Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    numerical verification

    1

    A rigorous Python-based protocol to verify arithmetic, factorizations, and equations in mathematical documents.

    Free

    1 useSecurity scanned
    numerical verification

    numerical verification

    Example session with this skill installed

    Run a verification on the specimen S1 with N=1000, kernel=2, c=5, exponent=3, and claimed factors 2^3 and 5^3. Catch any internal typos.

    • Read your context and instructions
    • Compiled the numerical verification

    The verification script has processed specimen S1. A discrepancy was identified between the claimed factors and the reconstructed value of N.

    Numerical Verification Report: Specimen S1

    Check TypeStatusResultDetails
    Visual (V1)PASSc=5, exp=3Matches document source
    Textual (V2)FAIL843 vs 84³Detected ghost exponent in prose
    Computational (V3)PASS2^3 * 5^3 = 1000Calculation matches N
    Factor AuditPASSCompleteNo composite primes found
    ConsistencyFAILTypo FoundInline prose (1003) differs from table (1000)
    {
      "specimen": "S1",
      "status": "INCONSISTENT",
      "errors": [
        {
          "type": "1.1",
          "label": "Ghost exponent",
          "expected": 1000,
          "actual": 843,
          "context": "Inline text transcription error"
        }
      ],
      "reconstruction": {
        "N": 1000,
        "factors_valid": true,
        "formula": "2^3 * 5^3"
      }
    }
    

    Next steps

    1. Update the inline prose to match the ground truth table value of 1000.
    2. Regenerate the LaTeX source using the reference/GUIDE.md pipeline to avoid retyping.
    3. Re-run the verifier with the --json flag to confirm the fix across all 407 pairs.

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

    About this skill

    Mathematical documents, especially PDFs and scans, are notorious for silent extraction errors. A superscript 84³ often collapses into 843 during OCR, and composite numbers are frequently misidentified as primes in tables. This skill provides a rigorous protocol to ensure every integer, factorization, and equation in a technical document is internally consistent before you trust or publish it.

    What it does

    • Triple-verify arithmetic by cross-referencing visual PDF data, extracted text, and computational inverse calculations.
    • Detect extraction traps like ghost exponents, phantom subscripts, and parasitic leading digits that invalidate proofs.
    • Audit factorizations using a complete trial division method up to the square root to expose composite numbers posing as primes.
    • Resolve data conflicts between inline prose and specimen tables to identify the correct ground truth.
    • Generate audit reports in dual console and JSON formats for both human review and automated agent workflows.

    How it works

    1. Define the specimen by creating a spec.json file containing the claimed N, factors, kernel, and equation components.
    2. Execute the verifier using the Python script to run the internal consistency checks against your specimen.
    3. Analyze the report to identify any of the seven classic pitfalls, such as internal typos or inconsistent formulas.
    4. Export valid data once the triple-verification protocol achieves consensus across all data sources.

    Frameworks & tools

    The verifier is a standalone Python tool using only the standard library. It requires no external dependencies, ensuring high portability for researchers and automated auditing agents.

    Why this beats prompting it yourself

    LLMs frequently hallucinate large integer arithmetic and miss subtle OCR collapses like subscripts merging into variables. This skill enforces a deterministic Python-based audit that catches the specific mechanical failures of document extraction that manual prompting ignores.

    Use cases

    • Auditing math papers for arithmetic errors before publication or peer review.
    • Verifying Taxicab-style claims and large integer specimen tables.
    • Validating numbers extracted from old scans or low-quality technical PDFs.
    • Standardizing a LaTeX pipeline to prevent transcription errors.

    Known limitations

    This tool checks internal numerical consistency only. It does not verify the validity of logical proofs, the choice of formulas, or the semantic truth of mathematical claims.

    Checks internal consistency only. Does not verify proof logic or formula selection. Best suited for integer arithmetic and factorizations.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 26 days ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed26 days ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'silent OCR failures' where symbols like exponents or subscripts collapse into plain numbers during extraction, and it uses deterministic Python logic to verify large integer arithmetic that LLMs often hallucinate.

    You will receive the core Python verification script, a template for the `spec.json` input file, and comprehensive documentation on how to interpret the seven classic pitfall reports.

    The skill is a standalone Python tool designed for maximum portability; it can be integrated into any AI agent workflow that supports Python execution or used as a pre-processing step for document analysis.

    No, the tool relies exclusively on the Python standard library, meaning you don't need to install external packages like NumPy or SymPy to run the consistency checks.

    The verifier focuses on internal consistency and arithmetic accuracy; it does not analyze the underlying logical arguments or the conceptual validity of a mathematical proof.

    New in Research & Analysis