looker

Analyze multimodal documents to extract insights from PDFs, images, videos, and audio.

1|1|Updated Jan 16, 2026
One-click install
npx skills add https://github.com/Lynricsy/Oh-My-ClaudeCode --skill looker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: looker
Source: https://github.com/Lynricsy/Oh-My-ClaudeCode/tree/main/skills/looker
Command: npx skills add https://github.com/Lynricsy/Oh-My-ClaudeCode --skill looker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Looker provides a dedicated multimodal analysis agent to extract meaningful insights from PDFs, images, videos, and audio, enabling extraction of content, data, and insights from complex documents.

Core Features & Use Cases

  • Analyze PDFs for text, tables, and structure; describe images; interpret charts; and summarize video/audio content.
  • Provide concise descriptions of scenes, UI elements, diagrams, and data relationships to support decision making.
  • Use cases include document review, data extraction, content summarization, and media QA across diverse formats.

Quick Start

Analyze an attached multimodal document (PDF, image, video, or audio) to generate a concise description of its main content and data insights.

Frequently Asked Questions about looker

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

FAQPage Schema
How do I extract data and text from a PDF with tables and charts?

To extract data from a PDF, analyze the document to parse text, interpret tables, and read charts. This generates a concise description of the main content and structured data insights from the file.

Can I analyze audio and video files to get a content summary?

Yes, you can analyze audio and video files to summarize media content. The process interprets audio tracks and visual scenes to extract meaningful insights and provide concise descriptions of the media.

What is the best way to interpret charts and diagrams from images?

The best way to interpret charts from images is to analyze the visual file directly. This extracts data relationships and provides concise descriptions of UI elements, scenes, and diagrams to support decision making.

Does this multimodal document analysis require an internet connection?

No, this multimodal document analysis operates entirely offline and enforces non-network operation. It processes PDFs, images, videos, and audio locally to extract insights without requiring internet access.

What file formats are supported for multimodal content extraction?

Supported file formats for multimodal content extraction include PDFs, images, videos, and audio. The analysis enforces file type support constraints to ensure structured output across these diverse media types.

How do I get structured output from unstructured PDF and media documents?

You get structured output from unstructured PDFs and media by analyzing the attached files. The process enforces clearly defined result formats and prompts to deliver structured data extraction and content summarization.