面。当用户要求构建 Web 组件、页面、海报或应用（如官网、落地页、仪表盘、React/Vue 组件、HTML/CSS 布局，或对任意 Web UI 进行样式/美化）时使用本技能。产出有创意、打磨到位且避免「AI 通用审美」的代码与界面设计。

Use when testing, debugging, or making targeted improvements to rendered frontend apps through the Build Web Apps or web dev plugin: local dev servers, UI regressions, interaction bugs, console errors, responsive layout, and visual QA. Check whether the Browser plugin is available and use it first when it is; otherwise use regular Playwright with the recorded reason.

Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.

Create and apply CSS gradient borders using a pseudo-element mask (the .border-gradient::before technique), including Tailwind-friendly usage and customization of angle, colors, border thickness, and radius. Use when asked for gradient borders, border glow, or the specific mask-composite border gradient snippet.

Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent".

Use when customer-facing API changes were made — i.e., API report .md files differ from main. Guides through release tag assignment, API Council review requirements, breaking change classification, deprecation process, and changeset guidance. Triggered automatically by ci-readiness-check when api-report diffs are detected.

Build polished, conversion-aware frontends with strong visual taste, clear hierarchy, and production-grade HTML/CSS/JS. Landing pages, dashboards, components, emails, redesigns — all as working files. Avoids generic AI aesthetics. Every design has a point of view.

Get honest design feedback. Upload any visual — UI design, logos, photos, graphics, PDFs — and get prioritized critique: what's broken, what works, what to polish. Theory-backed analysis using 11 frameworks.

Design native macOS apps following Apple's Human Interface Guidelines and Liquid Glass design system. Use when building SwiftUI/AppKit macOS apps, validating designs, or implementing macOS-specific patterns.

Search 78 public scientific, biomedical, materials science, and economic databases via their REST APIs and return structured JSON results. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD, Exoplanet Archive), earth/environment (USGS, NOAA, EPA, OpenWeatherMap), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, DailyMed, ZINC, BindingDB), materials science (Materials Project, COD), biology/genomics (Reactome, BRENDA, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, ChEBI, BioGRID, Gene Ontology, QuickGO, NCBI Protein/Taxonomy, dbSNP, SRA, ENA, gnomAD, UCSC Genome, ENCODE, JASPAR, MouseMine, PRIDE, LINCS L1000, Human Protein Atlas, Human Cell Atlas, RummaGEO, Metabolomics Workbench, EMDB, Addgene), disease/clinical (COSMIC, Open Targets, ClinPGx, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog, Monarch, HPO), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, BEA, BLS, Federal Reserve, World Bank, ECB, US Treasury, Alpha Vantage, Data Com

Fix deployed Rust binaries not reflecting code changes when using docker buildx. Use when: (1) Code changes are verified locally (tests pass) but production behavior doesn't change after deploy, (2) Docker image has a new tag but contains old compiled binary, (3) Dockerfile uses multi-stage build with dependency pre-compilation layer and source copy layer. Docker buildx layer caching can serve stale compilation output even when source files change, especially with cross-compilation (--platform linux/amd64).

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

Manages Docker Hub credentials for the MockServer project. Guides the user through creating a Docker Hub Personal Access Token, validates it, and stores it in AWS Secrets Manager for use by CI pipelines. Use when the user says "docker hub credentials", "docker hub token", "set up docker push", "configure docker hub", "rotate docker token", or needs to store Docker Hub credentials in AWS Secrets Manager.

UI test recipe -- composes browser-record (capture) + browser-replay (verify) so every test produces a replayable RVF artifact, not an ephemeral run

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.

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

Frontend review checklist for OpenAEV React/TypeScript code: component patterns, forms, MUI usage, permissions, i18n, state management, dead code. Use when reviewing PRs or auditing frontend features.

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.

Manage Docker containers, images, volumes, and networks via the Docker CLI and Dockerode API

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 a senior frontend engineer operating under strict architectural and performance standards. Use when creating components or pages, adding new features, or fetching or mutating data.

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.

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.

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.

Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.

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.

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

Generates pure CSS code to animate an image's position on hover (e.g., moving top) without changing its dimensions.

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.

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).

