📁文件系统 MCP 推荐

Where CSS should live. Claude defaults to dumping a giant <style> block or scattering style="..." attributes instead of putting styles in a .css file and linking it. Use when building or editing a web page or component, or whenever about to write a style attribute or an embedded style block. Covers defaulting to an external stylesheet, why inline style attributes are a trap, and the few cases where inline is actually correct (dynamic values via custom properties, critical CSS, single-file artifacts, email).

Production Docker Swarm deployment rules: what changes when a compose file goes from a single node to a multi-node Swarm. Use when writing or reviewing a stack file, a deploy block, an overlay network, or anything deployed with docker stack deploy. Covers the directives Swarm silently ignores, why fixed IPs and bind mounts break, the deploy orchestration block, and the exit-code and healthcheck discipline that Swarm self-healing depends on. Complements the docker skill, which covers writing the image and compose file itself.

Production Docker best practices for writing Dockerfiles, Compose files, and Swarm stacks. Use whenever creating or editing a Dockerfile, a docker-compose / compose.yaml, or a stack file, or building and optimizing an image. Fixes the handful of things Claude reliably gets wrong: multi-stage builds, layer-cache ordering, exec-form ENTRYPOINT for correct signals and exit codes, init:true, keeping secrets and env out of the image, non-root users, and healthchecks. From production, not defaults.

Audit SkiaSharp's native dependencies for security vulnerabilities and CVEs, including Component Governance (CG) alerts from the SkiaSharp-Native and SkiaSharp Azure DevOps pipelines. Read-only investigation that produces a status report with recommendations. Use when user asks to: - Audit security issues or CVEs - Check CVE status across dependencies - Find security-related issues and their PR coverage - Get an overview of open vulnerabilities - See what security work is pending - Check Component Governance alerts - Review CG alerts from the native build pipeline Triggers: "security audit", "audit CVEs", "CVE status", "what security issues are open", "check vulnerability status", "security overview", "what CVEs need fixing", "CG alerts", "component governance", "check container CVEs". This skill is READ-ONLY. To actually fix issues, use the `native-dependency-update` skill.

SQLiteCpp coding standards and API rules for core edits, public headers, style, and Doxygen.

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must match.

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Create, inspect, edit, archive, delete, run, and search scheduled or executable automation assets.

Use when writing, extending, or debugging Vitest unit tests anywhere in the Trilium monorepo — Preact components, jQuery widgets, client services, or the server/trilium-core backend. Covers how to render components (zero new deps), the easy-froca/becca fixtures, supertest API patterns, the honest coverage config, running a single test, and the known gotchas.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Connects Mux mobile (Expo web/native) to an isolated dev-server sandbox with deterministic port setup, backend pairing, and Chrome MCP interaction. Use when implementing or validating mobile features against a sandboxed Mux backend.

Use when building or modifying pages, components, modules, routes, data loading, forms, API integration, or UI features — including small changes like a column, filter, or panel — in the orchestration cluster webapp (webapp/client/apps/orchestration-cluster-webapp/).

Use when writing, modifying, or debugging Playwright tests in the orchestration cluster webapp — integration tests, visual regression, or accessibility tests; MSW mocking, Page Object Models, or axe-core. Test directory: webapp/client/apps/orchestration-cluster-webapp/test/.

Use when migrating, porting, or rewriting frontend code from operate/client/ or tasklist/client/ to the orchestration cluster webapp. Trigger when migrating legacy pages/components, converting React Router to TanStack Router, replacing MobX with TanStack Query, rewriting styled-components as SCSS, converting legacy tests to Vitest browser mode, or asking how a legacy pattern maps to the new app.

Review a Lightning Web Component for **mobile offline** compatibility — the Komaci offline static analyzer that pre-primes the data graph for Salesforce Mobile App Plus and Field Service Mobile App. Produces a finding list with code-level fixes covering inline GraphQL queries in `@wire` configurations, modern `lwc:if` / `lwc:elseif` / `lwc:else` directives, and Komaci ESLint rule violations (private wire properties, non-local reactive references, getter side-effects). Use when the user asks for a "mobile offline review", "Komaci check", "offline priming audit", "offline priming failure", or "offline data graph error", or to validate an LWC against the `@salesforce/eslint-plugin-lwc-graph-analyzer` recommended ruleset. Do not use for generic LWC code review (use an appropriate domain review skill) or for building LWCs with native mobile capabilities (use `mobile-platform-native-capabilities-integrate`).

The entry point for building any Salesforce native mobile app on iOS or Android. TRIGGER when the user says: "build a Salesforce iOS app", "add Salesforce login to my Android app", "set up Mobile SDK", "add MobileSync / SmartStore offline storage", "embed an Agentforce agent in my mobile app", "add Agentforce chat to iOS/Android", or otherwise asks to create, extend, or integrate a Salesforce mobile experience in Swift or Kotlin (MSDK, Agentforce SDK, or both). SKIP when the user is building a non-Salesforce mobile app, using React Native / Flutter / Ionic without Salesforce integration, asking about generic mobile UI design, or working on a Salesforce-adjacent web/desktop surface (LWC, Experience Cloud, Mobile Publisher branding-only).

