Extract and validate payslip data from the MCP Buste Paga server.
npx skills add https://github.com/morettimarco/MCP-Buste-Paga --skill bustepagamcpskill
Please help me install this Agent Skill. Skill: BustePagaMCPSKILL Source: https://github.com/morettimarco/MCP-Buste-Paga/tree/main Command: npx skills add https://github.com/morettimarco/MCP-Buste-Paga --skill bustepagamcpskill
The MCP Buste Paga payslip interpretation skill provides a structured, auditable way to understand and validate payslip data stored in the MCP server, ensuring accurate payroll and tax calculations for compliant payroll analysis.
Invoke get_payslip_details_tool for the target month and run the nine validation checks from the interpretation guide to confirm accuracy.
High-intent search queries and answers about installing and using this skill.
To validate INAZ payslip data, you extract structured information from the MCP Buste Paga server and run a nine-step validation workflow to check tax chains, rounding, and conguaglio for discrepancies. This process enforces strict tax and social contribution rules to flag anomalies for manual review.
The best way to cross-check payslip items across multiple months is to use keyword-based item searches combined with salary history retrieval. This allows you to validate consistency and detect anomalies across different periods to ensure overall data integrity.
Payslip validation handles IRPEF and INPS tax chain discrepancies by decoding line items and enforcing strict tax and social contribution rules. It provides a transparent framework that explicitly signals errors and flags discrepancies for manual review.
Yes, you can retrieve employee profiles and salary history from the MCP server. The skill supports scenarios for extracting structured, auditable payslip data including get_employee_summary and get_salary_history_tool to validate payroll consistency.
When interpreting single payslip details, limitations include potential rounding errors and conguaglio discrepancies that require manual review. The skill explicitly signals these anomalies during the nine validation checks rather than auto-correcting them.
ThomazRossitoManage Databricks workspace profiles and authentication via the Python SDK.
UnicornAnalyze tabular CSV, JSON, and spreadsheet datasets to produce statistical summaries, anomalies, and visualizations.
aviskaarManage employee and contractor compensation flows, including payroll runs and compliance.
nikhillinitValidate XIRR and fee calculations against Excel parity and truth cases.
