Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    SEO Keyword Agent

    1

    A LangGraph-based SEO agent for keyword generation, semantic deduplication, and meta tag optimization.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    SEO Keyword Agent

    SEO Keyword Agent

    Example session with this skill installed

    Run the SEO keyword workflow for a 'Lavender Sleep Spray' made with essential oils for stressed professionals.

    • Read your context and instructions
    • Compiled the seo keyword agent

    The SEO keyword generation workflow has completed. I processed the product 'Lavender Sleep Spray' through the ingest, seed, expand, dedupe, and ranking nodes.

    SEO Keyword Research Report

    KeywordTypeIntentStatus
    lavender sleep sprayShort-tailTransactionalPrimary
    best essential oil for sleepLong-tailInformationalSecondary
    pillow spray for stress reliefLong-tailTransactionalSecondary
    natural aromatherapy for professionalsLong-tailCommercialSecondary
    organic lavender spray ingredientsLong-tailInformationalSecondary

    SEO Metadata

    • Meta Title: Best Lavender Sleep Spray | Natural Stress Relief for Professionals

    Meta Description: Experience deep relaxation with our organic Lavender Sleep Spray. Crafted with pure essential oils to help stressed professionals achieve better sleep naturally. Shop now.

    Next steps

    1. Review the dedupe logs to verify the similarity threshold used in ChromaDB.
    2. Export the ranked keywords to your production database via the FastAPI endpoint.
    3. Run make test to ensure the new keyword expansion logic remains stable.

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

    About this skill

    Keyword research often results in messy, overlapping lists that require manual cleaning. This skill provides a structured workflow to generate, deduplicate, and rank high-intent keywords while producing optimized meta tags.

    What it does

    • Seed generation produces high-intent core keywords from product data.
    • Keyword expansion creates long-tail variations and search questions.
    • Semantic deduplication uses HuggingFace embeddings and ChromaDB to remove similar terms.
    • Intent ranking scores and classifies keywords as short-tail or long-tail.
    • Meta optimization generates SEO-ready titles and descriptions based on the final list.

    How it works

    1. Input data is ingested, including product name, purpose, ingredients, and audience.
    2. Graph execution runs through the LangGraph workflow from seed to SEO nodes.
    3. Vector processing identifies duplicates by measuring semantic distance in ChromaDB.
    4. Validation ensures all output follows the defined Pydantic schemas.

    Frameworks & tools

    This skill interfaces with a Python 3.10+ stack including FastAPI, LangGraph, LangChain, HuggingFace Inference API, ChromaDB, and Sentence Transformers.

    Why this beats prompting it yourself

    Generic prompts often return repetitive keywords that lack technical SEO structure. This skill implements a multi-step LangGraph workflow with a dedicated vector database step for deduplication, ensuring unique and high-value results.

    Use cases

    • Build automated SEO pipelines for e-commerce product catalogs.
    • Debug semantic similarity thresholds in ChromaDB keyword clusters.
    • Extend LangGraph nodes to include search volume API integrations.
    • Generate metadata for large-scale content migrations.

    Known limitations

    Requires a HuggingFace Inference API key for embeddings and a running ChromaDB instance. It does not pull real-time search volume data from external providers like Ahrefs or Semrush.

    Requires HuggingFace Inference API access and ChromaDB. Does not integrate with live search volume providers like Ahrefs.

    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

    Requires

    GitHub
    Python
    macOS
    Git

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files

    Allowed Hosts

    github.com
    Listedtoday

    What's inside

    Frequently Asked Questions

    This skill automates the cleanup of keyword lists by using ChromaDB and HuggingFace embeddings to identify and remove terms that are semantically identical, preventing content cannibalization.

    The purchase includes the complete LangGraph workflow source code, Pydantic schemas for data validation, and a FastAPI wrapper for immediate deployment.

    You will need Python 3.10+, a HuggingFace Inference API key for generating embeddings, and a running instance of ChromaDB to handle vector storage.

    While the skill generates high-intent keywords and meta tags, it does not include real-time search volume or keyword difficulty metrics from third-party providers like Ahrefs or Semrush.

    Yes, the LangGraph-based architecture is modular, allowing you to easily add custom nodes for specific API integrations or proprietary SEO logic.

    The agent is designed to process product-specific data such as ingredients, purpose, and target audience to ensure the generated meta tags are relevant and conversion-oriented.

    New in Agents & Orchestration