Kreuzberg.dev
Official@kreuzberg-dev
Legacy home of Kreuzberg — now Xberg at github.com/xberg-io. Hosts the v4 LTS docs (docs.kreuzberg.dev).
Agent Skills by Kreuzberg.dev
Showing 159 vetted skills indexed across 3 GitHub repositories.
kreuzberg-devconverting-html
Convert HTML documents into Markdown, Djot, or plain text with configurable formatting options.
kreuzberg-devhtml-to-markdown
Convert HTML to Markdown, Djot, or plain text with metadata and table extraction.
kreuzberg-devusing-the-mcp-server
Convert HTML to Markdown and extract metadata through the html-to-markdown MCP server tools.
kreuzberg-devextracting-metadata
Extracts structured metadata from HTML including titles, Open Graph tags, links, and structured data.
kreuzberg-devmcp
Convert HTML to Markdown and extract metadata through Model Context Protocol tools.
kreuzberg-devcli
Provides CLI reference documentation for the html-to-markdown-rs command-line interface.
kreuzberg-devapi
Provides API reference documentation for html-to-markdown-rs language bindings.
kreuzberg-devpicking-a-format
Maps document consumers to the correct Xberg CLI format and content-format flags.
kreuzberg-devbatch-extraction
Extract content from many documents concurrently with shared config and per-file overrides.
kreuzberg-devchunking
Split extracted text into sized chunks for LLM context windows and RAG ingestion.
kreuzberg-devextracting-tables
Extract structured tables from PDFs, spreadsheets, and images using layout-aware detection models.
kreuzberg-devextracting-with-ocr
Extract text from scanned PDFs and images using OCR backends and language packs.
kreuzberg-devxberg
Extract text, tables, metadata, and images from 106 document formats using Xberg APIs.
kreuzberg-devextracting-keywords
Extract keywords, detect languages, and generate embeddings from documents via the xberg CLI.
kreuzberg-devformat-specific-extraction
Extract text, tables, and metadata from Office, PDF, archive, and email documents.
kreuzberg-devmime-detection-routing
Detects MIME types and routes files to extractors via the FORMATS registry in core/mime.rs.
kreuzberg-devocr-pipeline-and-quality
Guides changes and A/B quality evaluation of OCR backends, preprocessing, caching, and table reconstruction.
kreuzberg-devfeature-flag-policy
Documents Cargo feature flags and target-conditional build configurations for the xberg crate.
kreuzberg-devpdf-backends
Configure and diagnose native and Pdfium PDF extraction backends in Xberg.
kreuzberg-devpolyrepo-boundaries
Determines repository ownership and coordinates cross-repository fixes across sibling Git repositories.
kreuzberg-devbenchmark-workflow
Run and diagnose Xberg extraction benchmarks, quality scoring, and ground-truth fixtures.
kreuzberg-devcrate-structure
Documents the Xberg Cargo workspace layout, crate roles, and member onboarding steps.
kreuzberg-devwasm-constraints
Enforces WASM build constraints for the xberg-wasm crate including sync-only APIs and size limits.
kreuzberg-devxberg-typescript-toolchain
Applies repository-specific pnpm, Vitest, napi-rs, and wasm-pack conventions to TypeScript package changes.
Frequently Asked Questions About Kreuzberg.dev
FAQPage SchemaWhat specific document processing tasks does Kreuzberg.dev enable?▼
It enables high-fidelity extraction of text, tables, metadata, and images from over 75 file formats. The system supports advanced HTML-to-Markdown conversion with configurable whitespace handling, visitor-based node customization, and robust recovery from malformed markup or binary data.
Which engineering personas benefit from these standards?▼
Systems architects and backend engineers managing polyglot codebases benefit most. The framework provides standardized patterns for Rust-core interop, ensuring consistent error handling, memory safety, and documentation parity across Python, TypeScript, Ruby, Java, Go, and Elixir environments.
How are these software development standards implemented?▼
Standards are enforced through modular Taskfile configurations, pre-commit hooks, and strict build profiles. Developers utilize standardized repository structures and language-specific linting configurations to ensure consistent testing, benchmarking, and release processes across all supported platforms.
What security measures are included for document handling?▼
Security is managed via the Ammonia crate for HTML sanitization, including URL scheme validation, style attribute whitelisting, and event handler removal. The system includes OWASP-aligned XSS test cases and binary data detection to prevent injection attacks during document ingestion.