An intelligent document processing skill that classifies file types and extracts key information into structured JSON for database integration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doc-structurer
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 doc-structurer 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 doc-structurer?
doc-structurer is a technical data pipeline skill designed to analyze raw text and metadata extracted from documents. It serves as the middle layer in an automation workflow, taking raw output from parsing tools and transforming it into highly organized, machine-readable JSON data. By leveraging Openclaw Skills, developers can automate the labor-intensive process of identifying document categories—such as contracts, proposals, or reports—and extracting specific fields like dates, financial amounts, and action items.
The skill utilizes a multi-stage logic engine that combines keyword frequency, structural pattern analysis, and optional LLM verification to ensure high accuracy. This makes it an essential tool for teams looking to build automated document management systems or sync physical records into digital platforms like Notion or internal databases.
doc-structurer Use Cases
- Automatically classifying incoming business documents into categories like contracts, invoices, or meeting minutes.
- Extracting and normalizing dates from various formats into a standard YYYY-MM-DD format for calendar synchronization.
- Identifying high-priority tasks by scanning documents for urgent keywords and upcoming deadlines.
- Converting unstructured financial tables in quotes and invoices into structured line-item data.
- Detecting relationships between document versions and related project files based on content similarity.
How doc-structurer Works
- Performs a primary classification by scanning the filename for specific keywords.
- Analyzes the frequency of category-specific terms within the document body to determine the likely document type.
- Evaluates structural patterns, such as the presence of tables, specific headers, or paragraph styles, to refine the classification.
- Triggers an LLM-based final review for the first 500 characters of the document if the internal confidence score falls below 0.7.
- Extracts defined metadata fields based on the identified document type, such as recipients, organizations, and financial figures.
- Normalizes all extracted data into a standardized JSON schema ready for export or further automation.
doc-structurer Setup
Ensure you have the required environment ready for Openclaw Skills processing.
# Verify Python 3 is installed
python3 --version
# Install the doc-structurer skill via the Openclaw CLI
openclaw install doc-structurer
Configuration involves setting up your LLM API keys if you require high-accuracy classification for ambiguous documents.
doc-structurer Data Schema & Taxonomy
The doc-structurer skill produces a detailed JSON output. The following table describes the primary data points captured:
| Field | Description | Type |
|---|---|---|
doc_id |
Unique identifier (UUID) | String |
doc_type |
Classified category (e.g., contract, proposal) | String |
summary |
A concise 3-line summary of the document | String |
dates |
Normalized dates for deadlines and events | Object |
priority |
Auto-calculated priority (High, Mid, Low) | String |
financial |
Extracted totals, currency, and line items | Object |
action_items |
List of tasks or required actions identified | Array |
doc-structurer Advanced Features
- Intelligent Confidence Scoring: Every classification includes a confidence value between 0.0 and 1.0 to ensure data integrity.
- Automatic Date Normalization: Converts diverse date strings (e.g., '2024.03.15', '24/03/15') into the standard YYYY-MM-DD format.
- Priority Auto-Determination: Automatically elevates document priority based on deadlines within 3 days or financial values exceeding specific thresholds.
- Document Relationship Mapping: Links related files by analyzing filename similarity and internal cross-references.
- Downstream Integration: Directly formats output for seamless use with other Openclaw Skills like notion-sync and calendar-sync.
SKILL.md
Loading
Related Openclaw Skills
TestDino Playwright CI Intelligence
Connects your AI agent to TestDino for natural language insights into Playwright CI test runs, failure patterns, and project health.
s-skill: Smart Code Assistant
An intelligent coding companion that provides deep code understanding, precise error diagnosis, refactoring suggestions, and automated documentation.
Web Browser Toolkit
A sophisticated multi-layered browsing engine designed for automated information gathering, data extraction, and real-time website monitoring.
Bid Proposal Manager
An intelligent bid and proposal management system that parses multi-format announcements, vectorizes content for semantic search, and automates Notion project creation.
Knowledge Consultant Agent Builder
A comprehensive framework for transforming domain expertise into professional, safe, and automated AI consulting agents on Feishu.
Calendar Sync
Automatically extracts deadlines, schedules, and events from structured document data to register them in Apple Calendar with intelligent alerts.
Featured*
