{
  "markdown": "# Nano Banana Skills\n\nThis project is a collection of AI agent skills designed for **Nano Banana**, focusing on advanced image generation capabilities.\n\n## How to use this agent skills in Gemini App\n\n1. Create a `gem` in the Gemini app.\n2. Add this repository URL as `Knowledge`: `https://github.com/ShinChven/nano-banana-skills.git`.\n3. **Say the name** of the skill to use it.\n\n## Project Structure\n\n- **`skills/`**: This directory contains the individual agent skills. Each skill is a self-contained folder with its own instructions and scripts.\n- **`GEMINI.md`**: The comprehensive guide for creating and structuring new skills for this project.\n\n## Available Skills\n\n| Name | Description |\n| :--- | :--- |\n| [anime-to-life](skills/anime-to-life/SKILL.md) | Transforms anime, art, or 3D rendering images into photorealistic cosplay-style photographs using a specific JSON-based prompt structure. |\n| [character-reference-sheet](skills/character-reference-sheet/SKILL.md) | Generates a 3:2 aspect ratio character reference sheet with three columns: detailed portrait, full-body front view, and full-body back view, mirroring the exact style and material details of the source. |\n| [figure-to-life](skills/figure-to-life/SKILL.md) | Converts figure photos to photorealistic human cosplayer images using a strict JSON-based reasoning mandate. |\n| [imax-portrait](skills/imax-portrait/SKILL.md) | Expands and recomposes images into an IMAX 70mm portrait style (1.43:1 aspect ratio) with high-fidelity Christopher Nolan-esque aesthetics. |\n| [j-cover](skills/j-cover/SKILL.md) | Analyzes and reconstructs J-Media and Gravure cover designs using a 4-axis structural layering approach. |\n| [j-idol](skills/j-idol/SKILL.md) | Adapts fictional characters into high-fidelity, photorealistic human portraits in the style of J-Idol and Gravure magazine covers. |\n| [j-poses](skills/j-poses/SKILL.md) | A library of Japanese style photography poses. |\n| [photo-restoration](skills/photo-restoration/SKILL.md) | Restores vintage and blurry photos to high-definition 8k images while preserving identity. |\n| [real-mecha](skills/real-mecha/SKILL.md) | Converts 2D/anime mecha art into photorealistic 3D/real-world visualizations with high-fidelity material textures. |\n\n## Contributing\n\nTo create a new skill for this project, please refer to the [GEMINI.md](GEMINI.md) guide. It outlines the required directory structure, `SKILL.md` format, and drafting rules.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
  "bytes": 2557,
  "sha": "d12ed9dece4009e9da727af8f11fafefde7a65c3f6aa239b56ecb5b745d304d7",
  "repo_slug": "shinchven/nano-banana-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_shinchven_nano_banana_skills_8308ac20/readme"
}