A powerful document AI skill that parses complex PDFs, images, and Office files into structured Markdown and JSON data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install textin-parse
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 textin-parse 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 Textin Document Parser?
Textin Parse is a sophisticated document processing integration designed for Openclaw Skills. It leverages the Textin API to perform deep layout analysis, optical character recognition (OCR), and table extraction across a wide variety of file formats. Whether you are dealing with scanned images or digital PDFs, this skill converts messy documents into clean, structured Markdown ready for AI consumption.
By integrating Textin Parse into your workflow, you gain the ability to extract formulas, hierarchical document trees, and even remove watermarks automatically. It is an essential tool for developers and researchers who need to turn static documents into actionable, machine-readable data with high precision.
Textin Document Parser Use Cases
- Converting scanned PDF invoices or reports into structured Markdown for LLM analysis.
- Extracting complex tables from Excel or PDF files into clean HTML or Markdown formats.
- Automating the extraction of table of contents and document hierarchies from long technical manuals.
- Identifying and digitizing mathematical formulas from academic papers or handwritten notes.
- Rapidly digitizing image-based text from formats like PNG, JPG, and WebP for searchable archives.
How Textin Document Parser Works
- The user provides a document or image file and triggers a request for parsing or conversion.
- The skill authenticates with the Textin API using the stored x-ti-app-id and x-ti-secret-code.
- The file is uploaded to the Textin engine where layout detection and OCR take place based on specified parameters (like parse_mode).
- The engine processes structural elements including tables, formulas, and headers.
- The skill receives the structured response and delivers the Markdown content or metadata back to the user environment.
Textin Document Parser Setup
To get started with Textin Parse, you must first obtain your API credentials from the official Textin platform.
- Register at Textin.
- Navigate to the Developer and Account Information page to find your
x-ti-app-idandx-ti-secret-code. - Configure the Openclaw Skills environment by providing these credentials when prompted:
# Example of how the agent might prompt for configuration
set_config textin_app_id "your_app_id_here"
set_config textin_secret_code "your_secret_code_here"
Textin Document Parser Data Schema & Taxonomy
The skill supports a wide array of formats and returns structured data as detailed below:
| Feature | Supported Specifications |
|---|---|
| Images | png, jpg, jpeg, bmp, tiff, webp |
| Documents | pdf, doc, docx, html, xls, xlsx, csv, ppt, pptx, txt, ofd, rtf |
| Max Size | 500MB |
| Output | Markdown (Default), HTML tables, Structured JSON, Excel |
| Metadata | Document tree (hierarchy), page details, and object coordinates |
Textin Document Parser Advanced Features
- Support for multiple parse modes including 'vlm' (Vision Language Model) and 'scan' for high-fidelity image processing.
- Intelligent watermark removal to clean up documents before OCR.
- Configurable table flavors allowing output in either native Markdown or complex HTML syntax.
- Formula recognition levels to specifically target or exclude inline and display math.
- Partial document parsing using page_start and page_count to save API credits on large files.
SKILL.md
Loading
Related Openclaw Skills
Vendor Risk Briefing Assistant
A specialized tool for generating concise risk summaries for external SaaS and API vendors, focusing on integration impact and data flow.
Retail Agent Setup Onboarding Wizard
A comprehensive 12-step onboarding wizard designed to transform blank AI agents into fully operational retail digital employees.
Klenty
A powerful sales engagement skill that enables AI agents to automate prospect outreach, manage email cadences, and synchronize CRM data through the Membrane framework.
WeChat Share
A specialized tool for exporting and importing selected Openclaw workspace files between users with optional burn-after-read security.
Shift Scheduler
An AI-driven workforce management tool that automates shift queries, swap requests, and manager approvals for retail environments.
Incident Response Plan Generator
A specialized tool for generating tailored incident response plans to secure AI agent deployments and ensure operational resilience.
Featured*
