skills.rest
vlm-run
vlm-runOFFICIAL
Explore all skills by this author →
Website𝕏@vlmrunGitHub

vlmrun-cli-skill

Orchestrate visual AI tasks from the CLI against the Orion agent.

16|Updated Jan 16, 2026
Search Tags:#image#cli#video#document#visual-ai#vlmrun#orion
One-click install
npx skills add https://github.com/vlm-run/skills --skill vlmrun-cli-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vlmrun-cli-skill
Source: https://github.com/vlm-run/skills/tree/main/skills/vlmrun-cli-skill
Command: npx skills add https://github.com/vlm-run/skills --skill vlmrun-cli-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables developers and operators to control the Orion visual AI agent from the command line, transforming natural-language prompts into media analysis, generation, and extraction tasks without a GUI.

Core Features & Use Cases

  • CLI chat with the Orion agent to perform image understanding, object detection, OCR, video summarization, and document extraction
  • Supports image, video, and document inputs with flexible prompts and toolsets
  • Quick experimentation and automation by combining prompts with inline skills and model options

Quick Start

Run vlmrun chat "Describe this image" -i photo.jpg to start processing with the CLI skill.

Frequently Asked Questions about vlmrun-cli-skill

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

FAQPage Schema
How do I run visual AI tasks like image understanding or OCR from the command line?▼

You can run visual AI tasks like image understanding and OCR from the command line using a CLI skill that orchestrates media analysis against the Orion agent. It transforms natural-language prompts into processing workflows without requiring a GUI.

What is the best way to automate video summarization and document extraction without a GUI?▼

The best way to automate video summarization and document extraction without a GUI is by using a CLI-driven skill to send prompts and media files directly to the Orion visual AI agent, enabling quick experimentation and automation.

Do I need an API key to process images and videos through the Orion agent?▼

Yes, you need a configured API key and base URL to process images and videos through the Orion agent. The CLI skill requires these credentials to orchestrate visual AI tasks and execute toolsets.

Can I pass multiple input types like images and documents to a CLI visual AI agent?▼

Yes, you can pass multiple input types including images, videos, and documents to the CLI visual AI agent. It supports flexible prompts, model options, and inline skill usage to handle diverse media workflows.

How do I start a chat with the Orion agent to analyze a photo using the CLI?▼

To start a chat and analyze a photo using the CLI, run a command like `vlmrun chat "Describe this image" -i photo.jpg` to send your prompt and image input directly to the Orion agent for processing.

What are the limitations of using a CLI for object detection compared to GUI tools?▼

Using a CLI for object detection lacks visual feedback compared to GUI tools, but it enables flexible automation and scripting. It relies entirely on text prompts and command-line inputs to configure toolsets and model options.

Related Skills

Explore More Software Engineering Skills→
willform-aiwillform-ai

wf-setup

Configure Willform Agent API key, base URL, and language preference.

Official
Basic
profmikegreeneprofmikegreene
1

plan-ingestion

Parses pilot plans and hypotheses into structured JSON or tabular data for downstream analysis.

Community
Intermediate
lanejlanej
40

claude-cli

Automate interactive AI sessions and scripting with the Claude CLI.

Community
Intermediate
BAIZ1DBAIZ1D

writer

Create, convert, and batch process LibreOffice Writer documents via soffice and UNO API.

Community
Intermediate