skills.rest
sheawinkler
sheawinklerCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

inference-sh-cli

Execute and monitor 150+ AI apps from a single CLI.

78|16|Updated Apr 23, 2026
Search Tags:#cli#task-tracking#app-discovery#inference-sh#ai-apps#infsh
One-click install
npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill inference-sh-cli-sheawinkler
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inference-sh-cli
Source: https://github.com/sheawinkler/hermes-agent-ultra/tree/main/optional-skills/devops/cli
Command: npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill inference-sh-cli-sheawinkler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a single CLI to manage and execute 150+ AI apps, reducing context switching and setup time for developers.

Core Features & Use Cases

  • Unified CLI for searching, listing, and running AI apps (infsh).
  • App discovery, sample generation, and task status tracking.
  • Cross-platform support (Linux, macOS, Windows) and authentication via INFSH_API_KEY.

Quick Start

Install the CLI and run your first app with infsh app run falai/flux-dev-lora using a sample input.

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 apps from a single command line interface?▼

You can run 150+ AI apps from a single CLI by installing the inference.sh CLI tool, authenticating with your INFSH_API_KEY environment variable, and executing commands like `infsh app run` to process tasks across local and cloud backends.

How do I discover and search for available AI models in a CLI environment?▼

AI app discovery is handled natively by the CLI, allowing developers to search, list, and sample available applications. You can use the unified `infsh` command surface to browse supported models before generating sample inputs.

Can I use a CLI to track the status of AI generation tasks across cloud backends?▼

Yes, task tracking is a core feature of the CLI workflow. After you run an AI app, the CLI provides a monitoring surface to check the status and results of your tasks across both local and cloud execution environments.

Does the inference.sh CLI support Windows, macOS, and Linux for AI app execution?▼

Yes, the inference.sh CLI provides cross-platform support for Linux, macOS, and Windows. Developers can maintain a consistent command-line workflow for executing and sampling AI apps regardless of their operating system.

How do I authenticate CLI requests to run AI apps on cloud backends?▼

Authentication for CLI requests relies on setting the standard INFSH_API_KEY environment variable. Once configured, this key secures your access to search, run, and monitor AI apps across local and cloud execution environments.

What is the best way to manage input templating and version pinning for AI apps?▼

The best way to manage inputs and versions is using the CLI's built-in support for input templating and version pinning. This ensures consistent, scalable execution when sampling and running 150+ AI apps from your terminal.

Related Skills

Explore More Software Engineering Skills→
DicklesworthstoneDicklesworthstone
70

gcloud

Manage Google Cloud resources via the gcloud CLI.

Community
Advanced
hve4638hve4638

monitor-experiment

Monitor remote experiments via SSH and summarize JSON results.

Community
Advanced
jacardljacardl

inference-sh-cli

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

Community
Intermediate
LynxLabVNLynxLabVN

inference-sh-cli

Run AI applications from the terminal via the inference.sh CLI.

Official
Intermediate