🎨设计类 MCP / Skill 推荐

Expert Kubernetes specialist mastering container orchestration, cluster management, and cloud-native architectures. Specializes in production-grade deployments, security hardening, and performance optimization with focus on scalability and reliability.

Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.

Migrate vanilla CSS, CSS modules, SCSS, or styled-component styles to Tailwind v4 utilities. Prefer @theme-backed tokens and semantic utilities; document arbitrary values and parity gaps. For audits, load review/workflow.md. Triggers: "CSS to Tailwind", "migrate to Tailwind", "tailwind migration", "styled-components to Tailwind", "SCSS to Tailwind", "review Tailwind classes", "tailwind parity".

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Evidence-first automation inventory and overlap audit workflow for ecc. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.

Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.

Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.

CSS design tokens and color system for vehicle insurance platform. Use when defining colors, spacing, typography, or design variables. Keywords: eye-care colors #5B8DEF/#8B95A5/#C5CAD3, CSS variables, spacing system, color palette, typography scale, design tokens, variables.css, theme colors.

A multi-screen mobile onboarding flow rendered as three phone frames side by side — splash, value-prop, sign-in. Status bar, swipe dots, primary CTA. Use when the brief mentions "mobile onboarding", "iOS onboarding", "phone signup", or "移动端引导".

Use `@tanstack/react-pacer` to debounce/throttle the high-frequency writes that drive an interactive `@tanstack/react-table` v9 table: column filter inputs and column resize state. Pattern: import `useDebouncedCallback` from `@tanstack/react-pacer/debouncer`, wrap your `onChange` writer in it, and keep local input state so typing feels instant. For column resizing, throttle `onColumnResizingChange` so a drag doesn't push 60+ state updates per second. Pacer is the v9 replacement for the hand-rolled `DebouncedInput` setTimeout component from v8 examples.

React Compiler compatibility for `@tanstack/react-table` v9. When you read table state via builder APIs (`column.getIsPinned()`, `row.getIsSelected()`, `cell.getIsAggregated()`, `header.column.getIsSorted()`) inside a nested custom component, React Compiler memoizes the child against the stable `column` / `row` / `cell` reference and never re-runs when the underlying atom changes. Symptom: stale checkboxes, frozen sort indicators, dead pin buttons. Fix: wrap the JSX in `<Subscribe source={table.store} selector={…}>` or `<Subscribe source={table.atoms.X}>` so the dependency is visible to the compiler. Routing keywords: Subscribe, table.Subscribe, React Compiler, stale checkbox, memoized header/cell, builder API.

CSS conventions, layout systems, and modern patterns: predictable styles through low specificity and explicit cascade control. Invoke whenever task involves any interaction with CSS code — writing, reviewing, refactoring, debugging, or understanding stylesheets, SCSS, layout, or responsive design.

Use when writing, editing, refactoring, or debugging tests anywhere under `tests/**` (unit, integration, or end-to-end); authoring NUnit 4 test classes (`*Test`, `*IntegrationTest`); using NSubstitute mocks, AutoFixture with `[AutoMockData]` / `[InlineAutoMockData]` / `[Frozen]`, or AwesomeAssertions (NOT FluentAssertions); working with `CliIntegrationFixture`, `IntegrationTestFixture`, `MockFileSystem`, `TestableLogger`, `NUnitAnsiConsole`, or `New*` factory helpers; adding or updating E2E fixtures under `tests/Recyclarr.Cli.IntegrationTests.E2E/`; editing `Fixtures/recyclarr.yml`, `metadata.json`, `cf/`, `cf-groups/`, or `quality-profiles/` fixture folders; running `Run-E2ETests.ps1` or `scripts/coverage.py`; investigating flaky tests, coverage gaps, or Testcontainers setup. Triggers on phrases like "write a test", "fix this test", "improve coverage", "add an E2E case", "mock this dependency", or any edit to `*.Tests.csproj` or files under `tests/**`.

Template for skills that integrate with an MCP server. Demonstrates the reference file pattern: Claude reads a domain-specific MCP cheatsheet before making any tool calls, reducing query failures caused by server-specific gotchas. Fork this skill and replace the Sentry example with your target MCP.

VERIFY your changes work. Measure CLS, detect theme flicker, test visual stability, check performance. Use BEFORE and AFTER making changes to confirm fixes. Includes ready-to-run scripts: measure-cls.ts, detect-flicker.ts

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

Use the Browserbase CLI (`browse`) for Browserbase Functions and platform API workflows. Use when the user asks to run `browse`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use the top-level `browse` driver commands (`browse open`, `browse get`, etc.) only when the user explicitly wants the CLI path.

Use when building Next.js App Router pages, server and client components, fetching data in server components, configuring layouts and middleware, handling routing patterns, optimizing images and fonts, or deploying a Next.js application.

