Expanso Keyword Extract

What This Skill Does

The Expanso Keyword Extract skill, developed by aronchick, is a powerful utility designed to transform raw, unstructured text into structured metadata. By leveraging the Expanso Edge runtime, this skill automatically identifies and pulls out significant keywords, salient entities, and critical phrases. This process is essential for streamlining SEO optimization, automating content tagging, and improving the accuracy of document indexing. Whether you are dealing with massive datasets or individual blog posts, this skill acts as a natural language processing bridge, allowing you to categorize content programmatically without manual intervention. It is built to operate both as a standalone CLI tool for quick processing and as an MCP server for integrated agentic workflows.

Installation

To integrate this skill into your environment, ensure you have the expanso-edge binary installed and accessible in your system PATH. Once the prerequisite is met, you can install the skill directly through the OpenClaw ecosystem by running the following command in your terminal: clawhub install openclaw/skills/skills/aronchick/expanso-keyword-extract. This command fetches the necessary pipeline configurations and dependencies. If you prefer to deploy this within a managed cloud environment, you can use expanso-cli job deploy https://skills.expanso.io/keyword-extract/pipeline-cli.yaml to push the job to Expanso Cloud, enabling scalable, offloaded processing for your text analysis needs.

Use Cases

This skill is ideal for several scenarios: 1. Content Strategy: Automatically generate metadata tags for blog posts and articles to improve search engine rankings. 2. Information Retrieval: Index large document repositories by extracting thematic keywords, making search functionality within your application significantly more robust. 3. Data Classification: Sort and categorize incoming customer feedback or emails by identifying recurring topics or issues. 4. Academic Research: Rapidly summarize the focus of research papers by identifying key terminology and subject areas.

Example Prompts

1. "Analyze the following blog post about quantum computing and extract the top 10 keywords for SEO tagging: [insert text]."
2. "Extract all relevant entities and key phrases from this customer support ticket to help me route it to the correct department: [insert text]."
3. "Scan this technical documentation snippet and provide a list of primary technologies mentioned so I can index it for my internal search engine: [insert text]."

Tips & Limitations

To get the best results, ensure your input text is cleaned of unnecessary HTML tags or boilerplate content before processing. While the skill is highly efficient at identifying prominent terms, it may require context for highly specialized jargon; providing a brief preamble about the subject matter can improve accuracy. Note that the skill relies on the Expanso Edge runtime, so ensure your edge configurations are updated regularly to benefit from underlying model improvements. It is not designed for full-document summarization, but rather for concise keyword extraction; for deeper sentiment analysis or summarization, consider chaining this skill with other OpenClaw specialized models.