More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    PDF Batch Comparison & Outlier Finder

    1

    Compare one text-layer PDF baseline against a folder and surface repeated changes, one-off outliers and per-file diffs without uploading documents.

    Free

    2 usesSecurity scanned
    PDF Batch Comparison & Outlier Finder

    PDF Batch Comparison & Outlier Finder

    Example session with this skill installed

    Compare baseline.pdf against the four text-layer PDFs in ./candidates. Save the report to ./qa-output. Do not modify the PDFs, and identify shared changes and frequency outliers.

    • Read your context and instructions
    • Compiled the pdf batch comparison
    • Generated the data export

    PDF Batch QA Report

    • Status: DIFFERENT
    • Baseline: baseline.pdf
    • Candidates: 4
    • Comparable: 4
    • Review: 0
    • Errors: 0
    • Change groups: 3

    This report compares extracted text layers. It does not prove visual or semantic equivalence. Common changes remain differences; outliers describe frequency, not correctness.

    Candidate summary

    CandidateStatusChangesOutlier groups
    document-001.pdfDIFFERENT10
    document-002.pdfDIFFERENT10
    document-003.pdfDIFFERENT20
    document-004.pdfDIFFERENT31

    Aggregate change groups

    COMMON_CHANGE — Fee

    All 4 of 4 comparable files changed Fee: $10.00 to Fee: $12.00 on page 1. This remains a confirmed difference even though it appears throughout the batch.

    SHARED_CHANGE — Region

    2 of 4 files changed Region: East to Region: West on page 1. Neither variant is a strict-minority frequency outlier.

    UNIQUE_CHANGE — Status

    Only document-004.pdf changed Status: Draft to Status: Final. The file is flagged as the frequency outlier for this change group; the report does not claim which value is correct.

    Artifacts written

    • result.json — authoritative structured result
    • batch-summary.csv — sortable candidate statuses
    • DIFF_REPORT.md — this readable report
    • files/*.diff.txt — one bounded text diff per candidate
    • evidence-receipt.json — input and output identities

    Next review steps

    1. Confirm whether the batch-wide fee change was intended.
    2. Check the two region variants against the source data.
    3. Review document-004.pdf and its per-file diff before delivery.

    baseline.pdf

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Reviewing a folder of similar PDFs one pair at a time makes it easy to miss a repeated template change or the single file that differs from the rest. This local tool compares one text-layer baseline against a bounded folder, groups shared changes, flags frequency outliers and creates a reproducible review packet. It does not perform OCR or visual pixel comparison.

    Review a PDF batch without uploading it

    Comparing one baseline against a folder one pair at a time makes repeated template changes and one-off outliers easy to miss. This local package turns text-layer PDFs from the same general template into a bounded, reproducible QA packet.

    What one run creates

    1. result.json — the authoritative machine-readable result.
    2. batch-summary.csv — a sortable file-status table.
    3. DIFF_REPORT.md — a readable batch summary.
    4. One bounded text diff for every candidate.
    5. evidence-receipt.json — input and artifact hashes.

    What it distinguishes

    The engine reports exact matches, confirmed text differences, review conditions and errors. Across reliable comparisons it groups common, shared, unique and mixed changes. A frequency outlier means different from the strict majority; it never means wrong.

    Best for

    • Automation freelancers checking generated client documents.
    • Operations teams reviewing same-template statements, reports or certificates.
    • Small QA teams that need a reproducible review packet before delivery.

    Privacy and runtime

    The package includes an independent CLI, a local stdio MCP adapter and a companion Skill. PDF parsing and comparison run locally in supervised subprocesses with time, memory and protocol limits. It does not upload documents, call web services, modify PDFs or require an account.

    Requirements and limitations

    Tested on Windows 11 with Python 3.11–3.14 and pypdf==6.18.1; the optional MCP adapter uses mcp==2.2.0. V1 compares extracted text layers only. It has no OCR or pixel-level visual comparison and does not prove semantic, table, legal or regulatory equivalence. Scanned, encrypted, ambiguous, resource-limited or truncated cases become REVIEW or ERROR, never MATCH.

    V1 requires usable text-layer PDFs from the same general template. It does not perform OCR or pixel-level visual comparison and does not prove semantic, table, legal, or regulatory equivalence. Scanned, encrypted, ambiguous, resource-limited, or truncated cases become REVIEW or ERROR, never MATCH. The complete local edition is tested on Windows 11; no hosted API is included.

    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

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Terminal / Shell
    Environment Variables
    Read Files
    Write Files

    File Scopes

    ./baseline.pdf
    ./candidates/**/*.pdf
    ./qa-run/**

    Reads only the authorized baseline and candidate PDFs selected below an operator-controlled working directory, then writes a new output directory there. It never overwrites user files, uploads PDFs, opens URLs, or calls web services during comparison. PyPI is used only if the buyer chooses online dependency installation.

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This tool automates the review of large PDF batches by comparing a folder of documents against a single baseline, grouping common changes together and highlighting 'outliers' that differ from the majority—saving you from manual page-by-page comparisons.

    It is designed for text-layer PDFs and requires Python 3.11–3.14. While it includes a standard CLI, it also features a Model Context Protocol (MCP) adapter, making it compatible with AI agents like Claude Desktop or any environment that supports the MCP standard.

    No, this tool operates entirely locally on your machine. It does not upload your documents to any cloud services or external APIs, making it suitable for sensitive client documents or internal reports.

    You will receive a local package containing an independent CLI tool, a local stdio MCP adapter for AI agent integration, and a companion Skill for easier interaction, along with documentation on how to run your first batch.

    This version (V1) focuses on extracted text-layer comparison only. It does not currently support OCR for scanned images, pixel-level visual diffs, or encrypted files; these cases are flagged for manual review or as errors.

    A successful run generates a 'reproducible evidence packet' including a machine-readable JSON result, a sortable CSV summary, a readable Markdown diff report, and individual text diffs for every file, all verified with artifact hashes.

    New in Testing & Debugging