⌨️Cursor 必备 MCP 组合推荐

Review UI code for design system compliance, accessibility, and best practices

Deploy Expo apps to production with EAS — build and submit to the iOS App Store, Google Play Store, and TestFlight, configure eas.json build and submit profiles, manage app versions and build numbers, publish App Store metadata and ASO, and deploy web bundles and API routes via EAS...

Use when writing, fixing, or reviewing Python pytest unit tests, fixtures, mocks, or test PR feedback.

Agentic end-to-end testing for LobeHub: backend verification via the CLI, frontend verification via agent-browser (Electron), full-stack verification in the browser, and bot-channel verification via osascript. Local-first today, designed to extend to cloud automation. Triggers on 'cli test', 'test with cli', 'verify with cli', 'backend test with cli', 'local test', 'test in electron', 'test desktop', 'test bot', 'bot test', 'test in discord', 'test in telegram', 'test in slack', 'test in wechat', 'test in weixin', 'test in lark', 'test in feishu', 'test in qq', 'manual test', 'osascript', 'test report', or any local end-to-end verification task.

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines; designpowers personas/accessibility/critique/handoff. Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, premium, luxury, minimal, brutalist, Awwwards, DESIGN.md, mockup, React, Lighthouse, accessibility, WCAG, Core Web Vitals, looks generic, make it pretty, like X brand.

MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and polish. Routes four rulesets: design taste router and brand references; perfection for Playwright/Chromium Lighthouse/Core Web Vitals; ui-ux-db palettes/fonts/guidelines; designpowers personas/accessibility/critique/handoff. Triggers: frontend, UI, UX, design, redesign, styling, layout, animation, motion, premium, luxury, minimal, brutalist, Awwwards, DESIGN.md, mockup, React, Lighthouse, accessibility, WCAG, Core Web Vitals, looks generic, make it pretty, like X brand.

Understand and explore the Omi Flutter mobile app's UI flows, navigation patterns, and widget architecture. Use when developing features, fixing bugs, or verifying changes in app/lib/ Dart files. Provides agent-flutter commands to explore the live app, understand how screens connect, and verify your work.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).

Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when cleaning up legacy code, preparing code for new features by restructuring, or identifying which transformation fits a specific code smell. Covers smell-driven refactoring, safe transformation sequences, and testing guards. For code-quality foundations, see clean-code. For managing complexity, see software-design-philosophy.

Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent design tokens, creating dark mode themes, improving data-visualization clarity, or polishing UI details before launch. Covers grayscale-first workflow, constrained design scales, shadows, and component styling. For typeface selection, see web-typography. For usability audits, see ux-heuristics.

Explain, derive, and debug CSS math for measurement units, calc(), min(), max(), clamp(), custom properties, inheritance, em/rem scaling, percentages, viewport units, and box model formulas. Use when CSS dimensions compute unexpectedly, when mixing units, when building scalable spacing/type systems, or when reviewing box sizing and inherited values.

Derive and debug CSS Grid layout math for grid coordinates, line placement, spans, negative indexes, fr units, minmax(), fit-content(), repeat(), auto-fill, and auto-fit. Use when building grid systems, explaining track sizing, troubleshooting fr distribution, placing items by line numbers, or converting a layout sketch into CSS Grid formulas.

Convert Docker Compose files or installation docs into production-grade Sealos templates. Use when user has a docker-compose.yml and wants a Sealos or Kubernetes template, wants to migrate from Docker Compose to Sealos, needs to convert container orchestration configs to Sealos format, or mentions compose-to-template conversion. Also triggers on "/docker-to-sealos".

Plan a safe, incremental refactor of messy code without changing behavior. Use when code needs restructuring, is hard to change, has grown tangled, or you want to clean it up before adding a feature. Produces a sequenced plan of small behavior-preserving steps, the safety net (tests/characterization) to add first, and the target structure — refactoring as a series of green commits, not a risky big-bang rewrite.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Manage and apply Design app brand systems. Use when creating, importing, linking, inspecting, or following design-system tokens, assets, fonts, logos, and custom instructions.

API design rules for openzeppelin-contracts. Use when adding, modifying, or reviewing any contract under contracts/. Covers virtual, memory vs calldata, public vs external, overloads, no-op vs revert, _update single-override pattern, internal/external split, _msgSender, and override points.

Testing conventions for openzeppelin-contracts. Use when writing or modifying tests, mocks, or formal verification specs. Covers hardhat-exposed $-wrappers, when manual mocks are warranted, Hardhat+Chai patterns (loadFixture, shouldBehaveLike, multi-target loops), Foundry fuzz, Halmos symbolic execution, Certora rule-based verification, and the changeset rule.

TypeScript coding standards — apply when writing, reviewing, or refactoring .ts/.tsx, or naming/renaming .ts files (camelCase casing).

