PPT Extract for Openclaw

A professional-grade extraction tool that converts legacy .ppt and modern .pptx files into clean, readable Markdown using the MinerU engine.

mzlzyca
v0.4.0
Apr 3, 2026
0
886
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install ppt-extract

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install ppt-extract 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 PPT Extract?

The PPT Extract skill is a high-performance document intelligence integration designed for Openclaw Skills. It leverages the MinerU engine from OpenDataLab to parse complex presentation files, transforming them into structured Markdown data that AI agents can easily analyze and process. Whether you are dealing with legacy binary .ppt formats or modern XML-based .pptx files, this skill ensures that the textual and structural information within your slides is preserved and accessible.

By integrating this capability into your workflow, you enable your AI agents to 'read' presentations as if they were standard text documents. This is particularly valuable for automated documentation, content repurposing, and building searchable knowledge bases from corporate slide decks. The skill supports both local file processing and direct extraction from URLs, making it a versatile addition to any Openclaw Skills library.

PPT Extract Use Cases

  • Converting corporate presentation decks into searchable Markdown documentation for internal wikis.
  • Enabling AI agents to summarize slide content during automated research tasks.
  • Batch processing legacy .ppt archives into modern, developer-friendly text formats.
  • Extracting text and data from presentations hosted on remote URLs without manual downloads.

How PPT Extract Works

  1. The skill receives a command to process a PowerPoint file from a local path or a remote URL.
  2. It authenticates with the MinerU API using a secure token stored in the environment variables.
  3. The file is processed by the MinerU engine, which performs layout analysis and text extraction.
  4. The extracted content is structured into Markdown, maintaining the logical flow of the slides.
  5. The resulting data is either streamed to stdout or saved to a specified output directory for the AI agent to consume.

PPT Extract Setup

To use this Openclaw Skills integration, you must install the MinerU CLI and configure your API token:

# Install via npm
npm install -g mineru-open-api

# Or install via Go (macOS/Linux)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

# Set up your authentication
export MINERU_TOKEN="your-token-here"
# Or use the interactive setup
mineru-open-api auth

PPT Extract Data Schema & Taxonomy

The PPT Extract skill organizes data to maximize readability and compatibility with LLM context windows:

Feature Specification
Output Format Markdown (.md)
Input Support .ppt, .pptx
Metadata Includes slide numbers and structural markers
Storage Defaults to stdout; supports file-based output via -o flag
Language Support Configurable via --language (e.g., en, ch)

PPT Extract Advanced Features

  • Multi-format support: Seamlessly switches between legacy .ppt and modern .pptx parsing logic.
  • Remote extraction: Directly process presentations via HTTP/HTTPS URLs.
  • Page range filtering: Use the --pages flag to extract content only from specific sections of a deck.
  • Environment variable integration: Fully compatible with CI/CD and automated agent workflows via MINERU_TOKEN support.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins mineru-open-api
Github Stars: 0
forks: 0

Featured*