skills.rest
ruiyangruiyi
ruiyangruiyiCOMMUNITY
Explore all skills by this author →
GitHub

inference-sh-cli

Run cloud-hosted AI apps via the inference.sh CLI and return media URLs.

Updated May 26, 2026
Search Tags:#cli#image generation#video generation#inference.sh#cloud ai#terminal tool#tavily search
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill inference-sh-cli-ruiyangruiyi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/optional-skills/devops/cli
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill inference-sh-cli-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you run many AI image, video, search, and 3D applications in the cloud without managing individual providers or GPUs.

Core Features & Use Cases

  • Centralized app execution with a single CLI: Uses the inference.sh command-line tool (infsh) to run AI apps by app ID.
  • Safe app discovery workflow: Searches first to find the correct app ID, avoiding brittle guesses when app names change.
  • Media and structured outputs: Runs apps with machine-readable JSON and returns generated media URLs for user presentation.

Quick Start

Ask the AI to run an image app by first searching for the right FLUX or video model, then executing the selected app with your prompt using infsh --json and returning the MEDIA: URLs.

Frequently Asked Questions about inference-sh-cli

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

FAQPage Schema
How do I run cloud AI image and video generation without a local GPU?▼

You can run cloud AI image and video generation without a local GPU by using the inference.sh CLI to execute provider-backed models via app IDs, returning structured JSON output with direct media URLs.

What is the best way to discover AI app IDs for terminal-based generation tasks?▼

The best way to discover AI app IDs for terminal-based generation tasks is to use the infsh search workflow first, which prevents brittle guesses and ensures you execute the correct cloud-hosted app with your input JSON.

Does the inference.sh CLI require local hardware setup for running large AI models?▼

No, the inference.sh CLI does not require local hardware setup for running large AI models. It manages cloud-hosted providers directly, allowing you to access many AI apps and generate media without GPU dependencies.

How do I pass input data to cloud AI apps using the infsh terminal tool?▼

You pass input data to cloud AI apps using the infsh terminal tool by running the command `infsh app run` with the `--input` JSON parameter, then parsing the structured `--json` output to retrieve your generated media URLs.

Can I use inference.sh for research and search tasks in addition to media generation?▼

Yes, you can use inference.sh for research and search tasks in addition to media generation. The CLI supports running cloud-hosted apps across categories like image, video, and research, including Tavily search integrations.

Related Skills

Explore More Software Engineering Skills→
HarriesHarries

inference-sh-cli

Run 150+ AI apps via the infsh CLI with JSON output.

Community
Intermediate
williamsforealwilliamsforeal
1

s3-uploader

Upload images or videos to S3/R2 and return canonical URLs for Airtable attachment fields.

Community
Basic
devMoezdevMoez
1

inference-sh-cli

Run cloud-hosted AI apps for media generation and search via the infsh CLI.

Community
Intermediate
matthew-johnsonmatthew-johnson

heartmula

Generate music from lyrics and tags using HeartMuLa models.

Community
Advanced