skills.rest
chisuhua
chisuhuaCOMMUNITY
Explore all skills by this author →
GitHub

agent-tools

Run 150+ cloud AI apps for image, video, LLM, search, and Twitter tasks via the inference.sh CLI.

Updated Mar 4, 2026
Search Tags:#cli#image generation#llm#video generation#inference.sh#ai apps#twitter automation
One-click install
npx skills add https://github.com/chisuhua/home --skill agent-tools-chisuhua
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-tools
Source: https://github.com/chisuhua/home/tree/main/.agents/skills.disabled/agent-tools
Command: npx skills add https://github.com/chisuhua/home --skill agent-tools-chisuhua

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Accessing modern AI models like FLUX, Veo, Claude, and Tavily normally requires separate accounts, SDKs, and GPU infrastructure for each provider. This Skill unifies 150+ AI apps behind a single CLI so agents can generate media, call LLMs, search the web, and automate Twitter without managing multiple integrations. ## Core Features & Use Cases - Unified App Execution: Run image generation, video creation, LLM calls, web search, 3D generation, and Twitter automation through one infsh app run command with JSON inputs. - Local File Uploads: Pass local file paths (images, audio, video) directly in inputs and the CLI uploads them automatically for tasks like upscaling, image-to-video, and avatar generation. - Discovery & Task Management: Search and filter apps by category, generate sample inputs, run tasks asynchronously with --no-wait, and poll results via infsh task get. - Use Case: Generate a product image with FLUX, animate it into a video with Veo, then post the result to Twitter, all through sequential CLI commands. ## Quick Start Install the CLI with the curl command from the docs, run infsh login, then ask the agent to generate an image of a cat astronaut using the falai/flux-dev-lora app.

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 models like FLUX or Veo from the command line?▼

Install the inference.sh CLI with curl -fsSL https://cli.inference.sh | sh, run infsh login, then execute infsh app run with the app name and a JSON input, for example infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'.

How to generate images and videos with AI without a GPU?▼

The inference.sh platform runs models in the cloud, so no local GPU is required. Use apps like falai/flux-dev-lora for images or google/veo-3-1-fast for videos, and the CLI returns URLs to the generated files.

Can I use local image or audio files as input to inference.sh apps?▼

Yes, any input field that accepts a URL also accepts a local path, including absolute paths, relative paths, and home directory paths. The CLI automatically uploads the file when running the app.

How do I check the status of a long-running video generation task?▼

Run the app with --no-wait to get a task ID immediately, then poll with infsh task get <task-id>. You can also retrieve results as JSON or save them to a file with the --json and --save flags.

What do I do when infsh returns a not authenticated error?▼

Run infsh login to authenticate through the browser, or set the INFSH_API_KEY environment variable for CI/CD and scripts. The environment variable overrides the stored config file credentials.

Related Skills

Explore More Software Engineering Skills→
gganbukim1gganbukim1

fal-ai-media

Generate AI images, videos, and audio from prompts and source inputs.

Community
Intermediate
michaelboedingmichaelboeding
24

social-producer-agent

Generate and assemble multi-asset social media content packs from prompts.

Community
Advanced
orthogonal-shorthogonal-sh
12

search

Orchestrate web and dataset searches across multiple backends with parallel API calls.

Official
Intermediate
HouseGarofaloHouseGarofalo
3

openrouter

Access and manage over 100 AI models via the OpenRouter API with Python's OpenAI-compatible client.

Official
Intermediate