Loading...
Loading...
Found 244 Skills
Execute automatic activation for all google vertex ai multimodal operations operations. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Show modal dialogs with showShadDialog, ShadDialog and ShadDialog.alert; title, description, actions, child content. Use when adding modals, confirmations, or alert dialogs in a Flutter shadcn_ui app.
Audit, plan, and safely optimize Shopify image alt text for product media, collection featured images, article featured images, and article inline images. Use when a merchant wants an AI agent to scan Shopify images, test whether the active AI model can inspect images, generate concise alt text with multimodal image understanding when available or context-only fallback when it is not, review the proposed changes in batches, and apply approved Shopify Admin updates.
Expert guidance for writing Python code using the official Google GenAI SDK (google-genai) for Gemini API and Vertex AI. Use for text generation, multimodal inputs, reasoning, tools, and media generation.
Execute Google Gemini CLI for large-context code analysis, multimodal reasoning, and repository-scale reviews. Also use for delegating tasks requiring 1M token context windows or Gemini-specific capabilities.
Recipes and patterns for common Inertia Rails use cases. Includes modal dialogs, shadcn/ui integration, search with filters, wizard flows, and other advanced patterns.
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.
Upgrade any skill to v5 Hybrid format using decision theory + modal logic
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.
Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.
Develop the Stitch SDK. Covers the generation pipeline, dual modality (agent vs SDK), error handling, and Traffic Light (Red-Green-Yellow) implementation workflow. Use when adding features, fixing bugs, or understanding the architecture.
#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.