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.

Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state. Applies to BOTH dashboard-authored and code-first (`@novu/framework`) workflows. Use when planning a new workflow, deciding which channels to include, picking severity, configuring digest behavior, or matching a use case (order confirmation, payment failed, account suspended, comment, trial expiring, password reset, webhook fan-out, fetch-then-notify) to a proven template.

Use this guide when working on TypeScript changes in the FAST monorepo — authoring Web Components, writing templates and styles, working with the observable/reactive system, and testing.

Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when the user wants to convert, port, rewrite, or migrate a browser-use Agent script to Stagehand, map browser-use features/APIs to Stagehand primitives (act/extract/observe/agent), or move agentic browser automation onto Browserbase with more determinism. Triggers on "browser-use", "browser_use", or "Agent(task=...)".

Scraping + AI-provider standards — the Scraper trait & SCRAPERS registry, selector resilience, rate-limiting/cancellation, and the provider-abstraction (zero-change) rule for embeddings/streaming/prompts. Load for changes under scraping/, ai_provider/, packages/prompts, documents/embed.

Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. (gstack)

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)

Refactor macOS SwiftUI views and scenes into stable structure. Use when splitting large views, tightening scene state, or narrowing AppKit escapes.

Use when writing or reviewing Python code with SQLModel, especially models, sessions, queries, FastAPI integration, relationships, link models, creates, updates, and deletes.

Review Cypress E2E spec files for Metabase conventions, common gotchas, and flakiness/performance issues. Use when reviewing pull requests or diffs containing Cypress spec files in e2e/test/scenarios/.

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.

HiMarket backend coding standards for Java and Spring Boot. Use whenever modifying or reviewing himarket-server, himarket-dal, himarket-bootstrap, backend Maven POMs, Flyway SQL, controllers, services, DTOs, repositories, validation, logging, exceptions, or backend tests. Read docs/standards/backend before editing.

Proma 内嵌自动任务与定时任务 Skill，属于 Proma 自带能力而不是用户临时安装的外部 Skill。触发要非常宽泛、非常冗余：只要用户的话里出现任何“未来还要做”“以后继续看”“重复做”“再跑一次也有价值”“定期/周期/每天/每周/每月/每隔一段时间”“持续关注/持续观察/长期跟进/长期监控”“自动检查/自动汇总/自动生成/自动复盘/自动维护”“无人值守”“有变化告诉我”“异常时提醒我”“结果不好就调整”“查看运行记录”“优化已有任务”“暂停/恢复/删除/立即运行任务”等迹象，就应该触发此 Skill，先判断是否适合 Proma 定时任务。也要覆盖一次性与有限次的延时执行信号：“X 小时/天后跑一次”“过一会儿/晚点/稍后自动做”“到某个具体时间点执行一次”“跑几次/连续观察 N 次就停”——这类未来无人值守的延时任务现在同样适合 Proma 定时任务（用 once 或 maxRuns），不要再一概当成不支持。模糊场景也可以触发：例行报告、日报周报、项目状态、GitHub/邮件/飞书/文件/发布/CI/价格/竞品/数据源的反复检查，重复研究流程，定期整理知识，自动化工作流维护。高频触发不代表必须创建任务；纯提醒/闹钟/倒计时、需要用户实时参与判断、或结果没有任何留存价值的事，要明确说明不推荐创建 Proma 定时任务，并给出替代做法。

Deploy Databricks jobs and pipelines with Declarative Automation Bundles. Use when deploying jobs to different environments, managing deployments, or setting up deployment automation. Trigger with phrases like "databricks deploy", "asset bundles", "databricks deployment", "deploy to production", "bundle deploy".

Docker容器化技能，生成Docker配置文件

Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is deployable, query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval` skill).

Résout les problèmes de layout CSS avec Flexbox, Grid et techniques modernes. Se déclenche avec "CSS", "layout", "Flexbox", "Grid", "centrer", "aligner", "responsive", "mon layout est cassé", "overflow", "z-index".

Improve the shape of existing code without changing behavior.

TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.

Running and debugging tests in the Golem workspace. Use when writing tests, running specific tests, filtering tests, debugging test failures, or understanding test infrastructure.

Inspect pod logs, analyze resource quotas, trace network policies, check deployment rollout status, and run cluster health checks for Kubernetes. Use this skill when diagnosing Kubernetes cluster issues, debugging failing pods, investigating network connectivity problems, analyzing resource usage, troubleshooting deployments, or performing cluster health checks.

Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.

Use when semantic refactoring is needed in Rider-supported solutions and projects, including .NET/C#, F#, VB, C++, Unity, Unreal Engine, XAML, Razor, and other GameDev or mixed-language projects. Trigger when edits must update declarations and usages across IDE-resolved references — rename symbols, move types or namespaces, safe-delete unused code, extract interface/base class/method, change signatures, or reorganize namespaces. Do not use for file-only moves, config keys, strings, comments, prose-only edits, generated output, or logic changes with unchanged names/signatures.