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

Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work. Supports batch commands, network interception, device emulation, per-site profile auth (one-time headed login, headless forever after), and parallel isolated sessions via --session. Workflows: ReviewStories (fan out YAML user stories to parallel UIReviewers), Automate (load/run parameterized recipe templates), Update. Delegates to general-purpose agents with agent-browser instructions for background parallel scraping. Falls back to Interceptor if site has bot detection. USE WHEN headless browser, batch scrape, fast screenshot, dev server test, parallel browser, background automation, extract data, review stories, automate recipe, batch screenshots, scrape multiple pages in parallel. NOT FOR deploy verification or UI confirmation with real Chrome (use Interceptor). NOT FOR simple single-URL fetching (use WebFetch). NOT FOR CAPTCHA or bot-detection bypass (use BrightData or

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtags/videos/comments, YouTube channels/search/comments, Facebook posts/groups/comments, Google Maps business search with contact/review/image extraction, Amazon products/reviews/pricing, and general-purpose multi-page web crawling with custom pageFunction extraction logic. File-based TypeScript wrappers (scrapeInstagramProfile, searchGoogleMaps, scrapeAmazonProduct, scrapeWebsite, etc.) filter and transform data in code before returning to model context, achieving 95-99% token savings over direct MCP protocol. Parallel multi-platform queries via Promise.all for social listening dashboards. Lead enrichment pipeline: Google Maps → qualified filter → optional LinkedIn enrichment. Competitive analysis across Instagram, YouTube, and TikTok simultaneously. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Faceboo

Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work. Supports batch commands, network interception, device emulation, per-site profile auth (one-time headed login, headless forever after), and parallel isolated sessions via --session. Workflows: ReviewStories (fan out YAML user stories to parallel UIReviewers), Automate (load/run parameterized recipe templates), Update. Delegates to general-purpose agents with agent-browser instructions for background parallel scraping. Falls back to Interceptor if site has bot detection. USE WHEN headless browser, batch scrape, fast screenshot, dev server test, parallel browser, background automation, extract data, review stories, automate recipe, batch screenshots, scrape multiple pages in parallel. NOT FOR deploy verification or UI confirmation with real Chrome (use Interceptor). NOT FOR simple single-URL fetching (use WebFetch). NOT FOR CAPTCHA or bot-detection bypass (use BrightData or

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtags/videos/comments, YouTube channels/search/comments, Facebook posts/groups/comments, Google Maps business search with contact/review/image extraction, Amazon products/reviews/pricing, and general-purpose multi-page web crawling with custom pageFunction extraction logic. File-based TypeScript wrappers (scrapeInstagramProfile, searchGoogleMaps, scrapeAmazonProduct, scrapeWebsite, etc.) filter and transform data in code before returning to model context, achieving 95-99% token savings over direct MCP protocol. Parallel multi-platform queries via Promise.all for social listening dashboards. Lead enrichment pipeline: Google Maps → qualified filter → optional LinkedIn enrichment. Competitive analysis across Instagram, YouTube, and TikTok simultaneously. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Faceboo

Design experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or estimating effects on existing data, use performing-causal-analysis instead.

Generate safe, correct SQL scripts for the Rock RMS database. Handles INSERT, UPDATE, DELETE, SELECT queries, data migrations, and seed scripts that respect Rock's schema conventions (PersonAlias, audit columns, FK constraints, DefinedType/DefinedValue lookups, Guid-based references). Use when the user says "create a sql script", "write sql", "insert data", "seed data", "data migration", "update records", "sql for Rock", "populate data", "add test data", "query Rock database", or any request involving direct SQL against the Rock RMS database. Also use when the user describes data they want to add, modify, or query in Rock — even if they don't explicitly say "SQL" — such as "add 100 attendance records", "create a new campus", "give Ted Decker some financial transactions", or "set up check-in data". If the task involves Rock database records and SQL is the right tool, use this skill.

Use when writing paper chapters - requires completed brainstorming, writes one chapter at a time with user confirmation

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Docker and container best practices. Multi-stage builds, security, optimization. Use when creating Dockerfiles.

Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, EXPLAIN/ANALYZE interpretation, before/after query benchmarking, or migrating queries between database dialects (PostgreSQL, MySQL, SQL Server, Oracle).