このスキルを使用して、機能をデプロイ後にブラウザ自動化を使用した自動ビジュアルテストとUI相互作用検証を自動化します。

フロントエンド設計の方向性、美的原則、および一貫した設計言語実装。

Claude Code 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。

評価ファースト実行、分解、コスト対応モデルルーティングを使用してエージェニックエンジニアとして動作します。

並行リポジトリ対応のレビューパスを使用して、スキル、コマンド、ルール、フック、エクストラを DAILY と LIBRARY のバケットに分類することで、特定のリポジトリ向けのエビデンスに基づいた ECC インストール計画を構築します。プロジェクトが完全なバンドルをロードする代わりに実際に必要なものに ECC をトリミングする必要がある場合に使用します。

キャプチャ、診断、封じ込め回復、内省レポートを使用した AI エージェント障害のための構造化された自己デバッグワークフロー。

AI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。

カスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定します

エージェントおよび LLM アプリケーション向けのフルスタック診断。12 層のエージェントスタックにおけるラッパーリグレッション、メモリ汚染、ツール規律の失敗、隠れた修復ループ、レンダリング破損を監査します。重要度順の発見事項とコードファーストの修正を生成します。エージェントアプリケーション、自律ループ、または LLM を活用した機能を構築する開発者に必須です。

アクセシビリティ、レスポンシブネス、テーマ設定、コンポーネント群、トークンを備えた本番環境対応デザインシステムの構築。Figma、Storybook、コンポーネントライブラリ統合。

リソース命名、ステータス コード、ページネーション、フィルタリング、エラー応答、バージョン管理、およびレート制限を含む REST API デザイン パターン。

ターゲット リポジトリの既存統合パターンに正確に一致する新しい API コネクターまたはプロバイダーを構築します。2 番目のアーキテクチャを発明せずに、1 つ以上の統合を追加するときに使用します。

PreToolUse security-anti-pattern hook for Claude Code. Catches 12 common security risks (command injection, XSS, SQL injection, unsafe deserialization, GitHub Actions workflow injection, eval/new Function code injection) BEFORE the Edit/Write/MultiEdit operation completes. Session-state caching prevents duplicate warnings on the same file+rule combo. Stdlib only — no dependencies. Use when you want a safety net during Claude Code sessions that touch security-sensitive code (auth, payments, user input handling, IaC). Disable with ENABLE_SECURITY_REMINDER=0 if you need to perform a verified-safe operation that would otherwise trip a pattern. Triggers — "add security hook", "block unsafe code", "detect command injection before write", "prevent SQL injection patterns", "security warning hook".

后端服务开发。当用户需要开发 API、数据库设计、微服务架构或后端业务逻辑时使用此技能。

后端服务开发专家（通才）。精通多种后端技术栈，能够根据需求选择最合适的技术方案。 当用户需要开发API、数据库设计、微服务架构或后端业务逻辑时使用此技能。 根据用户需求的技术栈，自动切换到对应语言的专家模式： - Python → 查看 python/SKILL.md - Node.js → 查看 nodejs/SKILL.md - Go → 查看 go/SKILL.md - Java → 查看 java/SKILL.md

后端架构模式、API 设计、数据库优化，以及针对 Node.js、Express 和 Next.js API 路由的服务端最佳实践。

Deploy webicached binary to beta.webi.sh. Use when building, uploading, or restarting the cache daemon. Covers cross-compile, conf sync, service management.

Create or modify SQLAlchemy models, queries, and Alembic migrations. Use when: defining new database tables, writing queries, creating migrations, checking model conventions, or understanding the database layer.

Work with the Docker Compose development environment. Use when: starting or stopping services, inspecting logs, opening a shell in a container, resetting the database, or understanding the service topology.

Apply TypeScript style rules that prefer checked literal typing with satisfies and as const satisfies over unsafe assertions. Use when writing or reviewing TypeScript or TSX code, test fixtures, typed object literals, mocks, config objects, or table-driven cases.

Deploy, manage, and debug Kubernetes in production — Deployments, Services, Gateway API, Service Mesh (Istio/Linkerd/Cilium), eBPF observability (Cilium Hubble), security hardening (Pod Security Standards, OPA/Kyverno, seccomp, runtime security with Falco/Tetragon), Helm, HPA, PDB, topology spread, and debugging. Use when user asks to write K8s manifests, deploy to a cluster, debug pods, set up Gateway API, configure autoscaling, or harden cluster security. Do NOT use for Dockerfiles (use docker), CI/CD pipeline design (use ci-cd), or Terraform infrastructure (use terraform).

Use when writing service functions that perform multi-row database writes, bulk updates, reordering, or any operation that must succeed or fail atomically. Triggers on Kysely transactions, sortOrder updates, bulk inserts/updates, multi-table writes, and service functions with array/loop writes.

Evidence-first automation inventory and overlap audit workflow for EGC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

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

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.

Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.