A high-performance extraction tool that converts PowerPoint presentations into clean Markdown or structured JSON data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pptx-to-text
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pptx-to-text using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is PPTX to Text?
PPTX to Text is a developer-centric tool designed to bridge the gap between visual presentation files and machine-readable text. By leveraging the MinerU document intelligence engine from OpenDataLab, this skill allows users to programmatically ingest content from .pptx files. It is an essential addition to the Openclaw Skills ecosystem for anyone building automated document processing pipelines.
The skill provides two primary modes of operation: a quick, token-free flash extraction for small files and a comprehensive API-driven extraction for complex data structures. Whether you are building a knowledge base or preparing data for an AI agent, this tool ensures that presentation content is easily accessible and ready for analysis.
PPTX to Text Use Cases
- Automating the extraction of slide content for search engine indexing.
- Converting corporate presentations into Markdown for LLM preprocessing and context injection.
- Building searchable archives of legacy PowerPoint decks within Openclaw Skills workflows.
- Extracting text from remote slide URLs without downloading files manually.
- Streamlining content review processes by viewing presentation text directly in the terminal.
How PPTX to Text Works
- The skill accepts a local path or a URL pointing to a .pptx presentation.
- It utilizes the mineru-open-api to communicate with the MinerU document intelligence engine.
- The engine parses the slide layouts and extracts text elements, maintaining logical order.
- Users can choose between flash-extract for immediate Markdown output or full extraction for structured JSON.
- The resulting text is returned to the standard output or saved to a designated directory for further use.
PPTX to Text Setup
To get started with this skill, install the MinerU CLI via npm or Go:
npm install -g mineru-open-api
# Alternatively, for macOS/Linux users
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
For basic use, no token is required. For full extraction features, set up your API token:
mineru-open-api auth
# Or set the environment variable
export MINERU_TOKEN="your-token-here"
PPTX to Text Data Schema & Taxonomy
The skill organizes extracted data based on the requested format to ensure compatibility with various Openclaw Skills:
| Output Format | Description | Best Use Case |
|---|---|---|
| Markdown | Near-plain text representation of slides | Human reading / LLM context |
| JSON | Structured objects containing per-slide text fields | Data parsing / Database ingestion |
| Stdout | Direct text stream | CLI piping and automation |
Users can also provide a --language hint (e.g., en for English) to improve extraction accuracy.
PPTX to Text Advanced Features
- Support for targeted extraction using the --pages flag to process specific slide ranges.
- Token-free flash-extract mode for rapid processing of files up to 10MB or 20 pages.
- Seamless URL integration allowing for remote file processing without local storage.
- Language-aware extraction to optimize processing for different character sets.
- Flexible output management that redirects status messages to stderr while keeping document content in stdout for clean piping within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Linux Sysadmin Expert
A professional-grade Linux system administration skill for AI agents covering 12 core modules from security hardening to automated orchestration.
FlyAI Elder Travel Care Core
A central AI orchestration hub designed to provide elderly travelers with voice-activated assistance, emergency medical response, and seamless travel coordination.
PPTX Parse
A high-performance utility for converting PowerPoint files into structured, hierarchical Markdown using the MinerU document intelligence engine.
AI Startup Opportunity Finder
A systematic intelligence assistant that helps entrepreneurs and developers identify, validate, and launch profitable AI and Agent-based startup projects.
PPTX OCR
A high-performance OCR skill for extracting text from image-embedded PowerPoint presentations using the MinerU engine.
PowerPoint Content Extractor (pptx-extract)
A high-performance skill for converting PowerPoint presentations into structured Markdown for AI agents and documentation workflows.
METADATA
Featured*
