Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    sec xbrl gaap reconciler

    1

    Extract and reconcile US GAAP financial statements from SEC XBRL filings using deterministic Python scripts.

    $14.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    sec xbrl gaap reconciler

    sec xbrl gaap reconciler

    Example session with this skill installed

    Extract the consolidated Operating Cash Flow and CapEx from data/tsla-20231231.xml and compute the Free Cash Flow.

    • Read your context and instructions
    • Compiled the sec xbrl gaap

    I have extracted the financial facts from the SEC filing and computed the Free Cash Flow using the deterministic metrics engine.

    SEC Financial Reconciliation

    MetricExtracted Value (USD)Source Concept
    Operating Cash Flow$13,256,000,000NetCashProvidedByUsedInOperatingActivities
    CapEx$8,895,000,000PaymentsToAcquirePropertyPlantAndEquipment
    Free Cash Flow$4,361,000,000Calculated (CFO - CapEx)
    {
      "metric": "free_cash_flow",
      "cfo": "13256000000",
      "capex": "8895000000",
      "free_cash_flow": "4361000000",
      "status": "reconciled"
    }
    

    Next steps

    1. Run python3 scripts/fin_metrics.py net_debt using the balance sheet facts from this filing.
    2. Verify the Retained Earnings roll-forward using the reconcile_balance_sheet command.
    3. Cross-reference these figures against the references/usgaap_concept_map.md to ensure correct concept mapping.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Financial statement analysis often suffers from LLM hallucinations and manual data entry errors. This skill automates the extraction and reconciliation of US GAAP data directly from SEC EDGAR XBRL filings using deterministic Python scripts.

    What it does

    • XBRL Extraction parses raw XML and JSON instance files to isolate consolidated US-GAAP line items.
    • Metric Computation calculates Free Cash Flow, Net Working Capital, Net Debt, and Effective Tax Rate using verified data.
    • Identity Validation runs mathematical checks on Balance Sheet equality and Cash Flow statement reconciliation.
    • Fact Verification isolates consolidated figures from dimensional segment disclosures to prevent double counting.

    How it works

    1. Locate Concepts by running xbrl_facts.py on a target filing to extract specific GAAP concepts like Revenues or Operating Cash Flow.
    2. Compute Metrics by feeding extracted values into fin_metrics.py for derived corporate finance calculations.
    3. Reconcile Statements to verify that Assets equals Liabilities plus Equity with zero mathematical discrepancy.
    4. Audit Roll-forwards to check Retained Earnings residuals and cash flow deltas.

    Frameworks & tools

    Python 3.9+ standard library. Uses localized scripts for XBRL parsing and financial math with no external API dependencies or paid keys.

    Why this beats prompting it yourself

    Generic prompts often hallucinate financial figures or fail to distinguish between consolidated totals and segment disclosures in complex XBRL trees. This tool uses deterministic execution to ensure every number is traced back to a specific filing fact without guesswork.

    Use cases

    • Extracting core financial line items from a 10-K instance file.
    • Calculating a company's Net Debt and Free Cash Flow for a financial model.
    • Auditing the mathematical accuracy of a balance sheet in a 10-Q filing.
    • Running a Retained Earnings roll-forward to verify period-over-period changes.

    Known Limitations

    Requires local SEC XBRL files as input. Does not scrape live SEC endpoints or provide stock valuation and investment advice.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.

    Runs offline and requires local XBRL/JSON filing files. Not for live web scraping or speculative investment advice. Requires Python 3.9+.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    Unlike LLMs that may hallucinate figures, this skill uses deterministic Python scripts to parse XBRL data, ensuring that every financial figure is mathematically reconciled and traced directly to the official SEC filing.

    The package includes the core XBRL extraction engine, a dedicated financial metrics calculator, and validation scripts for auditing balance sheets and cash flow statements.

    This skill is designed for AI agents with Python execution capabilities; it requires a Python 3.9+ environment and works best with agents that can handle local file inputs.

    No, the skill operates using a local Python execution environment and standard libraries, meaning you do not need to pay for external API keys or data provider subscriptions.

    The skill requires local SEC XBRL files (XML or JSON) as input; it does not currently include a built-in scraper to pull live data directly from the SEC EDGAR website.

    Yes, it is specifically programmed to isolate consolidated line items from segment disclosures, preventing the common error of double-counting figures from subsidiary or geographic data.

    New in Finance & Accounting