inference-sh-skills

AI tools cannot access current web information on their own. This skill searches the web using Tavily and Exa APIs through the belt CLI.

Manual posting, liking, and messaging on Twitter and X is slow and hard to scale across many accounts and workflows. This skill lets Claude, Codex, and Claude Code drive the inference.sh belt CLI to post tweets, attach media, like, retweet, send direct messages, follow users, and fetch profiles with simple commands.

Creating MP4 videos from React components requires complex rendering infrastructure that is difficult to set up locally. This skill sends your Remotion TSX code to the inference.sh cloud API and returns a ready-to-use MP4 video file with configurable resolution, FPS, and duration.

Developers need a safe way to run Python code for data processing and automation without local setup. This skill executes Python scripts in a sandboxed environment with 100+ pre-installed libraries via the inference.sh platform.

运行 FLUX、Veo 和 Gemini 等 AI 模型需要强大的硬件和复杂的配置。此技能让你通过简单的 CLI 命令直接从终端访问 250+ AI 应用，无需 GPU。

Creating professional videos from text prompts or images is time-consuming and requires technical skills. This skill provides a simple CLI interface to generate, edit, and enhance AI videos using state-of-the-art models like Google Veo, Seedance 2.0, and HappyHorse directly from Claude Code.

Creating AI-generated images requires accessing multiple APIs with different parameters. This skill provides a unified CLI interface to generate images with GPT-Image-2, FLUX, Gemini, and 50+ other models.

Creating professional talking head videos requires expensive equipment and editing skills. This skill enables you to generate realistic AI avatar videos from a single portrait image and text or audio input using the inference.sh CLI.

运行AI模型需要昂贵的GPU硬件和复杂的设置。本技能提供通过简单CLI即时访问250+ AI模型的功能，无需本地安装。

浏览器自动化工具通常需要复杂的 CSS 选择器和 DOM 解析。该技能让 AI 智能体可以通过 inference.sh 平台使用简单的 @e 元素引用来导航和与网页交互。