auditing

Validate XBRL numeric facts against calculation linkbases and taxonomies.

11|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/xueqingpeng/trading-analysis --skill auditing-xueqingpeng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auditing
Source: https://github.com/xueqingpeng/trading-analysis/tree/main/.claude/skills/auditing
Command: npx skills add https://github.com/xueqingpeng/trading-analysis --skill auditing-xueqingpeng

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 values in a filing's instance document against the "true" values 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/. Use this skill whenever the user asks to audit a filing, verify a reported XBRL value, compute a calculated value from linkbases, or check numeric consistency in a 10-K or 10-Q — even if they phrase it as "what is the reported value of X", "audit this concept", "check the filing math", or "verify AssetsCurrent for FY2021".

Core Features & Use Cases

  • The MCP-based auditing workflow locates filings, resolves contexts, navigates calculation networks, and validates results.
  • It supports sign-correction for monetary concepts and algebraic derivations using calculation-linkbase relationships, with provenance via MCP tools.
  • It emits a concise audit via the write_audit.py tool for auditable JSON output.

Quick Start

Audit a filing by locating it with find_filing, extracting the relevant facts with get_facts, building the calculation network with get_calculation_network, and writing the final JSON with write_audit.py.

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?

To audit XBRL numeric facts in SEC filings, locate the filing, extract relevant facts, build the calculation network, and validate reported values against computed true values derived from linkbases and US-GAAP taxonomy. The workflow outputs a concise auditable JSON record.

Can I verify reported values against US-GAAP taxonomy calculations?

Yes, you can verify reported values against US-GAAP taxonomy calculations by comparing instance document facts to algebraic derivations and summation recomputations from the calculation linkbase, applying XBRL sign conventions for directional concepts like expenditures and losses.

How does XBRL sign correction work for monetary concepts in 10-K or 10-Q filings?

XBRL sign correction for monetary concepts in 10-K or 10-Q filings works by checking balance-type attributes and applying sign conventions so directional concepts like expenditures and losses are positive. The workflow resolves contexts, matches periods, and flags sign errors or misstatements.

What is the best way to check numeric consistency across a defined filing period?

The best way to check numeric consistency across a defined filing period is to navigate the calculation network via MCP tools, extract facts with resolved contexts, and compare reported values to computed true values. The process identifies misstatements and writes a concise audit result.

Do I need MCP tools to validate XBRL data integrity?

Yes, you need MCP tools to validate XBRL data integrity. The workflow uses find_filing, get_facts, get_calculation_network, and get_concept_metadata to locate filings, resolve contexts, navigate relationships, and produce provenance-backed audit results written to a JSON file.

Why does my XBRL calculation linkbase recomputation mismatch the reported value?

An XBRL calculation linkbase recomputation mismatches the reported value when sign conventions for directional concepts are not applied, or when context resolution and period matching fail. The audit workflow checks balance types and algebraic derivations to identify the specific sign error or misstatement.