skills.rest
paidethon
paidethonCOMMUNITY
Explore all skills by this author →
GitHub

agent-tools

Execute AI tasks like image generation and web search via inference.sh CLI.

Updated Apr 9, 2026
Search Tags:#image generation#ai#llm#web search#inference.sh#video creation#twitter automation
One-click install
npx skills add https://github.com/paidethon/Daily --skill agent-tools-paidethon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-tools
Source: https://github.com/paidethon/Daily/tree/main/.agents/skills/agent-tools
Command: npx skills add https://github.com/paidethon/Daily --skill agent-tools-paidethon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires inference.sh, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill unit provides access to a suite of AI tools, enabling users to generate images, create videos, interact with LLMs, perform web searches, and automate Twitter actions with a simple CLI.

Core Features & Use Cases

  • AI App Execution: Run over 150 AI apps through the inference.sh CLI.
  • Image Generation: Create images using various AI models.
  • Video Creation: Generate videos from prompts.
  • LLM Interaction: Call LLMs for explanations or text generation.
  • Web Search: Conduct web searches using AI.
  • Twitter Automation: Automate Twitter actions like posting, liking, and following.
  • Use Case: Quickly generate a video of a drone flight over mountains by running the appropriate command in the CLI.

Quick Start

Generate an image using the agent-tools skill by running the command: infsh app run falai/flux-dev-lora --input '{"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 generate images using AI models from the command line?▼

Generate images by running the inference.sh CLI through an AI tool skill, executing commands like `infsh app run` with your desired model and prompt inputs.

Can I automate Twitter actions like posting and liking via a CLI?▼

Yes, Twitter automation is supported via the inference.sh CLI, allowing you to execute automated posting, liking, and following actions directly from your command line.

How do I run LLM interactions and web searches in a terminal environment?▼

Run LLM interactions and web searches by executing the inference.sh CLI, which calls the appropriate AI models and APIs to generate text or retrieve web results.

Do I need the inference.sh CLI installed to create AI videos from prompts?▼

Yes, creating AI videos from prompts requires installing the inference.sh CLI and having access to the appropriate AI models and APIs to execute the generation commands.

What is the best way to execute over 150 AI apps in a local environment?▼

Execute over 150 AI apps by running the inference.sh CLI, which provides a unified command-line interface to interact with various models for video creation, web search, and more.

Related Skills

Explore More Software Engineering Skills→
rafaelcallejarafaelcalleja
2

gemini-cli

Interact with Gemini AI models through a command-line interface.

Community
Intermediate
SeaCloudAISeaCloudAI
1

pixverse_upload_image

Upload an image to PixVerse via SeaCloud CLI and output a reusable img_id.

Official
Intermediate
jongwonyjongwony
4

veo

Generate high-fidelity videos via Veo 3.1 API with text, image, or video input.

Community
Advanced
caoronglincaoronglin
2

modelscope

Access ModelScope AI for text-to-image generation, model search, and inference.

Community
Intermediate