670 skills · sorted by relevance
Plan and improve popups and banners for email signups, purchases, and announcements. The skill helps define display timing, audiences, copy, and frequency, with mobile design guidance and comparison tests to evaluate changes.
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
Helps adapt LLMs to specific tasks with LLaMA-Factory, including training through a web interface and memory-saving methods such as QLoRA. Provides documentation references for learning features, implementing workflows, and investigating code problems.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.
Build LlamaIndex applications that retrieve relevant material before generating answers, a method called RAG. Connect documents, websites, and databases to support document questions, conversational search, structured summaries, and checks of answer relevance and source consistency.
Turn a feature into an agent skill or improve an existing one. Define purpose-specific quality criteria, review outputs with models from three providers, then add tests and check that user requests reach the intended skill.
Audit instructions and memory files loaded on every agent turn. Identify repeated rules, contradictions, outdated content, and material better moved into skills, then receive evidence-backed recommendations ranked by estimated token savings and change risk.
Analyze single-cell data with scvi-tools, using deep learning to combine datasets, correct differences between experiments, and transfer cell labels. Model guides and reusable scripts cover RNA, protein, chromatin accessibility, spatial data, and downstream analysis.
Design and improve in-app screens that invite users to paid plans. Develop complete screen copy, prompt timing rules, upgrade flows, and experiment ideas based on the value users have already experienced.
Plan popups that encourage email signups, purchases, or inquiries. Define when they appear, who sees them, how often they repeat, and what they say, with mobile adjustments, overlap rules, and ideas for comparing alternatives.
Design Google Cloud systems where multiple AI agents process live audio, video, or text and respond in real time. Guides requirements discovery, architecture diagrams, infrastructure code, deployment instructions, and validation for technical guidance or safety monitoring workloads.
Guides building AI applications that search documents before answering questions, an approach called RAG. Covers importing files and web data, creating searchable indexes, adding conversational interfaces, and evaluating whether answers match the retrieved material.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill guides model selection, batch processing, and memory optimization, with examples for understanding images without training for each specific task.
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
Guides LLM fine-tuning with Axolotl, from YAML configuration and dataset formats to distributed training across GPUs. Covers LoRA and QLoRA, methods that train on preferences, multimodal support, and troubleshooting using documentation references and code examples.
Build or update Figma pages, dialogs, and panels from code or descriptions. The workflow reuses design system components, shared colors, spacing, and text styles, producing assembled views that remain linked to existing design resources.
Apply layered, neutral shadows to cards, form controls, panels, and larger containers using Tailwind classes with custom values. Three prescribed shadow strengths help match visual depth to the size and purpose of each component.
Build Apple-inspired translucent interfaces using shared CSS settings and component patterns. The skill covers glass cards, toolbars, buttons, and modals, with light and dark modes, motion guidance, and accessibility requirements for readable text and reduced animation.
Builds frosted-glass interface components using translucent backgrounds, background blur, subtle borders, and soft shadows. Provides shared CSS settings and examples for consistent cards, navigation bars, modals, and buttons, with guidance on readability and browser support.
Learn from top Kaggle solutions across text, images, time series, tabular data, and multimodal tasks that combine data types. Explore technical analyses, model settings, reusable code templates, and practical lessons to inform machine learning projects.
Learn from top Kaggle solutions across text, images, time series, tabular data, and multimodal tasks that combine data types. Explore technical analyses, model settings, reusable code templates, and practical lessons to inform machine learning projects.
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
The English summary is being prepared. Showing the original description.
Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video. Triggers: "azure-ai-contentunderstanding", "ContentUnderstandingClient", "multimodal analysis", "document extraction", "video analysis", "audio transcription".
The English summary is being prepared. Showing the original description.
Multi-Omics Factor Analysis (MOFA2) for unsupervised integration of multiple data modalities. Identifies shared and view-specific sources of variation. Use when integrating RNA-seq, proteomics, methylation, or other omics to discover latent factors driving biological variation across modalities.
The English summary is being prepared. Showing the original description.