Design & 3D modeling

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. Use when introducing or refactoring toward Ports and Adapters, or when domain logic has become entangled with I/O.

Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. Use when introducing or refactoring toward Ports and Adapters, or when domain logic has become entangled with I/O.

Best practices for HeyGen - AI avatar video creation API

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

Trace Paperclip runs, requests, and full CI suites in Honeycomb. Use to find traces, diagnose latency, design readable and foldable waterfalls, configure opt-in OpenTelemetry, or add missing spans.

Build one self-contained HTML file — no build step, no dependencies, no CDN — to explain, plan, report, review, diagram, compare, or prototype something a human should read, share, or poke at. Use when the deliverable has color, layout, diagrams, tables, or interaction, or when the user asks for an artifact, explainer, plan write-up, diagram, or design variants. Not for markdown-shaped notes, brand-matching a known site's look, or generative canvas art.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions, propose mechanisms, for scientific inquiry across domains.

Create, edit, design and export Apple Numbers, Keynote and Pages files. Verified and Arabic-safe.

Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.

Turn a self-contained HTML design into an editable Adobe InDesign (.idml) file. Up to 2 pages free.

49 audio tools: trim, convert, normalize, remove vocals, split stems, transcribe, and more.

Human know-how for AI agents: rules, reasons and checks for design, code, product and writing.

Shares Docker build layers and heavy images between cloud sessions through the owner's ghcr.io. Use when a repo's image build is slow on cloud, when a session pulls or pushes ghcr.io images, or when a heavy tool image should be prebuilt once.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Generate and edit images via OpenAI's GPT Image 2.5 API. Use for requests to create, draw, edit, extend, combine, or remove backgrounds from images. Outputs PNG, JPEG, or WebP files to disk and requires OPENAI_API_KEY.

Image URL → plain text OCR for bots. Free try then prepaid TEST. https://ocr.kymac.co

Process images in TS/JS with Bun's Bun.Image API: resize, crop, rotate, compress, convert (JPEG/PNG/WebP/HEIC/AVIF), thumbnails, LQIP/ThumbHash placeholders, EXIF. Replaces sharp on Bun.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Design, critique, polish or overhaul frontend UI: sites, landing pages, dashboards, components, forms, onboarding, empty states. Covers UX review, hierarchy, accessibility, typography, color, motion, design systems. Not backend.

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio.

Reviews a branch, pull request or uncommitted change for the interface problems it introduced or regressed, across accessibility, layout, writing, typography, color and UI.

Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling.

Answer a question about what is on the screen or in a recording; solves text, images and audio.

AI data-center design engine: size, validate & lay out Rubin-era data centers. Korea live.

MCP server for Qwen Image 3 AI image generation

Analyze videos: extract frames, transcribe audio, generate storyboard breakdowns.

Video Editing Ai MCP server. Tools: split scenes, generate subtitles, thumbnail data. Built by MEOK

Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

Let any LLM watch a video locally — and search everything it has ever watched.

Props, examples, design tokens and page blocks for the Halo React design system.

Google Gemini image generation, editing, and local processing via MCP

Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.

Generate design systems: OKLCH colors, fluid type scales, spacing, shape, icon and motion tokens.

Analyze any video (local file or URL) into frames + transcript for Claude Code

An MCP server that converts Figma designs into React code.

InChat Image Viewer MCP - View images inline in AI chat by just providing the file path

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.

Bidirectional Figma MCP — AI draws UI on Figma canvas, reads designs back

Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.

Retrieve existing or generated YouTube transcripts with timestamps through Capslane.

Give AI agents full read & write access to Figma — 50+ tools for design automation

MCP server for context-aware royalty-free image search from Pexels and Unsplash

Animated b-roll overlays for short-form video. Paste a script, get an mp4. Free, MIT, local.

Figma MCP server in Rust: plugin bridge, no API token, no rate limits, 73 tools.

Read Lanhu design specs and export fine-grained UI assets with platform-adjusted units