Is the VLM Run CLI skill free?

Yes. The skill itself is free from vlm-run/skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the VLM Run CLI SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.

How do I install VLM Run CLI?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use VLM Run CLI with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

VLM Run CLI

Drive the vlmrun CLI to OCR, extract, and analyze images/video/PDFs

by vlm-run · vlm-run/skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 279666f

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

The skill is an accurate wrapper doc for the real vlmrun CLI: pip install 'vlmrun[cli]' succeeded and every documented subcommand (chat, generate, files, hub, models, artifacts) and flag exists exactly as the SKILL.md describes. Output could not be measured against a baseline because `vlmrun chat` on a test image returns 'API key not found' and demands a key from app.vlm.run -- a signup/paid wall, so no real visual-AI result was produced. No overselling of anything checkable, but every task in the skill needs a funded VLM Run account before it does anything.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 5/5

What VLM Run CLI does

Teaches the agent to call the vlmrun CLI to send images, video, and documents to VLM Run's Orion visual model for OCR, object detection, extraction, summarization, and image/video generation. Triggers on requests like 'extract text from this image', 'summarize this video', or 'parse this invoice PDF'.

How to install VLM Run CLI

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger VLM Run CLI

/vlmrun-cli-skill Drive the vlmrun CLI to OCR, extract, and analyze images/video/PDFs

It also activates on plain-language prompts like these:

Extract text from this scanned invoice image
Summarize what's happening in this uploaded video file
Parse this receipt PDF and pull out the line items

Frequently asked questions

Is the VLM Run CLI skill free?: Yes. The skill itself is free from vlm-run/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does VLM Run CLI work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Works with setup. The skill is an accurate wrapper doc for the real vlmrun CLI: pip install 'vlmrun[cli]' succeeded and every documented subcommand (chat, generate, files, hub, models, artifacts) and flag exists exactly as the SKILL.md describes. Output could not be measured against a baseline because `vlmrun chat` on a test image returns 'API key not found' and demands a key from app.vlm.run -- a signup/paid wall, so no real visual-AI result was produced. No overselling of anything checkable, but every task in the skill needs a funded VLM Run account before it does anything.
What is the VLM Run CLI SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install VLM Run CLI?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use VLM Run CLI with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.