Skill Claude CodeCodex
Axum server design for document extraction endpoints, middleware, async processing, and Model Context Protocol integration for AI agents.
11 19d ago A 9 tokens
original MIT
Skill Claude CodeCodex
Text splitting strategies, embedding generation with FastEmbed, RAG pipeline integration.
11 19d ago A 11 tokens
original MIT
Skill Claude CodeCodex
Searches current directory and parents for kreuzberg.toml, kreuzberg.yaml, or kreuzberg.json. Stops at first match.
11 19d ago A 3 tokens
original MIT
Skill Claude CodeCodex
Kreuzberg's format detection -> extraction -> fallback orchestration for 75+ file formats.
11 19d ago A 11 tokens
original MIT
Skill Claude CodeCodex
ZIP archive → Security validation → XML parsing → Text + tables + metadata.
11 19d ago A 3 tokens
original MIT
Skill Claude CodeCodex
Extension → EXTTOMIME map → validate → Registry lookup → Extractor.
11 19d ago A 3 tokens
original MIT
Skill Claude CodeCodex
Skill "plugin-architecture-patterns" from kreuzberg-dev/kreuzberg-lts, covering priority: critical, plugin architecture & registration, plugin types, documentextractor implementation and priority system.
11 19d ago A 3 tokens
original MIT
Skill Claude CodeCodex
WASM target in crates/kreuzberg-wasm/. Uses wasm-bindgen with sync-only internal APIs.
11 19d ago A 3 tokens
original MIT
kreuzberg
09Skill Claude CodeCodex
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…
11 19d ago A 89 tokens
original MIT