table-extraction-and-reconstruction

taule extraction and reconstruction

7,385 stars

Best use case

table-extraction-and-reconstruction is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

taule extraction and reconstruction

Teams using table-extraction-and-reconstruction should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/table-extraction-and-reconstruction/SKILL.md --create-dirs "https://raw.githubusercontent.com/kreuzberg-dev/kreuzberg/main/.ai-rulez/domains/ocr-integration/skills/table-extraction-and-reconstruction/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/table-extraction-and-reconstruction/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How table-extraction-and-reconstruction Compares

Feature / Agent	table-extraction-and-reconstruction	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

taule extraction and reconstruction

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

Cursor vs Codex for AI Workflows

Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

SKILL.md Source

Identify and reconstruct tables from OCR data

1. Extract word positions from hOCR
2. Perform spatial clustering:
   - Group words by vertical alignment
   - Identify column boundaries
   - Identify row boundaries
3. Detect table cells:
   - Assign words to cells
   - Handle merged cells
   - Detect cell padding
4. Parse TSV output if available:
   - Map cells to TSV rows/cols
   - Merge with hOCR data
5. Convert to Markdown table:
   - Generate table header
   - Add alignment indicators
   - Handle spanning cells
   - Escape special characters
6. Validate table structure

Related Skills

format-specific-extraction

7385

from kreuzberg-dev/kreuzberg

format specific extraction

extraction-pipeline-patterns

7385

from kreuzberg-dev/kreuzberg

extraction pipeline patterns

extraction-quality-testing

7385

from kreuzberg-dev/kreuzberg

extraction quality testing

kreuzberg

7385

from kreuzberg-dev/kreuzberg

Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins.