xml-reader

What This Skill Does

The xml-reader skill provides OpenClaw agents with the specialized capability to parse, traverse, and extract data from complex construction-related XML schemas. Designed specifically for the architecture, engineering, and construction (AEC) industry, this tool handles the hierarchical nature of P6 schedules (XER files), buildingSMART Data Dictionary (bsDD) exports, IFC-XML representations, and COBie-XML exchange formats. By leveraging a robust Python implementation based on xml.etree.ElementTree and pandas, the skill transforms nested XML structures into flattened, analysis-ready tabular formats. This allows users to perform quantitative analysis on project timelines, asset registers, and metadata exports without manually converting files or dealing with the overhead of schema-heavy XML parsing.

Installation

To integrate this skill into your environment, use the OpenClaw command-line interface. Ensure you have the necessary environment variables set for your agent profile:

clawhub install openclaw/skills/skills/datadrivenconstruction/xml-reader

Use Cases

• Project Schedule Analysis: Quickly extract activity IDs, finish dates, and resource assignments from Oracle Primavera P6 XML exports for comparison against project milestones.
• BIM Interoperability: Parse IFC-XML or COBie data to generate reports on asset counts, classification codes, and material types directly from BIM models.
• Data Standardization: Convert disparate vendor XML exports from buildingSMART Data Dictionary (bsDD) into consistent DataFrames for multi-source database integration.
• Automated Compliance Reporting: Audit construction submittals by scanning XML manifests for required metadata fields against organizational standards.

Example Prompts

1. "Read the schedule.xml file in my project folder and identify all tasks with a duration greater than 20 days that are scheduled to finish before Q3."
2. "Extract all entity types from this COBie XML export and organize them into a table showing the component name, manufacturer, and installation status."
3. "Convert the bsDD XML data provided in the attached file into a pandas DataFrame and highlight any items that lack a localized description field."

Tips & Limitations

• Namespace Management: The skill includes an automated namespace extractor, but deeply nested or unconventional XML schemas may require manual namespace mapping for precise element retrieval.
• Memory Constraints: While the library uses efficient streaming potential, loading extremely large IFC-XML files (>500MB) directly into memory may impact performance; for massive datasets, filter elements before full conversion.
• Data Flattening: The element_to_dict function converts attributes to dictionary keys. Ensure your source XML does not have conflicting attribute and child-element names, as child elements may override attributes during the transformation to a DataFrame.