skills.rest
ZardLi1115
ZardLi1115COMMUNITY
Explore all skills by this author →
GitHub

inference-sh-cli

Search app IDs and run cloud AI apps via the infsh CLI.

4|Updated May 18, 2026
Search Tags:#image generation#video generation#inference.sh#ai search#cli automation#json outputs#terminal tool
One-click install
npx skills add https://github.com/ZardLi1115/zedclaw --skill inference-sh-cli-zardli1115
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/ZardLi1115/zedclaw/tree/main/optional-skills/devops/cli
Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill inference-sh-cli-zardli1115

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the burden of managing many separate AI provider APIs by letting you run a wide catalog of cloud AI apps through a single, authenticated CLI.

Core Features & Use Cases

  • Unified AI app execution: Run image, video, search, and other AI apps using the infsh terminal tool.
  • App discovery before running: Search the app catalog to obtain the correct app ID before execution, avoiding broken or outdated names.
  • Structured outputs for media: Use --json and present generated media URLs as MEDIA:<url> for easy viewing.

Quick Start

Tell the AI to generate an image by searching for the right app ID first, then running it with an inline JSON prompt using infsh.

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 multiple AI image and video generation apps without managing separate provider APIs?▼

You can run 150+ cloud AI apps without GPUs by using the inference.sh CLI. It unifies image generation, video generation, and AI search into a single authenticated terminal tool with structured JSON outputs.

What is the correct way to execute AI apps using the inference.sh terminal tool?▼

To execute AI apps using the inference.sh terminal tool, you must first search the app catalog to discover the correct app ID. Then, run the app with an inline JSON prompt and use the --json flag for structured media outputs.

Do I need to install and authenticate the infsh CLI before running cloud AI apps?▼

Yes, running cloud AI apps through the inference.sh CLI requires the infsh CLI installation and authentication. This setup ensures consistent cloud execution for your terminal commands without managing individual provider APIs.

How does the inference.sh CLI handle generated media URLs for easy viewing?▼

The inference.sh CLI handles generated media URLs by using the --json flag for structured outputs. It presents the generated media URLs in the format MEDIA:<url> directly in your terminal for easy viewing.

Why do I need to search for an app ID before running an AI generation task in the terminal?▼

Searching for the app ID before running an AI generation task avoids broken or outdated app names. The inference.sh CLI mandates this app discovery step to ensure you execute the correct cloud application.

Related Skills

Explore More Software Engineering Skills→
MarbleSodasMarbleSodas

inference-sh-cli

Run cloud-based AI apps via the inference.sh CLI with JSON outputs.

Community
Intermediate
KaiserWhoLearnsKaiserWhoLearns

FFmpeg Media Info

Extract duration, resolution, bitrate, codecs, and stream details from media files.

Community
Intermediate
runkidsrunkids
11

skillshare

Synchronize AI CLI skills across multiple targets from a single source.

Community
Intermediate
rhpdsrhpds

01-vertex-setup

Configure Claude Code to use Google Cloud Vertex AI as the backend provider.

Official
Advanced