Loading...
Loading...
Found 399 Skills
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.
Guide for implementing Google Gemini API document processing - analyze PDFs with native vision to extract text, images, diagrams, charts, and tables. Use when processing documents, extracting structured data, summarizing PDFs, answering questions about document content, or converting documents to structured formats. (project)
AI-powered comprehensive health analysis system that integrates multi-dimensional health data, identifies abnormal patterns, predicts health risks, and provides personalized recommendations. It supports intelligent Q&A and AI health report generation.
Background knowledge for droid-control workflows -- not invoked directly. Deliverable verification against commitments.
Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design backlogs.
Document Q&A with RAG using Supabase pgvector store.
Help users create custom batch image generation Skills through interactive Q&A. Users don't need to write code; they can generate fully functional image generation Skills just by answering questions. Triggered when users say "Help me create an image generation Skill", "I want to make an image matching Skill", "Create a batch image generation Skill", "How to make an image generation Skill", or "Help me make an AI image generation Skill". Supports any image scenarios such as article illustrations, Logo design, storyboards, social media images, posters, etc.
Provides patterns to build Retrieval-Augmented Generation (RAG) systems for AI applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Quick answers to questions without heavy note-taking overhead
Query any public GitHub repo's documentation via DeepWiki. Use when needing to understand a library, framework, or dependency. Triggers on "look up docs", "how does X work", "deepwiki", "deepwiki".
Design a product-led sales motion from usage signals to sales handoff and conversion.
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.