Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    SharpSearch — Universal Codebase & PDF Intelligence

    1

    Ultra-fast token-saving search across any codebase (TS, Python, Go, C#, Rust), intelligent code compression, and deep PDF document inspection via MCP.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    SharpSearch — Universal Codebase & PDF Intelligence

    SharpSearch — Universal Codebase & PDF Intelligence

    Example session with this skill installed

    Search the codebase for the 'ProcessOrder' method and show me the implementation, including any related call sites in the workspace.

    • Read your context and instructions
    • Compiled the sharpsearch

    I have searched the codebase for the ProcessOrder method. I found the primary definition in the OrderService.cs file and identified several call sites where this method is invoked.

    Search Results and Call Graph

    File PathMatch TypeLineContext
    src/Services/OrderService.csDefinition42public async Task ProcessOrder(OrderRequest request) { ... }
    src/Controllers/OrderController.csCall Site88await _orderService.ProcessOrder(payload);
    src/Jobs/RetryOrderJob.csCall Site15_service.ProcessOrder(failedOrder);
    tests/OrderServiceTests.csReference104var result = await service.ProcessOrder(testOrder);

    Code Snippet: src/Services/OrderService.cs (Lines 42-50)

    public async Task ProcessOrder(OrderRequest request)
    {
        _logger.LogInformation("Processing order {OrderId}", request.Id);
        var validationResult = await _validator.ValidateAsync(request);
        
        if (!validationResult.IsValid)
        {
            throw new ValidationException(validationResult.Errors);
        }
        // ... logic continues
    

    Next steps

    1. Review the validation logic in OrderService.cs to ensure it covers new business rules.
    2. Inspect OrderRequest.cs if you need to see the schema for the request parameter.
    3. Run search_related on _validator to see which specific validation rules are being applied.

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

    About this skill

    Codebase navigation and document inspection often waste thousands of tokens on irrelevant boilerplate or massive files. This skill provides a high-performance MCP interface to search local codebases, reverse-engineer NuGet packages, and extract structured data from PDF documents.

    What it does

    • Token-efficient search executes BM25 or regex queries to find symbols and snippets without loading entire files.
    • NuGet decompilation reverse-engineers compiled .NET assemblies into readable C# source code.
    • Code compression strips comments and whitespace to fit large logic blocks into tight context windows.
    • PDF intelligence extracts text, bookmarks, hyperlinks, and form fields from complex documents.
    • Visual rendering converts PDF pages and embedded raster images into high-resolution PNGs for vision-capable models.

    How it works

    1. Locate specific symbols or keywords across the workspace using the search tool to get precise line numbers.
    2. Inspect external dependencies by passing NuGet package names to decompile_type for implementation details.
    3. Analyze large documents by first checking get_pdf_info and then streaming specific page ranges or rendering visual charts.

    Frameworks & tools

    Built for the .NET ecosystem using the PuneethDC.DotNetSearch global tool. It integrates via Model Context Protocol (MCP) to work with Claude Desktop, Cursor, and other MCP-compliant agents.

    Why this beats prompting it yourself

    Manual file reading consumes massive amounts of context and often hits token limits on large C# projects. This skill automates targeted retrieval and decompilation, giving you access to third-party library internals that are otherwise invisible to the agent.

    Use cases

    • Navigating massive legacy .NET repositories to trace call chains and symbol definitions.
    • Reverse-engineering NuGet libraries when documentation is missing or outdated.
    • Extracting technical diagrams and tables from architectural PDFs for analysis.
    • Reducing token costs by compressing source code before final processing.

    Known limitations

    Requires the PuneethDC.DotNetSearch global .NET tool installed on the host machine. Decompilation is limited to .NET assemblies and NuGet packages.

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

    Requires PuneethDC.DotNetSearch .NET global tool installed. Decompilation supports .NET assemblies only. Large PDF operations should be chunked to avoid context overflow.

    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 17 days ago

    Permissions

    Terminal / Shell
    Read Files
    Listed17 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the 'context window' problem by using high-efficiency search and code compression, ensuring you only feed the AI relevant code rather than wasting tokens on boilerplate or entire files.

    Yes, the skill includes a NuGet decompilation tool that allows the AI to reverse-engineer compiled assemblies into readable C# source code, filling the gap when external documentation is missing.

    It is fully compatible with any Model Context Protocol (MCP) host, including Claude Desktop and Cursor, provided you have the PuneethDC.DotNetSearch global tool installed on your machine.

    Beyond text extraction, it can render PDF pages and embedded images into high-resolution PNGs, allowing vision-capable models to analyze technical diagrams and charts directly.

    You receive the MCP configuration and access to the toolset; however, you must have the .NET SDK installed to run the required 'PuneethDC.DotNetSearch' global tool on your host system.

    New in APIs & Backend