Browse reusable Agent Skills, each with a clear purpose and practical guidance.
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Extract unique garments from outfit or model photos, reconstruct clean transparent clothing cutouts, generate identity-preserving modeled editorial photos, and import approved items directly into this Wardrobe project's local JSON database. Use when a user asks Codex to add, ingest, extract, or import clothes from a folder of photos into Wardrobe, wants modeled photos for imported pieces, or wants finished wardrobe PNGs without using the in-app OpenAI import flow.
Use when generating short videos with RedBox official video API. Produces a detailed shot script first, asks the user to confirm it, then chooses between text-to-video, reference-guided, and first-last-frame modes and calls the correct wan2.7 video model with prompt discipline focused on motion, reference elements, and transitions.
Source or generate Beutl-ready photos, footage, audio, and fonts with license and provenance discipline.