Agent skills for Microsoft Copilot

Automate Ignisign tasks via Rube MCP (Composio).

Use when preparing IJCAI or IJCAI-ECAI supplementary material, technical appendices, ZIP files, proofs, derivations, data, source code…

Illustrate, explain, or visualize anything as a single self-contained .html file instead of a wall of markdown, following "The…

Defines medium, mark-making, shapes, texture, and stylization for illustrated or graphic wallpapers.

Installs, troubleshoots, and personalizes the official Tencent IMA skill (a wrapper layer that orchestrates upstream ima-skill, not a…

Synchronizes visual assets with development specifications to ensure implementation matches design intent.

Enhances image clarity and de-blurs photos with configurable quality presets using the Flyelep AI API.

Compresses images to WebP (default) or PNG with automatic tool selection.

Improve image and screenshot quality by enhancing resolution, sharpness, and clarity for professional presentations and documentation.

Generate and edit images using AI. Powered by Nano Banana Pro (Google Gemini image models) with Pollinations.ai and Imagen 4 fallback…

Generate or edit images via Google Gemini (nano-banana-pro) or OpenAI gpt-image-2.

Single-image generation skill for posters, key art, and editorial illustrations.

Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions.

Generate AI video from static images using Kling 3.0, Hailuo, Luma Ray3, Runway Gen-4.5, and 8 other tools.

Generates and edits vector graphics, covers, logos, and UI components programmatically using SVG authoring and ImageMagick rendering.

Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

Multi-perspective academic paper review with dynamic reviewer personas.

Create publication-quality scientific visualizations across physics, biology, chemistry, and climate science.

Image recognition via OpenAI-compatible vision models.

Extract text from an image file (PNG, JPG, etc.) using Tesseract OCR and save the result as a .txt file.