Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Network Diagram Generator

    1

    Generate Mermaid network diagrams and identify single points of failure from raw Cisco/Arista discovery data.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Network Diagram Generator

    Network Diagram Generator

    Example session with this skill installed

    Process these three Cisco show cdp neighbors detail files and generate a Mermaid diagram. Identify any single points of failure in the topology.

    • Read your context and instructions
    • Compiled the network diagram generator

    I have processed the discovery data from dist-sw-01.txt, access-01.txt, and access-02.txt. The link parser successfully resolved 4 distinct physical links and normalized interface names across all devices.

    Network Topology and Risk Analysis

    Device/LinkRoleStatusRisk Factor
    dist-sw-01DistributionArticulation PointLoss isolates all access layer switches.
    access-01AccessRedundantDual-homed to distribution block.
    access-02AccessSingle UplinkOnly connected via Gi0/1 to dist-sw-01.
    Link: dist-sw-01:Gi0/2 <-> access-02:Gi0/1UplinkBridgeCritical link; no alternative path exists.
    graph TD
        subgraph Core
            dist-sw-01[dist-sw-01]
        end
        subgraph Access
            access-01[access-01]
            access-02[access-02]
        end
        dist-sw-01 ---|Gi0/1 <-> Gi0/1| access-01
        dist-sw-01 ---|Gi0/2 <-> Gi0/1| access-02
        dist-sw-01 ---|Gi0/3 <-> Gi0/2| access-01
    

    Next steps

    1. Review the Bridge link identified between dist-sw-01 and access-02 for physical redundancy.
    2. Run the Graphviz export command to generate a high-resolution SVG for your internal Wiki.
    3. Add discovery data from your secondary distribution switch to verify cross-stack EtherChannels.

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

    About this skill

    Network documentation often lags behind reality, leaving teams blind during outages. This skill reconstructs your actual network topology from raw discovery data, identifying structural weaknesses before they cause downtime.

    What it does

    • Normalizes discovery data by processing raw CLI output from Cisco, Arista, and Linux devices into a unified link map.
    • Deduplicates links by merging bidirectional neighbor information and resolving device name inconsistencies.
    • Generates visual diagrams in Mermaid and Graphviz formats, automatically layered from core to access.
    • Performs graph analysis to pinpoint single points of failure, including articulation points and bridges.
    • Identifies edge risks by listing devices that rely on a single uplink.

    How it works

    1. Input collection: Provide raw text files containing show cdp neighbors detail or show lldp neighbors detail outputs.
    2. Processing: The skill normalizes interface names and strips domain suffixes to match device pairs.
    3. Analysis: It builds a graph model to calculate connectivity and redundancy metrics.
    4. Export: It generates .mmd files for Markdown-ready rendering and .dot files for high-resolution SVG exports.

    Frameworks & tools

    Built for network engineers using Cisco IOS, Arista EOS, or Linux lldpd. Outputs compatible with GitHub, GitLab, Notion, and Graphviz.

    Why this beats prompting it yourself

    Manual prompting often fails to reconcile "Gig0/1" on one side with "GigabitEthernet 0/1" on the other, leading to broken diagrams. This skill handles link deduplication and graph-theory analysis that standard LLMs struggle to perform reliably on large datasets.

    Use cases

    • Auditing data center redundancy to find hidden single points of failure.
    • Generating up-to-date topology maps for disaster recovery documentation.
    • Visualizing complex VLAN or physical link layouts during hardware migrations.

    Known limitations

    Requires specific CLI neighbor detail formats or a structured links CSV. Does not support non-standard proprietary discovery protocols outside of CDP and LLDP.

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

    Requires standard CDP/LLDP detail output or CSV. Logic assumes a hierarchical network structure for optimal layering. Validation requires external Mermaid/Graphviz binaries.

    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 1 month ago

    Permissions

    Terminal / Shell
    Environment Variables
    Listed1 month ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    The skill supports raw CLI text output from Cisco IOS (CDP/LLDP), Arista EOS, and Linux `lldpd`. It can also process structured link data in CSV format if your discovery tools use a custom schema.

    Standard LLMs often duplicate links when one device calls an interface 'Gi0/1' and the other calls it 'GigabitEthernet 0/1'. This skill uses a normalization engine to reconcile these naming differences and build an accurate, deduplicated graph.

    The skill identifies 'Articulation Points' and 'Bridges'—critical nodes or links where a single failure would partition the network. It also highlights edge devices that lack redundant uplinks.

    You will receive the AI agent skill configuration, optimized processing logic for network data, and templates for Mermaid and Graphviz exports. It is designed to be compatible with major AI agent platforms that support file uploads or text-based data processing.

    No, this skill is designed for 'offline' analysis of discovery data. You simply paste your CLI output or upload the text files; there is no need to grant the AI direct access to your production network hardware.

    New in DevOps & Cloud