Loading...
Loading...
Found 8 Skills
Use this skill when a content-complete website has missing/placeholder images and needs visual assets — scenario illustrations, tool screenshots, instructor cards, conceptual diagrams, classroom location maps, QR codes. Triggers on phrases like "插圖", "工具截圖", "QR", "講師卡", "地圖", "示意圖", "Playwright 爬蟲", "AI 生圖", "visual assets", "screenshots", "illustrations", "QR codes", "instructor cards". This skill covers the four asset sources (scraping, AI generation, hand-drawn SVG, generated codes), the PNG-first + SVG-fallback render pattern, and verification scripts. Usually invoked AFTER interactions are wired (so missing images are visible), but can be invoked earlier if assets are pre-planned.
Use when selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics in an editable PPTX deck.
Programmatic visual asset pipeline for proposal-context logos and images. Uses Recraft, OpenAI Image, and Nano Banana Pro together with phase-aware breadth vs convergence.
Generate social media covers and assets for AGENCY Community events, meetups, and YouTube recordings. Use when creating event covers, YouTube thumbnails, or social posts for the AGENCY Community.
Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual references.
Image prompt templates, model selection guidance, and anti-generic patterns for generating visual assets. Use when the user needs AI-generated images for landing pages, marketing, or products. Covers hero images, feature illustrations, OG cards, icons, and backgrounds.
Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets.
Write or modify directly copyable image prompt Markdown for short-drama characters, looks, locations, props, and states. Use when the user mentions character design sheets, three-view drawings, reference images, scene boards, prop sheets, style frames, Look Development, state variants, or partial edit prompts; does not generate images or call vendors.