Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    PDF & Image Spell Checker

    1

    Proofread English and French text in print artwork using multi-layered OCR and dictionary verification.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    PDF & Image Spell Checker

    PDF & Image Spell Checker

    Example session with this skill installed

    Please run a text preflight on the attached 'Summer_Festival_Banner_v2.pdf'. I've also attached 'client_dict.csv' for brand names. Report all findings for page 1.

    • Read your context and instructions
    • Compiled the pdf & image
    • Generated the data export

    I have completed the text preflight for the requested artwork. The analysis compared native text extraction with OCR and visual inspection of the rendered page.

    Preflight Report: Summer_Festival_Banner_v2.pdf

    FieldDetail
    File NameSummer_Festival_Banner_v2.pdf
    ScopePage 1 of 1
    LanguagesEnglish, French
    Dictionaryclient_dict.csv (Loaded)
    StatusERROR
    CoverageComplete (Native, OCR, and Visual)

    Priority Findings

    PageRegionObserved TextSuggestionSeverityReasonSource
    1HeaderGrand OpenningGrand OpeningERRORDictionary match: common_mistakeOCR
    1FooterSaint-EtieneSaint-ÉtienneWARNINGDictionary match: common_mistakeNative
    1Main BodyEntertainementEntertainmentERROREnglish spelling errorVisual
    1SubtextJulliet 2024Juillet 2024ERRORFrench spelling errorOCR

    Technical Limitations

    • Native extraction returned zero text for the header (likely outlined fonts); results derived from OCR and visual inspection.
    • QR code present in bottom-right corner was not scanned for URL validity.

    Next steps

    1. Correct the spelling of "Opening" and "Entertainment" in the source design file.
    2. Verify the spelling of "Saint-Étienne" as the dictionary flagged the current version as a common mistake.
    3. Perform a final human sign-off on the layout before sending to print.

    Summer_Festival_Banner_v2.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

    Catching a typo on a thousand-copy print run is an expensive mistake. This skill provides a technical preflight check for French and English text within PDF, PNG, and JPEG artwork, using a multi-layered approach to verify what is actually visible on the page. It bridges the gap between native text extraction and visual reality to ensure that outlined text, rasterized layers, and hidden objects don't hide critical errors.

    What it does

    • Multi-source extraction compares native PDF text layers against OCR and visual evidence to find discrepancies.
    • Bilingual proofreading detects spelling, grammar, and agreement errors in both English and French.
    • Dictionary enforcement applies custom client-supplied CSV dictionaries to respect brand-specific spelling or forbidden terms.
    • Coverage tracking monitors exactly which regions and pages were successfully analyzed to prevent false positives from unreadable areas.
    • Structured reporting generates page-specific findings with severity levels and evidence sources.

    How it works

    1. Load artwork by providing a PDF or image file and an optional CSV dictionary of brand terms.
    2. Execute extraction where the agent runs native text extraction, page rendering, and OCR in parallel.
    3. Analyze content to identify language, check spelling, and compare findings against the dictionary.
    4. Review status via a report that flags issues as ERROR, WARNING, or INFO based on evidence.

    Frameworks & tools

    Works with standard file-reading and OCR tools available to the host agent. It processes PDF, PNG, and JPEG formats natively without external API calls or specialized print-industry software.

    Why this beats prompting it yourself

    Generic prompts often hallucinate text or miss mistakes hidden in rasterized layers. This skill forces a systematic comparison between OCR and native text, ensuring the agent doesn't "correct" a visible typo just because it knows the right spelling.

    Use cases

    • Proofing signage for banners and posters where outlined fonts might skip standard spellcheckers.
    • Marketing collateral review for French/English bilingual brochures to ensure linguistic consistency.
    • Packaging checks against a client-approved dictionary to verify technical terms and product names.

    Known limitations

    Does not check ink coverage, bleed, color profiles, resolution, or PDF/X compliance. It cannot verify the factual accuracy of URLs, phone numbers, or prices without a reference document.

    No support for color, bleed, resolution, or PDF/X certification. Limited to English and French. Requires host OCR/image capabilities. Cannot factually verify URLs or phone numbers.

    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

    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 today

    Permissions

    Network Access
    Listedtoday

    What's inside

    Frequently Asked Questions

    Unlike standard spellcheckers, this skill uses OCR to 'see' text that has been converted to outlines or rasterized into images, which often bypasses native text extraction. It then cross-references this visual data with the PDF layer to ensure what is printed matches the intended content.

    This skill is a logical workflow compatible with any AI agent host that supports file-reading and OCR capabilities. It does not require external print-industry software or proprietary API subscriptions to function.

    Yes, you can provide a custom CSV dictionary to ensure the agent recognizes brand-specific terminology, product names, or industry jargon that would otherwise be flagged as errors.

    You will receive the complete logic flow, tool requirements, and structured reporting schema for the skill. This includes the multi-layered verification process and the scoring system for ERROR, WARNING, and INFO flags.

    The skill supports English and French text, including specific linguistic checks for grammar and agreement in both languages. It is particularly effective for bilingual marketing materials where consistency is critical.

    This skill focuses exclusively on text accuracy and linguistic proofreading. It does not analyze technical print specifications like CMYK color profiles, bleed margins, or image resolution.

    New in Technical Documentation