Guide developers through creating and updating MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a MCP app, MCP server or use the Skybridge framework.

Write AND review XML API documentation for SkiaSharp (ECMA/mdoc XML in the docs submodule). Two modes: (1) ADD docs for new APIs with "To be added." placeholders; (2) REVIEW existing docs by scope for accuracy, freshness, examples, and hygiene. Triggers: "document class", "add XML docs", "write XML documentation", "fill in missing docs", "remove To be added placeholders", "review documentation", "check docs for errors", "fix doc issues", "audit the docs", "review the font docs", "are the examples correct", "update out-of-date docs", any request to add, validate, correct, or expand SkiaSharp API documentation.

Use when creating or editing documentation pages in docs/content/guides/ - covers YAML frontmatter, page structure, framework-specific example embedding, writing style, and sidebar registration

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack for a new platform.

Docker containerization expert specializing in multi-stage builds, image optimization, Docker Compose patterns, and production container security. Use for Dockerfile optimization, compose configurations, and container best practices.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.

Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the user's real ~/.codex. The first-party method drives the real `codex app-server` against an isolated CODEX_HOME plus a LOCAL mock model (no real API call), and proves a plugin hook fired by asserting hook/started + hook/completed notifications. Also: isolated install verification, per-component hook probes, a tmux TUI smoke, and runtime log observation (RUST_LOG / logs SQLite / /debug-config). Ships tested helper scripts each with a --self-test. Use whenever someone changes anything under packages/omo-codex or wants to QA, smoke-test, verify, or debug the Codex plugin, its hooks/components, the installer/config.toml, the app-server flow, or the Codex TUI. Triggers: codex qa, qa codex, codex-qa, test codex plugin, verify codex hook, codex app-server, lazycodex qa, isolated CODEX_HOME, prove codex hook fired, codex tui test.

提交或推送前的安全检查，扫描 API Key、访问令牌等敏感信息。

Testing standards for LoongCollector: unit tests, e2e tests, benchmarks. Reference when writing or reviewing tests.

Review a GitHub issue or pull request URL as an openai-agents-python maintainer, with a staged assessment of whether the claim is real, practically important, already solvable with supported functionality, correctly scoped, better served by another design, and worth maintainer and contributor effort. Use when assessing issue validity or severity, deciding whether an issue should be prioritized or closed, determining whether a requested feature represents an unmet need rather than a discoverability or usage gap, judging whether a PR is worth bringing to mergeable quality, comparing open PRs or alternative designs, separating code quality from repository readiness, or drafting a concise maintainer assessment. When closure, additional evidence, or code changes should be requested, also produce a polite, concise, complete, copy-paste-ready maintainer comment.

Design one-off HTML artifacts (landing, deck, prototype).

LobeHub TypeScript style and type-safety guide. Use when editing TS/TSX/MTS, fixing types, choosing interface vs type, avoiding any/object, import type, async flow, or ts-expect-error.

Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.

当需要调查 Cursor 本地模式 debug/log 证据时使用：config.yaml 的 log 热加载、history/<conversationId>/debug JSONL 文件、Bidi 原始/解码记录、RunSSE 记录、runtime/provider debug 记录、debug 文件缺失原因，或解释这些 debug 文件如何生成与如何查询。

Use when debugging Cursor client agent/local-mode/tool/backend-store/provider-replay failures in this repo, especially after the state/context history-store refactor, when triaging installed app bundles read-only, correlating installed-client behavior with repo code, mapping a user-provided id to conversation/request/model-call evidence, replaying provider requests from debug logs, or locating the current client/backend/protocol/log files quickly.

Use when extracting, formatting, refreshing, or investigating a read-only formatted snapshot of the installed Cursor.app bundle under .cursor-app-formatted; includes git-ignore rules, snapshot generation workflow, and the rule to inspect formatted code without patching either the snapshot code or the installed app.

React Native and Expo app patterns — Expo Router navigation, state separation (server/client/route/form), TanStack Query data fetching with Zod, performant lists, NativeWind/StyleSheet styling, native APIs, and secure storage. Use when building or editing React Native / Expo screens, components, navigation, or data layers.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.

Generate or refine complete interactive HTML prototypes in Design. Use when creating screens, variants, Alpine/Tailwind prototypes, tweaks, or visual refinements from a prompt or selected design.

Use Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MCP app.

Internals of tests.cmd execution flow, test discovery, and troubleshooting. Use when debugging test discovery issues or understanding the test runner.

Internals of tests.cmd execution flow, test discovery, and troubleshooting. Use when debugging test discovery issues or understanding the test runner.

Refactor existing prompt artifacts against explicit requirements through the full prompt-builder loop.

TypeScript project conventions: derived types, type placement, acronym casing, imports, generics, factories, and runtime schema patterns. Use when editing `.ts` files, defining exported types, reviewing type names, or organizing type tests.