আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
Write blog posts, social media content, and email newsletters. Optimizes for SEO and creates content calendars. Use PROACTIVELY for marketing content or social media posts.
This skill should be used when the user asks to optimize, polish, or improve text content. It provides text optimization capabilities including polishing, humanization (removing AI tone), content expansion, and content condensation. Automatically removes AI patterns after processing.
Generate SEO-optimized blog articles using the Content Factory pipeline
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
AI agent maximizes efficiency and minimizes costs through strategic token usage while maintaining output quality. Use when managing AI interactions, designing prompts, or reducing costs.
Ultra-generic LaTeX BeamerPoster skill. Produces reusable academic posters using XeLaTeX + beamerposter, with full-width TikZ header band, 3-column layout, fixed content height, compact lists, and overflow-safe defaults.
Google Docs document creation and formatting from Markdown. Use when converting Markdown to Google Docs, formatting documents for sharing, or creating professional PM deliverables. Triggers on "Google Docs", "export to Docs", "share document", "format for stakeholders".
Expert tutorial and teaching skill for creating comprehensive, step-by-step explanations. Use when the user asks to explain something, create a tutorial, teach a concept, write documentation, create a guide, or learn something new. Also triggers on phrases like "how do I", "explain", "teach me", "walk me through", "show me how", or "step by step".
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text pr
Generate campaign handouts using Midjourney with Trip 19 moodboard. Know when to use AI generation vs HTML for text-heavy documents.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Write documentation, help articles, specs, and user-facing text in the authentic Grove voice. Use when writing any text that users will read, updating help center content, or drafting specs. Ensures warmth, clarity, and avoidance of AI patterns.
Create publication-quality architecture diagrams using Nano Banana Pro AI or Mermaid. Specialized in system architecture, C4 diagrams, data flow, sequence diagrams, and software design visualizations for project planning.
Generate Android Jetpack Compose UI from Figma using Figma Desktop MCP (get_metadata, get_variable_defs, create_design_system_rules, get_design_context, get_screenshot). Automatically detect icon/vector nodes in Figma, obtain SVG/path data when available, and convert icons to Android VectorDrawable XML using Android MCP Toolkit (convert-svg-to-android-drawable). Use when the user shares a Figma link/node-id and asks to implement UI in Compose from Figma.
Create UI and graphic design layouts in the sunfaded style: oversized condensed typography, bilingual JP/EN type, high-contrast overlays on photo or illustration, halftone wave bands, and analog grain. Use when a user asks for sunfaded-like aesthetics, bold typographic posters, editorial layouts, or UI screens with this specific visual system.
Create and manage Mermaid architecture diagrams with automatic SVG generation
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Suite of tools for creating elaborate, multi-component HTML artifacts for SEA-Forge™ using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
