claudecode-cli-vision

Route claudecode provider requests to vision-capable CLI for OCR.

3|Updated Mar 17, 2026

Search Tags:#ocr #pdf #multimodal #vision #claudecode #provider routing #claude code cli

Ready to run

npx skills add https://github.com/transreal/claudecode --skill claudecode-cli-vision

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: claudecode-cli-vision
Source: https://github.com/transreal/claudecode/tree/main/Claude%20Directives/skills/claudecode-cli-vision
Command: npx skills add https://github.com/transreal/claudecode --skill claudecode-cli-vision

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It fixes multimodal/vision failures when using claudecode’s Claude Code CLI path for image and PDF-page OCR, ensuring the correct redirect to the vision-capable backend.

Core Features & Use Cases

Provider redirect for multimodal: Automatically routes provider == "claudecode" requests through the CLI vision-capable flow instead of rejecting multimodal.
Image/PDF page OCR via existing normalization: Leverages existing iNormalizePrompt behavior that exports Image[...] to temporary PNG files and attaches them to the Claude CLI prompt.
Works with SourceVault OCR workflows: Designed to plug into PDFIndex / SourceVault Stage 4C routines that call ClaudeQueryBg with non-blocking execution and a timeout budget.

Quick Start

Ask ClaudeCode to run vision OCR by routing ClaudeCode\$ClaudeModelto{"claudecode", "<model>"}and passing anImage[...]` (or a PDF page rasterized to an image) alongside a direct OCR prompt.

Frequently Asked Questions about claudecode-cli-vision

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

FAQPage Schema

How do I run OCR on PDF pages using Claude Code CLI?▼

To run OCR on PDF pages using Claude Code CLI, rasterize the pages to images and pass them with a direct prompt. The Skill routes provider requests through the CLI vision-capable flow, leveraging existing normalization to attach images to the prompt.

Why does multimodal vision fail when using the Claude Code CLI path?▼

Multimodal vision fails because the default Claude Code CLI path rejects image inputs. This Skill fixes the failure by redirecting provider requests through the correct vision-capable backend flow for image and PDF-page OCR.

Can I use Claude Code CLI for image OCR with non-blocking query execution?▼

Yes, you can use Claude Code CLI for image OCR with non-blocking execution. The Skill preserves deterministic non-blocking query execution and returns timeout-aware errors for workflows calling ClaudeQueryBg with a timeout budget.

Does the Claude Code CLI path support provider routing for multimodal inputs?▼

The Claude Code CLI path supports multimodal provider routing through this Skill. It automatically routes requests to the vision-capable flow instead of rejecting multimodal inputs, satisfying the functional requirement for correct provider handling.

What's the best way to integrate vision OCR into SourceVault Stage 4C workflows?▼

The best way to integrate vision OCR into SourceVault Stage 4C is routing the provider to the vision-capable CLI flow. This Skill plugs directly into PDFIndex and SourceVault Stage 4C routines that call ClaudeQueryBg with attached image media files.

How does image normalization work for Claude Code CLI vision prompts?▼

Image normalization for Claude Code CLI vision prompts works by exporting Image inputs to temporary PNG files. The existing iNormalizePrompt behavior attaches these normalized media files to the Claude CLI prompt for processing.