skills.rest
lihanghang
lihanghangCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

insightdoc

Convert PDFs and images into MD, HTML, or DOCX via the InsightDoc API.

Updated Mar 1, 2026
Search Tags:#ocr#pdf#image#data-extraction#insightdoc#document-parse#output-formats
One-click install
npx skills add https://github.com/lihanghang/agent-daily-blog --skill insightdoc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: insightdoc
Source: https://github.com/lihanghang/agent-daily-blog/tree/main/skills-archive/2026-03-17/insightdoc
Command: npx skills add https://github.com/lihanghang/agent-daily-blog --skill insightdoc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This skill uses the InsightDoc API to convert PDF and image documents into structured data, producing markdown, HTML, or other formats to simplify downstream processing.

Core Features & Use Cases

  • Local file parsing: Upload a PDF or image and receive structured results.
  • URL parsing: Download remote documents and parse them seamlessly.
  • Multiple outputs: Generate md, html, block_md, docx; finance_ocr outputs matrix or normalization for financial reports.
  • Use Case: Automate archival of reports by converting them to searchable, machine-readable formats.

Quick Start

Parse a local or remote document using the provided parse.py script and specify the desired output format.

Frequently Asked Questions about insightdoc

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

FAQPage Schema
How do I parse PDF and image files into structured markdown or HTML?▼

You can convert PDFs and images into structured markdown or HTML by using the InsightDoc API workflow. It processes local uploads and remote URLs, outputting md, html, block_md, or docx formats for easy consumption.

Does this document parsing tool support extracting data from financial reports?▼

Yes, document parsing supports financial reports through the finance_ocr workflow. It specifically extracts financial data and yields matrix or normalization outputs, making it suitable for automating the archival of financial reports.

Can I parse remote URLs instead of uploading local PDF files?▼

Yes, you can parse remote documents by providing their URLs. The tool downloads the remote files and parses them using the same workflows to generate structured markdown, HTML, or docx outputs.

What output formats are available when converting PDFs to structured data?▼

When converting PDFs to structured data, available output formats include md, html, block_md, and docx. For financial reports, the finance_ocr workflow yields matrix or normalization outputs for downstream processing.

Do I need an API key to extract text from images and PDFs?▼

Yes, an API key is required to extract text from images and PDFs. The implementation enforces API key authentication, which can be configured via environment variables, .env files, or CLI parameters.

What's the best way to automate converting paper reports into machine-readable formats?▼

The best way to automate converting paper reports into machine-readable formats is using the docparse workflow. It converts local or remote PDFs and images into searchable markdown, HTML, or docx outputs for archival.

Related Skills

Explore More Data & Analytics Skills→
PaddlePaddlePaddlePaddle
87.3k

paddleocr-text-recognition

Extract text and location data from images and PDFs via the PaddleOCR API.

Official
Intermediate
gquthiergquthier
14

ocr-and-documents

Extract text, tables, and OCR content from PDFs and documents.

Community
Intermediate
winsorllcwinsorllc

url-tools

Manipulate URLs and perform HTTP requests with curl and Python.

Community
Intermediate
mxzinkemxzinke
2

document-parse

Parse PDFs, DOCX, PPTX, XLSX, and images into text or structured JSON.

Community
Intermediate