skills.rest
JKhyro
JKhyroCOMMUNITY
Explore all skills by this author →
GitHub

inference-sh-cli

Manage inference.sh CLI app discovery and execution workflows.

Updated Apr 2, 2026
Search Tags:#automation#authentication#cli#search#image-generation#video-generation#inference.sh
One-click install
npx skills add https://github.com/JKhyro/HERMES-AGENT --skill inference-sh-cli-jkhyro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/JKhyro/HERMES-AGENT/tree/main/optional-skills/devops/cli
Command: npx skills add https://github.com/JKhyro/HERMES-AGENT --skill inference-sh-cli-jkhyro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the guesswork from using inference.sh by helping you authenticate the CLI, discover the right app, and run AI workloads from a terminal-first workflow.

Core Features & Use Cases

  • Search the app catalog before running anything so you always use the correct app ID.
  • Run image generation, video creation, search, text-to-speech, avatar, and social automation tasks from a single CLI.
  • Handle local file uploads, version-pinned app runs, and long-running jobs with task tracking.
  • Use cases include creating a FLUX image, generating a Veo video, or querying an AI search tool without managing separate provider APIs.

Quick Start

Ask me to use the inference.sh CLI to find the right app and run it for your image, video, search, or TTS request.

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 AI image and video generation tasks from the terminal?▼

Terminal AI image and video generation is handled by passing a JSON payload to the inference.sh CLI after discovering the correct app ID, allowing you to execute FLUX image or Veo video workloads locally.

What is the best way to find the correct app ID before running an inference.sh CLI job?▼

The best way to find the correct app ID is to search the inference.sh app catalog directly through the CLI before execution, ensuring you select the right application for your specific AI task.

Can I use local file uploads when running AI apps through the inference.sh CLI?▼

You can use local file uploads with the inference.sh CLI by including them in your execution workflow, allowing the cloud jobs to process your local assets for image generation, video creation, or text-to-speech tasks.

How do I track long-running AI video generation jobs from the command line?▼

Long-running AI video generation jobs are tracked using the task tracking mechanism built into the inference.sh CLI, which monitors cloud job status until the execution completes and returns your output.

Does the inference.sh CLI support text-to-speech and social automation tasks?▼

The inference.sh CLI supports text-to-speech, avatar, social automation, and search tasks by querying the app catalog to find the matching provider, then executing the workload with a version-pinned JSON payload.

Related Skills

Explore More Software Engineering Skills→
SethyPagnaSethyPagna

inference-sh-cli

Run inference.sh AI apps from the terminal with JSON inputs.

Community
Intermediate
fran0220fran0220

asset-gateway

Generate visual, audio, and 3D assets via the asset-gateway CLI.

Community
Intermediate
jacardljacardl

inference-sh-cli

Orchestrate 150+ AI apps from a terminal CLI with JSON inputs and file uploads.

Community
Intermediate
nadicodeainadicodeai

inference-sh-cli

Execute 150+ AI apps in the cloud via a single CLI.

Official
Advanced