デザイン / メディアのスキル — 4 ページ目

Remove image backgrounds via CLI; returns a transparent PNG URL from local files or image URLs.

End-to-end marketing brochure design with a layout-first workflow and mandatory approval before delivery.

Get platform-tuned social-media post designs and copy that match each platform's native specs, safe areas, and engagement style.

Generate production-ready GLB 3D models from text, sketches, photos, or lists — single objects or batches for games, products, and AR/VR.

Generate videos from scripts, URLs, PDFs, or audio using the Visla API.

AI meme generator that researches trends, targets an audience, and produces multiple variations for curated humor output.

Generate a complete podcast episode — multi-voice dialogue, intro/outro music, and a finished MP3 — from a single prompt.

Auto-selects the best dlazy CLI image model from your prompt, then runs the generation command.

Generate Codex-compatible animated pet spritesheets from concepts, brands, or reference art.

Bootstrap, scaffold, and verify WinUI 3 desktop apps using the official Windows App SDK template and bundled setup flow.

Map Figma components to their code counterparts via Code Connect, scanning your codebase to find matching implementations.

Tracks calories, macros, and weight trends from meal photos, text logs, and nutrition labels. Use when the user logs a meal or a drink, keeps a food diary, asks how many calories something has, wants a calorie or protein target for a cut, bulk, deficit, or maintenance, asks for their TDEE or maintenance calories, counts macros or carbs, reads a food label, asks whether to eat back exercise calories or workout burn, or asks why the scale is stuck, why they are not losing weight, or why it jumped overnight. Covers TDEE calibration from the user's own logs, restaurant, alcohol, and cheat-day estimates, plateaus and water weight, smart-scale body-fat readings, GLP-1 and medical guardrails, and eating disorder safety. Not for meal planning or recipes.

Produce a repository-grounded AppSec threat model as a concise Markdown document.

Translates Figma designs into production-ready code with pixel-perfect visual parity, mapped to your project design system.

Generate narration, voiceover, IVR prompts, or accessibility audio from text via the OpenAI Audio API.

Run ffmpeg, sox, and ImageMagick jobs against your files in a fixed-allowlist SSH sandbox.

Generate videos from prompts, images, or frames with automatic model selection.

Summarize YouTube videos into Markdown notes with chapter breakdowns, timestamped transcripts, and key takeaways.

Run ByteDance's Seedance 2.0 Fast video model from the dLazy CLI, using text prompts, reference media, or first/last frames.

Generate Amazon-compliant main, secondary, and A+ images through a stepwise, confirmation-driven workflow.

Generate short video spoken scripts using a fixed 7-step structure with hooks, stories, and a punchline ending.

A two-phase workflow for designing social-media carousels, from intent confirmation to cover-first generation.

Upscale images via a cloud super-resolution API and get back a hosted enhanced image URL.

Generate videos with the PixVerse C1 model from the dLazy CLI.