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

doc-extract-engine

Extract structured data from PDFs via a remote API workflow.

Updated Mar 1, 2026
Search Tags:#pdf#api#session-management#sse#schema-design#document-extraction
One-click install
npx skills add https://github.com/lihanghang/agent-daily-blog --skill doc-extract-engine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doc-extract-engine
Source: https://github.com/lihanghang/agent-daily-blog/tree/main/skills-archive/2026-03-17/doc-extract-engine
Command: npx skills add https://github.com/lihanghang/agent-daily-blog --skill doc-extract-engine

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides an end-to-end remote API workflow to extract structured information from PDFs, encapsulating authentication, document upload, AI-assisted schema design, session creation, SSE-based extraction, result correction, and archiving to streamline document processing.

Core Features & Use Cases

  • Remote API driven end-to-end PDF extraction with built-in authentication, upload, schema design, session creation, SSE streaming, correction, and archiving.
  • Upload PDFs and receive document IDs for downstream processing.
  • Design extraction schema via AI-assisted dialog, create a session, perform extraction, and iteratively refine results.
  • Archive completed runs and view history for auditing, reuse, and governance.

Quick Start

Upload a PDF, design its extraction schema via chat, create a session, run extraction, and archive the results.

Frequently Asked Questions about doc-extract-engine

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

FAQPage Schema
How do I extract structured data from PDFs via a remote API?▼

PDF extraction via API supports authentication, document upload, schema design, session creation, SSE streaming, iterative correction, and archiving. It applies to scalable document processing, schema conversation, and batch extraction across multiple files.

How does SSE extraction work for batch processing PDFs?▼

SSE extraction streams structured data from uploaded PDFs within a created session. You design the schema via AI-assisted dialog, run extraction, iteratively correct results, and archive runs for history retrieval and reuse.

Do I need httpx to perform PDF document extraction?▼

You need httpx to handle remote API connections for PDF extraction. This dependency manages the HTTP requests required for authentication, document upload, session creation, and SSE streaming.

Can I design extraction schemas dynamically for different PDF documents?▼

You can design extraction schemas dynamically via AI-assisted dialog before creating a session. This allows the PDF extraction workflow to adapt to varied document structures and iteratively refine results.

What is the best way to manage PDF extraction history for auditing?▼

The best way to manage extraction history is by archiving completed runs after SSE extraction and correction. This enables history retrieval for auditing, reuse, and governance across processed PDF documents.

Related Skills

Explore More Software Engineering Skills→
lihanghanglihanghang

xiaer-pdf-extractor

Monitor 虾饵论坛 posts for PDFs, upload them to an extraction API, and comment results.

Community
Intermediate
Alex1980AlexAlex1980Alex

duckdb-analytics

Analyze JSONL and Parquet logs directly with DuckDB.

Community
Advanced
firdaus12pfirdaus12p
8

brainstorm-schema

Guide database schema creation through targeted questions and generate schema.md documentation.

Community
Intermediate
linfordWulinfordWu
1

ocr-and-documents

Extract text from PDFs and scanned documents using OCR and parsing libraries.

Community
Intermediate