qu-skills

Accessing multiple AI models requires juggling different APIs and tools. This skill provides a unified CLI to run 250+ AI apps for image, video, text, and search tasks.

Setting up Python environments with specialized libraries takes time and effort. This skill runs Python code in a remote sandbox with 100+ libraries pre-installed, accessible via a simple CLI command.

Developers waste time integrating multiple AI APIs separately. This skill provides the belt CLI to access 250+ AI models for images, video, LLMs, and search through a single command-line interface.

Running multiple web search and content extraction APIs requires learning different CLIs and SDKs. This skill provides ready-made commands for Tavily and Exa through a single belt CLI, letting Claude complete research tasks in one step.

Browser automation lets AI agents navigate the web without writing Playwright code. The agent-browser skill teaches Claude and Codex to drive a remote Chromium session through the inference.sh belt CLI, capturing screenshots, video, and structured page state.

Posting tweets, managing engagement, and handling DMs on Twitter/X requires constant manual effort. This skill automates these workflows through the belt CLI, letting you schedule posts, like, retweet, and follow users without leaving your AI assistant.

Writing a video renderer in code usually means setting up Remotion, bundling React, and waiting on slow local builds. This skill turns React/Remotion components into MP4 files through a single CLI call, so you can ship motion graphics without touching a build pipeline.

Creating professional AI videos normally requires juggling multiple platforms and APIs. This skill provides a unified interface to generate videos using Veo, Seedance, HappyHorse, Wan, Grok, and 40+ other models through a single CLI.

Creating images with different AI models usually requires switching between many tools and APIs. This skill gives Claude a single CLI workflow to generate, edit, and upscale images across 50+ models including FLUX, GPT-Image-2, and Gemini.

Creating professional AI avatar videos typically requires expensive platforms and complex workflows. This skill enables you to generate talking head videos, UGC content, and multilingual presentations from a simple portrait image using the inference.sh CLI.