发现优质的 AI Agent 技能

bot_token = "YOUR_BOT_TOKEN" chat_id = "YOUR_CHAT_ID" photo_path = "path/to/image.png" url = f"https://api.telegram.org/bot{bot_token}/sendPhoto" files = {"photo": open(photo_path, "rb")}

**For Humans**: This skill transforms a rough image request into a production-grade result through a controlled 8-stage pipeline. It asks guided questions, formalizes your intent into machine-readable constraints, generates via Nano Banana Pro, and uses a separate Gemini instance to critique the result — never the same model that generated. Each iteration regenerates from scratch. No artifact stacking. No silent loops. You confirm every stage.

Generate a handful of “random but structured” prompts and render them via OpenAI Images API.

Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image).

Use the bundled script to generate or edit images.

Generate an image of a whimsical, fairytale-inspired floral · arch with pastel-colored flowers and delicate ivy.

千问-图像翻译模型（Qwen-MT-Image）可精准翻译图像中的文字，并保留原始排版。

> 🔄 **同步更新**：本项目在 [GitHub](https://github.com/StanleyChanH/aliyun-image-skill) 和 [ClawHub](https://clawhub.com/skill/aliyun-image) 同步发布。

A skill that automatically finds and moves loose images/attachments from your Obsidian vault root to the designated Attachments folder.

Generate images using ChatGPT's DALL-E integration through OpenClaw browser automation.

SociClaw is an AI agent dedicated to managing social media accounts autonomously. Drafts can be synced to Trello/Notion, and images are optional via a configured SociClaw Image API.

Convert bedtime stories, narrations, or any spoken content into engaging YouTube Shorts videos with: - **Synced subtitles** - Words highlighted in real-time as spoken - **Dynamic backgrounds** - Images searched and selected based on story content/section - **YouTube Shorts format** - 9:16 portrait video optimized for mobile - **Professional styling** - Centered, animated subtitle effects