skills.rest
AKCqhzdy
AKCqhzdyCOMMUNITY
Explore all skills by this author →
GitHub

extraction

Extract structured text data from PDFs or images via YAML-configured pipelines.

Updated Aug 27, 2026
Search Tags:#pdf#image#extract#structured-data#artifact-generation#model-routing#yaml-config
One-click install
npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill extraction-akcqhzdy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extraction
Source: https://github.com/AKCqhzdy/dse-subject-grading/tree/main/.github/skills/extraction
Command: npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill extraction-akcqhzdy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracting structured text from PDFs or images is often tedious and error-prone. This skill orchestrates the repository's extraction pipeline to produce consistent, structured results.

Core Features & Use Cases

  • Build and edit YAML extraction configs.
  • Choose input modes (whole_pdf, page_by_page, page_by_page_with_prev) and route models to providers.
  • Parse model outputs into structured extraction rows and artifacts for downstream analysis.
  • Common use cases include extracting questions, student answers, rubrics, or other structured content from documents.

Quick Start

Provide a PDF or a directory of PDFs along with a YAML config to initialize and run the extraction pipeline and obtain structured results.

Frequently Asked Questions about extraction

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

FAQPage Schema
How do I extract structured data from a PDF or image?▼

To extract structured data from a PDF or image, provide the document along with a YAML configuration file to initialize and run the extraction pipeline. The results are saved as structured extraction rows and artifacts ready for downstream use.

What is YAML-driven model routing for PDF extraction?▼

YAML-driven model routing allows you to configure extraction settings, including input modes, page ranges, and provider routing, within a YAML file. This configuration directs the pipeline to use specific models for processing documents.

Can I batch process PDFs to extract structured text page by page?▼

Yes, you can batch process PDFs to extract structured text page by page. The extraction pipeline supports single-document or batch workflows and offers input modes like page_by_page and page_by_page_with_prev for targeted document processing.

Do I need environment-based provider configuration to extract text from images?▼

Yes, environment-based provider configuration is required to extract text from images. The extraction pipeline enforces this setup to route models to designated providers securely before generating structured data artifacts.

What are the limitations of extracting structured data from scanned PDFs?▼

Limitations of extracting structured data from scanned PDFs include dependency on the accuracy of the routed model's output and the enforced environment-based provider configuration. Results are constrained by the input mode and page ranges defined in your YAML config.

Related Skills

Explore More Data & Analytics Skills→
winsorllcwinsorllc

pdf-tools

Extract text, merge, split, and watermark PDFs using pypdf and pdf2image.

Community
Intermediate
wanyusheng63-altwanyusheng63-alt

excel-parser-integrator

Parse and normalize tabular data from Excel and CSV files in backend services.

Community
Intermediate
thisismynewfmail-uithisismynewfmail-ui

instructor

Extract structured data from LLM outputs using Pydantic models.

Community
Advanced
trpc-grouptrpc-group
1.6k

ocr

Extract text from images using pytesseract and Pillow.

Official
Advanced