发现优质的 AI Agent 技能

Detailed documentation for posting text and images to X.

Publish Markdown articles to X Articles editor with rich text formatting and images.

Posts text, images, videos, and long-form articles to X via real Chrome browser (bypasses anti-bot detection).

> 版本: v2.0 | 最后更新: 2026-02-23

This skill allows you to generate videos using Flyworks (a.k.a HiFly 飞影数字人) Digital Humans. Available features: 1. **Public Avatar Video**: Create video from text or audio using pre-made highly realistic avatars. 2. **Talking Photo**: Create a "talking photo" video from a single image and text/audio. 3. **Voice Cloning**: Clone a voice from an audio sample to use in TTS.

How to use images, video, diagrams, and other visual elements to make your X content more engaging, more memorable, and more human.

Generate videos using SiliconFlow API with Wan2.2 model. Supports both Text-to-Video and Image-to-Video.

Generate images using SiliconFlow API with support for FLUX.1, Stable Diffusion, and more.

Generate vector graphics and raster images using pure SVG code and system conversion tools.

Extract text from scanned documents and image-based PDFs using OCR technology.

Generate images with FLUX models via [inference.sh](https://inference.sh) CLI.

bark-push --user alice --content "会议将在10分钟后开始" bark-push --user alice,bob --content "https://example.com/image.png"