structured-data

What This Skill Does

The structured-data skill provides the OpenClaw agent with robust capabilities for handling tabular data formats and transforming them into actionable insights. It serves as an essential bridge between raw data files and human-readable reporting. The skill excels in parsing complex CSV files, even those with unconventional delimiters or embedded formatting issues. Beyond parsing, it facilitates seamless conversion from JSON objects back into standardized CSV formats, which is crucial for integrations with external spreadsheets or legacy systems. Additionally, the skill includes a powerful SVG chart generation engine that can visualize data arrays as bar, line, or pie charts, enabling the agent to communicate trends and statistics directly in the conversation flow.

Installation

To integrate this skill into your environment, run the following command within your terminal or CLI: clawhub install openclaw/skills/skills/paulgnz/xpr-structured-data Ensure you have the latest version of the ClawKit CLI to support dependency management for this repository.

Use Cases

• Automated Reporting: Extracting raw data from web scrapes and converting them into clean CSV deliverables for stakeholders.
• Business Intelligence: Quickly summarizing large CSV datasets and generating visual bar charts to identify sales trends or performance metrics.
• Data Migration: Transforming JSON-based API responses into CSV format for legacy system compatibility.
• Dashboarding: Creating visual representations of user engagement data extracted from JSON logs to include in final project summaries.

Example Prompts

1. "Parse this CSV data: [paste data here] and create a bar chart showing the growth trends across the last four quarters."
2. "Take this JSON array of user feedback and convert it into a formatted CSV file named 'feedback_summary.csv', ensuring only the 'user_id' and 'comment_score' columns are included."
3. "Analyze the provided CSV contents. Generate a line chart comparing the monthly revenue series and save the SVG for my report."

Tips & Limitations

• Large Datasets: When dealing with massive CSV files, use the limit parameter in parse_csv to avoid context window overflow; perform bulk processing inside execute_js instead.
• Data Integrity: While the CSV parser is highly adaptive to delimiters, always verify the schema column names if the input file has missing headers.
• Visualization: For complex multi-series charts, ensure your input objects are structured according to the multi-series schema documentation to prevent rendering errors.
• Combination Power: This skill is most effective when piped into store_deliverable to ensure processed files are saved as verifiable job evidence rather than just appearing as transient chat text.