kreuzberg-dev

Format-specific document extraction workflows

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.

REST API server and MCP protocol integration

Chunking, embeddings, and RAG pipeline integration

Document extraction pipeline architecture and patterns

Plugin architecture, registration, and trait patterns

Add a new language to Alef-based e2e test generation

Create a new e2e test fixture for cross-language test generation

Universal LLM API client for 142+ providers with native bindings for 11 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C. Covers chat, streaming, embeddings, image generation, speech, transcription, moderation, reranking, search, OCR, tool calling, and configuration.

Generate fully-typed polyglot language bindings for Rust libraries using Alef. Use when configuring alef.toml, running alef CLI commands, writing e2e test fixtures, debugging binding generation, or setting up CI/CD for multi-language Rust libraries. Covers 16 language backends (Python, TypeScript, WASM, Ruby, PHP, Go, Java, C#, Kotlin, Elixir, Gleam, R, Swift, Dart, Zig, C), DTO styles, trait bridges, adapter patterns, version sync, and pre-commit hooks.

Audit bindings for coverage gaps — verify every public Rust item is exposed across all generated language bindings. Use this skill any time you need to check that a function/type is present in every target language, audit intentional exclusions, or investigate missing bindings in one or more languages. Covers the full audit flow: config review, attribute scan, item enumeration, cross-binding diff, gap reporting, and triage (alef vs actions vs consumer config).

Cut, tag, and publish an alef release end-to-end. Use this skill any time the user asks for a release, a version bump, a hotfix tag, or a CHANGELOG roll-up in this repo. Covers the full pipeline: changelog, version sync via Taskfile, Cargo.toml verification, prek lint pass, atomic commit (no AI signatures, no --no-verify when avoidable), git tag, and `gh release create` (not just a tag).

Work in iterations with implementation rounds followed by critical review passes

Split tasks among subagents for parallel execution

Convert HTML to Markdown, Djot, or plain text with structured extraction. Use when writing code that calls html-to-markdown APIs in Rust, Python, TypeScript, Go, Ruby, PHP, Java, C#, Elixir, R, C, or WASM. Covers installation, conversion, configuration, metadata extraction, document structure, and CLI usage.

Parse and extract code intelligence from 306+ programming languages using tree-sitter grammars. Provides Rust core with native bindings for Python, Node.js, TypeScript, Ruby, Go, Java, C#, Elixir, PHP, and WebAssembly. Use when writing code that parses source code, extracts structure/imports/exports, or analyzes code with syntax-aware chunking.