Catmcp Data Analysis

What This Skill Does

Catmcp Data Analysis is a specialized AI-driven data intelligence agent designed for the CatLab ecosystem. It acts as a professional, rigorous analytical consultant that bridges the gap between raw MongoDB databases and actionable insights. By strictly adhering to a built-in Thinking Protocol, the skill ensures that all queries—whether simple data retrieval or complex statistical trend analysis—are executed with high precision, security, and efficiency. It serves as your primary interface for interacting with system data, including user communication logs, transaction histories, and platform configurations.

Installation

To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/beelkic/catmcp-data-analysis

Use Cases

• Deep Business Insights: Conduct complex trend analysis on user engagement, such as message volume fluctuations over time in the Whisper_Mail collection, without manual calculation.
• Operational Audits: Retrieve specific system configuration details or monitor user wallet history (CatLab_Wallet_History) to verify transactions or activity rewards.
• Content & Achievement Tracking: Aggregate statistics on contributions, article engagement, or track the redemption status of Gift_Codes across the platform.
• Cross-Collection Correlation: Connect disparate data points, such as linking user whisper IDs to specific reply contents or correlating platform activity to individual wallet interactions.

Example Prompts

• "Can you generate a monthly trend report for user messages received in the Whisper_Mail collection for the last quarter?"
• "I need to know how many gift codes have been redeemed in the last 30 days and what the distribution of rewards looks like."
• "What is the current balance status of users who have participated in the most recent system achievement events?"

Tips & Limitations

• Thinking Protocol: Always allow the agent to perform an inspect_collection_sample before running complex queries to ensure it understands the current schema.
• Performance Efficiency: The skill is optimized to perform calculations directly within the database (MongoDB Pipeline). Avoid requesting raw data dumps for local processing to stay within token and performance limits.
• Data Integrity: Never guess schema structures. If a collection field name is updated, the agent will verify it via inspection.
• Security: The agent enforces a maximum query limit of 100 records and strictly maintains privacy by avoiding the exposure of full sensitive documents unless explicitly requested as a 'detail' view.