菜单
Complete flow from index creation to working vector search with Elasticsearch
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Debug and analyze LLM eval runs — view traces, compare runs, investigate failures, track costs. Use when debugging @kbn/evals failures, comparing eval runs, or analyzing LLM performance.
Start your security session with a personalized briefing — attacks, alerts, cases, rules, threat intel. Use as the first thing when starting security work.
Guide users from zero to a working Elastic cluster — Cloud or on-prem, connection config, first queries, and next steps.
Interactive guide for creating an APM service overview dashboard — discovers service data, presents metrics, and creates a tailored dashboard.
Interactive guide for creating SLOs from discovered APM and metric data — identifies candidates, lets user configure targets, and creates SLOs.
Create, configure, and manage Elasticsearch indices — mappings, settings, templates, data streams, and lifecycle policies.
| name | vector-search-setup |
| description | Complete flow from index creation to working vector search with Elasticsearch |
Use this skill when the user wants to add vector/semantic search to their application.
create_index with a mapping that includes a dense_vector field (dimensions match your model, e.g. 384 or 768).create_inference_endpoint for an embedding model (e.g. ELSER or a third-party endpoint).create_ingest_pipeline with an inference processor to embed text at index time if needed.index_document or bulk_index; ensure the vector field is populated (from app or pipeline).search tool with a knn query (or hybrid with a keyword query) to run vector search.search with a kNN query and confirm hits and scores.