agent-tools

Run image, video, text, search, 3D, and social media tasks via the inference.sh CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/paulovictor237/PeveAgent --skill agent-tools-paulovictor237
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-tools
Source: https://github.com/paulovictor237/PeveAgent/tree/main/.agents/skills/agent-tools
Command: npx skills add https://github.com/paulovictor237/PeveAgent --skill agent-tools-paulovictor237

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Many creators and developers need fast access to a wide range of AI capabilities—image generation, video creation, language models, web search, 3D rendering, and social media automation—without installing and managing separate tools or GPU hardware.

Core Features & Use Cases

  • Unified CLI: Leverages the inference.sh command line to execute over 250 AI apps across categories such as image, video, LLM, search, 3D, and Twitter automation.
  • Model Flexibility: Supports models like FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter and many more.
  • Simple Installation: Single script installs the CLI and sets up authentication, enabling immediate use.
  • Use Cases: Generate high‑quality images for marketing, create video content for social media, run LLM queries for research, perform web searches, or automate tweets—all from one command interface.

Quick Start

Ask the skill to generate an image of a cat astronaut using inference.sh with the prompt “a cat astronaut”.

Frequently Asked Questions about agent-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run AI image generation and LLM queries without a local GPU?

AI image generation and LLM queries can run without a local GPU by using the inference.sh CLI to execute cloud-based AI apps, retrieving results directly over a network connection.

Can I automate Twitter posts and web searches from a single command line interface?

Yes, you can automate Twitter posts and perform web searches from a single CLI by using inference.sh to invoke supported models like Tavily, Exa, and Twitter automation apps.

What do I need to install to start generating video content via command line?

To start generating video content via command line, you need to install the inference.sh CLI using its single setup script and ensure you have network access to inference.sh services.

Does inference.sh support models like FLUX and Veo for video creation and image generation?

Yes, inference.sh supports models like FLUX for image generation and Veo for video creation, alongside other models like Gemini, Claude, and Seedance for various AI tasks.

What is the best way to access multiple AI models for 3D rendering and text generation?

The best way to access multiple AI models for 3D rendering and text generation is through a unified CLI like inference.sh, which runs over 250 cloud-based AI apps without local hardware.

Are there limitations to running social media automation tasks via a cloud-based CLI?

Running social media automation tasks via a cloud-based CLI requires continuous network access to inference.sh services, meaning tasks will fail if the connection drops or authentication expires.