auditing

Audit XBRL numeric facts against calculation linkbase and US-GAAP taxonomy values.

Updated May 3, 2026
One-click install
npx skills add https://github.com/CYP0630/agentic_benchmark_single_agent --skill auditing-cyp0630
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auditing
Source: https://github.com/CYP0630/agentic_benchmark_single_agent/tree/main/skills/auditing
Command: npx skills add https://github.com/CYP0630/agentic_benchmark_single_agent --skill auditing-cyp0630

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastmcp, pydantic, and includes scripts (resource) components.

What problem does it solve?

Audits XBRL numeric facts in SEC-style filings by comparing the reported (book) value from the instance document against the correct (true) value derived from the filing's calculation linkbase, US-GAAP taxonomy, and XBRL sign conventions. The correct value may be a summation recomputation, a sign correction for directional concepts (expenditures, losses must be positive), or an algebraic derivation. Handles fact extraction, context resolution, period matching, balance-type checking, and writing the final JSON result to results/auditing/.

Core Features & Use Cases

  • Audits XBRL numeric facts by validating reported values against computed true values from linkbases and taxonomy.
  • Supports period alignment, context resolution, and sign handling for directional concepts.
  • Outputs a single JSON audit record via the write_audit.py script for reproducible results.

Quick Start

Audit a filing's numeric fact by computing the true value from the calculation linkbase and taxonomy and compare it to the reported value.

Frequently Asked Questions about auditing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit XBRL numeric facts in SEC filings against the calculation linkbase?

To audit XBRL numeric facts in SEC filings, compare the reported book value from the instance document against the computed true value derived from the calculation linkbase and US-GAAP taxonomy. This validates summation recomputations, sign corrections, and algebraic derivations.

Why do XBRL calculations fail for directional concepts like expenditures and losses?

XBRL calculations fail for directional concepts like expenditures and losses when sign conventions are not applied. Auditing resolves this by checking balance types and enforcing sign corrections, ensuring these directional concepts are reported as positive values.

Can I output SEC filing audit results as a single JSON record?

Yes, you can output SEC filing audit results as a single JSON record. The auditing process uses a write_audit.py script to export one-line JSON results, capturing fact extraction, context resolution, and period matching into a reproducible file.

Does this auditing approach handle context resolution and period matching for XBRL facts?

Yes, this auditing approach handles context resolution and period matching for XBRL facts. It extracts facts from instance documents, aligns reporting periods, resolves contexts, and checks balance types before comparing reported values against computed true values.

What is the best way to validate US-GAAP taxonomy calculations in financial filings?

The best way to validate US-GAAP taxonomy calculations in financial filings is to audit XBRL numeric facts by recomputing summations from the calculation linkbase. This method compares reported values against algebraically derived true values, ensuring full compliance.