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.