Run an apples-to-apples benchmark of two embedding models on a fixture or your KB and produce an HTML report covering cold-start indexing, warm-query latency, batch throughput, storage, and quality.
$npx -y skills add jeanibarz/knowledge-base-mcp-server --skill compare-embedding-modelsInstalls into the current project.
Run `npx skills use "https://github.com/jeanibarz/knowledge-base-mcp-server" --skill "jeanibarz/knowledge-base-mcp-server/compare-embedding-models"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/jeanibarz/knowledge-base-mcp-server" that are relevant to the current task. Run `npx skills add "https://github.com/jeanibarz/knowledge-base-mcp-server"` and select the relevant skills, then follow their instructions.