git:20260519.f531e55 to git:20260710.2925510

11 added, 14 removed. Audit A to B.

---

- name: "Apache Tika Document Extractor"

- slug: "apache-tika-document-extractor"

+ title: "Apache Tika Document Extractor"

description: "Wraps Apache Tika Server REST API for extracting structured text from PDFs, DOCX, PPTX, and 1,200+ file formats. Outputs clean markdown with metadata preservation using Tika /rmeta/text endpoint and recursive parsing mode."

- github_stars: 3695

verification: "security_reviewed"

source: "https://github.com/apache/tika"

- category: "Data Extraction & Transformation"

- framework: "Codex"

+ category:

+ - "Data Extraction & Transformation"

+ framework:

+ - "Codex"

tool_ecosystem:

github_repo: "apache/tika"

github_stars: 3695

---

# Apache Tika Document Extractor

Wraps Apache Tika Server REST API for extracting structured text from PDFs, DOCX, PPTX, and 1,200+ file formats. Outputs clean markdown with metadata preservation using Tika /rmeta/text endpoint and recursive parsing mode.

## Installation

- Requirements and caveats from upstream:

- - **N.B.** [Docker](https://www.docker.com/products/personal) is used for tests in tika-integration-tests. If Docker is not installed, those tests are skipped.

- Basic usage or getting-started notes:

- - ===========

- - **Parse a file in Java:**

- - java

+ Choose whichever fits your setup:

- - Source: https://github.com/apache/tika

- - Extracted from upstream docs: https://raw.githubusercontent.com/apache/tika/HEAD/README.md

+ 1. Copy this skill folder into your local skills directory.

+ 2. Clone the repo and symlink or copy the skill into your agent workspace.

+ 3. Add the repo as a git submodule if you manage shared skills centrally.

+ 4. Install it through your internal provisioning or packaging workflow.

+ 5. Download the folder directly from GitHub and place it in your skills collection.

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/apache-tika-document-extractor/)