How do I install the Local Ocr Vlm skill?

Run npx skillmds@latest add batteryshark/local-ocr-vlm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Local Ocr Vlm safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Local Ocr Vlm?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Local Ocr Vlm free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Local Ocr Vlm?

batteryshark (@batteryshark) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Local Ocr Vlm by batteryshark — Agent Skill

Name: Local Ocr Vlm
Author: batteryshark

Local Ocr Vlm

Run OCR on local images through an OpenAI-compatible local vision endpoint (LM Studio, vLLM/vmlx). Use when you need offline, on-machine document OCR into markdown, including batch directory processing, without sending images to a hosted service.

batteryshark Updated Sep 17, 2026

File contents

Local OCR VLM

Send image(s) to a locally hosted OpenAI-compatible vision endpoint and capture the text. Defaults to http://127.0.0.1:1234/v1. The tool is a single, zero-dependency Node script; no Python or SDK is required.

When to use

OCR screenshots, scans, or document images on-machine.
Batch a folder of images into per-image markdown files.
Keep OCR offline using LM Studio or a vLLM/vmlx-compatible API.

Prerequisites

Node.js 18+ (uses the built-in global fetch; no packages to install).
A local OpenAI-compatible server exposing a /v1 API with a vision-capable model loaded. Qwen 3.5 9B is preferred; Qwen 3.5 27B also works.

Commands

Run the portable entry point:

bin/local-ocr-vlm invoice.png
bin/local-ocr-vlm --input-dir doc_input --output-dir doc_output --max-workers 4
bin/local-ocr-vlm --input-dir doc_input --model "qwen3.5-vl-9b"

Run bin/local-ocr-vlm --help for every flag. See references/reference.md for the endpoints called, model auto-selection, thinking-mode handling, and exit codes.

Workflow

Confirm a local endpoint is serving /v1 with a vision model loaded.
Point the tool at one or more images and/or an --input-dir. With no --output-dir, results print to stdout; with one, each image becomes <stem>.md.
Let the tool auto-select a model, or pass --model when the endpoint hosts several.
Tune --max-workers for throughput; use 1 for strictly sequential processing.

Rules

Never point the tool at a remote/hosted endpoint when the intent is to keep images on-machine; the default base URL is loopback.
The tool reads images and writes only markdown output; it does not modify input images.
Treat an unreachable endpoint or a per-image request failure as an explicit error. A run exits non-zero if any image fails.

Use agents/ocr-operator.md when a subagent should choose flags and verify the endpoint before running a batch.

---name: local-ocr-vlmdescription: Run OCR on local images through an OpenAI-compatible local vision endpoint (LM Studio, vLLM/vmlx). Use when you need offline, on-machine document OCR into markdown, including batch directory processing, without sending images to a hosted service.---# Local OCR VLMSend image(s) to a locally hosted OpenAI-compatible vision endpoint and capture the text. Defaults to `http://127.0.0.1:1234/v1`. The tool is a single, zero-dependency Node script; no Python or SDK is required.## When to use- OCR screenshots, scans, or document images on-machine.- Batch a folder of images into per-image markdown files.- Keep OCR offline using LM Studio or a vLLM/vmlx-compatible API.## Prerequisites- Node.js 18+ (uses the built-in global `fetch`; no packages to install).- A local OpenAI-compatible server exposing a `/v1` API with a vision-capable model loaded. Qwen 3.5 9B is preferred; Qwen 3.5 27B also works.## CommandsRun the portable entry point:```shbin/local-ocr-vlm invoice.pngbin/local-ocr-vlm --input-dir doc_input --output-dir doc_output --max-workers 4bin/local-ocr-vlm --input-dir doc_input --model "qwen3.5-vl-9b"```Run `bin/local-ocr-vlm --help` for every flag. See [`references/reference.md`](references/reference.md) for the endpoints called, model auto-selection, thinking-mode handling, and exit codes.## Workflow1. Confirm a local endpoint is serving `/v1` with a vision model loaded.2. Point the tool at one or more images and/or an `--input-dir`. With no `--output-dir`, results print to stdout; with one, each image becomes `<stem>.md`.3. Let the tool auto-select a model, or pass `--model` when the endpoint hosts several.4. Tune `--max-workers` for throughput; use `1` for strictly sequential processing.## Rules- Never point the tool at a remote/hosted endpoint when the intent is to keep images on-machine; the default base URL is loopback.- The tool reads images and writes only markdown output; it does not modify input images.- Treat an unreachable endpoint or a per-image request failure as an explicit error. A run exits non-zero if any image fails.Use [`agents/ocr-operator.md`](agents/ocr-operator.md) when a subagent should choose flags and verify the endpoint before running a batch.

Frequently asked questions