设计与三维建模

Resize, convert, compress, crop, thumbnail and watermark images from your AI chat.

Local video tools for AI agents: contact sheets, transcripts, cuts, loudness and sync checks.

Figma MCP server with full read/write access via plugin bridge — no API token or rate limits.

AI image generation and editing with Google Gemini. Structured JSON editing.

Figma MCP server with full read/write access via plugin — no API token, no rate limits. 73 tools.

MCP server that gives AI agents geometric spatial awareness of web page layouts using Playwright

Phase 2/3 clinical trial design via gsDesign / gsDesign2: sample size, GS boundaries, multiplicity

Korean stock market MCP — DART disclosures + KRX prices, English-first for global LLM analysts.

Generate and edit images with GPT Image 2.5 for $0.029 — free key, 50 credits, no card.

OAuth-protected ImagineVid MCP for image, video, and music generation.

Download, transcribe, and get metadata for any video/audio URL. Managed yt-dlp + speech-to-text.

Build and run visual creative-production workflows from your AI agent.

Create encrypted LIQAA video meetings; read plans, capacity & stats. No install, no account.

AI-agent MCP server for FPGA design: compile, validate & generate Verilog from C⏚ HDL.

Revit model query + APS Design Automation runner.

Twinmotion rendering + video export via Datasmith pipeline.

MCP Server that generate video call url

Open-source DAW your agent runs itself, no AI audio model: compose, mix, hear it as text, play live.

Spring Boot 中的 JPA/Hibernate 模式，涵盖实体设计、关系、查询优化、事务、审计、索引、分页和连接池。适用于设计 JPA 实体或关系，或修复 Hibernate 查询、事务或 N+1 问题。

面向Spring Boot中实体设计、关系、查询优化、事务、审计、索引、分页和连接池的JPA/Hibernate模式。

Spring Boot 中的 JPA/Hibernate 模式，涵盖实体设计、关系、查询优化、事务、审计、索引、分页和连接池。适用于设计 JPA 实体或关系，或修复 Hibernate 查询、事务或 N+1 问题。

面向Spring Boot中实体设计、关系、查询优化、事务、审计、索引、分页和连接池的JPA/Hibernate模式。

Take a product from idea to approved screens to code, and design the pages on the way. Use this skill whenever the user describes a product idea — an app, site, tool or mini program — or asks to add, change or remove a user-facing product feature, even without saying design: it guides a soft, skippable route through feature breakdown and confirmation, then page design on a canvas the user watches and adjusts, then implementation. Use it whenever the user wants to design, mock up, wireframe, redesign or restyle a web page, app screen or mobile screen — landing page, dashboard, settings, pricing, onboarding — or change spacing, colour, typography or layout, or import a .pen file. Also use it for a page editor, a design file, design tokens, or reviewing someone else's design. Prefer it over hand-written markup: the file is validated and the user can adjust it on a canvas without code. For a concrete edit in an existing design, skip the route.

Design engine for AI agents: images at every size, no Chrome, 2× fewer tokens

Catalog MCP for kwnva.design case studies, studio profile, and project inquiries.

Design high-converting landing pages end to end: batched intake, page structure, layout choice, conversion copywriting, SEO/AEO, plus a strict visual token system for type, spacing, radius, motion and states. Use for any marketing page, hero, or product section.

Check whether an npm package, GitHub Action, MCP server or Docker image is dead or abandoned.

Client feedback pinned on live sites, Figma frames, PDFs, images and video, for Claude and agents.

Render LDraw/LEGO models to images with real part geometry via headless Blender + ImportLDraw

Add, update, or review entries in the shared lexicon at ~/.claude/lexicon.md. Run autonomously when a new concept crystallises, a term is used repeatedly with consistent meaning, or an image/metaphor is coined that compresses shared understanding. Also run when user says "add that to the lexicon", "remember that term", or "let's define that".

日本語翻訳：このファイルは liquid-glass-design 用の日本語翻訳が必要です

iOS 26 Liquid Glass设计系统——面向SwiftUI、UIKit和WidgetKit的动态玻璃材质，具有模糊、反射和交互式变形。当在SwiftUI、UIKit或WidgetKit中构建iOS 26 Liquid Glass UI时使用。

iOS 26 液态玻璃设计系统 — 适用于 SwiftUI、UIKit 和 WidgetKit 的动态玻璃材质，具有模糊、反射和交互式变形效果。

iOS 26 Liquid Glass设计系统——面向SwiftUI、UIKit和WidgetKit的动态玻璃材质，具有模糊、反射和交互式变形。当在SwiftUI、UIKit或WidgetKit中构建iOS 26 Liquid Glass UI时使用。

ログ設計の妥当性チェック。一般的なログ基準と日本国内法的要件（電子帳簿保存法・個人情報保護法等）に基づき、ログ設計・実装を検証する。

Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/build/judge skeletons, and runaway prevention; mechanism wiring lives in autonomous-loops. Use when designing, writing, or checking an agent loop. 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。

Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.

当用户要求通过Luma AI API（Dream Machine / Photon）生成图像时使用；以交互方式收集提示词和选项，然后使用捆绑脚本调用API。需要LUMA_API_KEY——若缺失将提示用户。

Local design engine for AI agents: create, edit and export real, editable designs.

应用具体的设计工程细节，让界面更精致。适用于审查或改进 UI 间距、字体、边框、阴影、动效、点击区域、图标、文字换行和交互状态。

应用具体的设计工程细节，让界面更精致。适用于审查或改进 UI 间距、字体、边框、阴影、动效、点击区域、图标、文字换行和交互状态。

Manim Community综合指南——用于以编程方式创建数学动画和教育视频的Python框架。

为技术概念、图表、系统示意图和产品演示构建可复用的Manim讲解视频，如有需要再移交给更广泛的ECC视频工具链。适用于用户想要简洁的动画讲解视频而非通用口播脚本的场景。

构建可复用的Manim解释器，用于技术概念、图表、系统图和产品演示，并在需要时移交给更广泛的ECC视频栈。当用户希望获得清晰的动画解释而非通用的人物讲解脚本时使用。

日本語翻訳：このファイルは manim-video 用の日本語翻訳が必要です

Marketing brand-asset generation (raster images via AI): logo design (55 styles, 30 palettes, 25 industries), corporate identity / CIP mockups (50 deliverables - business card, letterhead, signage, packaging, apparel), banner design (22 styles, social/ads/web/print), SVG icon design (15 styles), social photos (multi-platform), and model-agnostic poster prompts. Default image engine is Codex gpt-image-2 (ChatGPT subscription via `codex login`), attaching the brand logo as a reference image for CIP compositing; falls back to Gemini Nano Banana (GEMINI_API_KEY, same key as omnimedia). Actions: design logo, create CIP / brand identity, generate mockups, design banner, generate icon, create social photos, design poster, social media images. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads. For HTML/web pages, dashboards, and slide decks, use opendesign instead.

使用 7 个精美主题（default、minimal、colorful、dark、gradient、tech、business）创建专业 Marp 幻灯片。用户要求制作幻灯片、演示文稿或 Marp 文档时使用。支持自定义主题、图片布局，并通过自动质量改进处理“让它好看些”等请求。

Deterministic Minecraft pixel-art engine: textures, animation sheets, and pack validation.

MCP server for architecture and system design. Store and manage project architecture locally.

将产品的MCP设计为四个工具（guide、read、write、delete），基于其自身路由，销毁操作由本人确认。适用于任何MCP服务器。