Loading...
Loading...
Found 312 Skills
Complete guide for Google Gemini API using the CORRECT current SDK (@google/genai v1.27+, NOT the deprecated @google/generative-ai). Covers text generation, multimodal inputs (text + images + video + audio + PDFs), function calling, thinking mode, streaming, and system instructions with accurate 2025 model information (Gemini 2.5 Pro/Flash/Flash-Lite with 1M input tokens, NOT 2M). Use when: integrating Gemini API, implementing multimodal AI applications, using thinking mode for complex reasoning, function calling with parallel execution, streaming responses, deploying to Cloudflare Workers, building chat applications, or encountering SDK deprecation warnings, context window errors, model not found errors, function calling failures, or multimodal format errors. Keywords: gemini api, @google/genai, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, multimodal gemini, thinking mode, google ai, genai sdk, function calling gemini, streaming gemini, gemini vision, gemini video, gemini audio, gemini pdf, system instructions, multi-turn chat, DEPRECATED @google/generative-ai, gemini context window, gemini models 2025, gemini 1m tokens, gemini tool use, parallel function calling, compositional function calling
Builds AI chat interfaces and conversational UI with streaming responses, context management, and multi-modal support. Use when creating ChatGPT-style interfaces, AI assistants, code copilots, or conversational agents. Handles streaming text, token limits, regeneration, feedback loops, tool usage visualization, and AI-specific error patterns. Provides battle-tested components from leading AI products with accessibility and performance built in.
Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
Master metaphysics and ontology - the study of being, existence, and fundamental reality. Use for: existence, being, substance, identity, causation, modality, time, universals. Triggers: 'ontological', 'metaphysical', 'what exists', 'substance', 'essence', 'existence', 'being', 'identity', 'persistence', 'causation', 'modality', 'possible worlds', 'universals', 'particulars', 'properties', 'abstract objects', 'time', 'change', 'composition'.
Invokes Google Gemini models for structured outputs, multi-modal tasks, and Google-specific features. Use when users request Gemini, structured JSON output, Google API integration, or cost-effective parallel processing.
#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.
AnyCap CLI -- capability runtime for AI agents. One CLI for image generation, image read, video analysis, audio analysis, music composition, text-to-speech, web search, web crawling, file download, static site hosting, and cloud file storage. Use when the agent needs to generate images, analyze images, video, or audio, produce audio/music, search or crawl the web, download remote files, deploy static sites, or store and share files. Also use when the agent needs to authenticate with AnyCap (login, API key, credentials), or when encountering errors from AnyCap to submit feedback via 'anycap feedback'. Trigger on mentions of AnyCap, multimodal capabilities, AI-generated media, page hosting, or drive storage.
Use when building features that answer questions from private data, documents, policies, or time-sensitive information — RAG architecture, chunking strategies, hybrid search, re-ranking, vector databases, evaluation, agentic RAG, multimodal RAG...
Semantic and multi-modal search across documents using LanceDB vector embeddings. Use when searching knowledge bases, finding information semantically, ingesting documents for RAG, or performing vector similarity search. Triggers on "search documents", "semantic search", "find in knowledge base", "vector search", "index documents", "LanceDB", or RAG/embedding operations.
Implement Syncfusion Angular Dialog component with complete API coverage. Build modal/modeless dialogs, confirmation popups, forms in dialogs, draggable windows, and overlaid content. Use this skill when users need dialog implementation, positioning, animations, WCAG 2.2 accessibility, forms integration, and event handling.
Apple HIG guidance for presentation components including alerts, action sheets, popovers, sheets, and digit entry views. Use this skill when the user says "should I use an alert or a sheet," "how do I show a confirmation dialog," "when should I use a popover," "my modals are annoying users," or asks about alert design, action sheet, popover, sheet, modal, dialog, digit entry, confirmation dialog, warning dialog, modal presentation, non-modal content, destructive action confirmation, or overlay UI patterns. Cross-references: hig-components-menus, hig-components-controls, hig-components-search, hig-patterns.
Multi-modal ComfyUI skill that generates retro late-1990s / early-2000s anime-style characters, movie frames, images, sounds, and voices using a single, consistent Midjourney-style prompt template.