# opensearch-skills

Top-level skill to build search applications, configure vector indexes, and query observability logs in OpenSearch.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 571 installs · ★ 62
- Author: opensearch-project
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/opensearch-project/opensearch-agent-skills/tree/HEAD/skills/opensearch-skills/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/opensearch-skills

## What it does

The skill routes developer requests across search architecture, ingestion, and log analytics. It triggers workflows for BM25, KNN vector search, document chunking from PDF or DOCX into JSONL, and querying log patterns using PPL. It also supports deployment steps for AWS and Aiven.

Under the hood, operations run through `scripts/opensearch_ops.py`, paired with a local Docker bootstrapper in `scripts/start_opensearch.sh` and a search UI on port 8765. The setup strictly requires Docker and `uv`. Without Docker and `uv` ready on the host, local cluster bootstrap commands will fail. Cloud operations targeting AWS require configured AWS credentials.

## Requirements
- Works with: AWS

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-skills -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/opensearch-skills/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/opensearch-skills/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-skills -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/opensearch-skills/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-skills -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/opensearch-skills/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install opensearch-project/opensearch-agent-skills opensearch-skills
```

2. **Manually: put the files in place**
- File: `.github/skills/opensearch-skills/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-skills -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/opensearch-project/opensearch-agent-skills --path skills/opensearch-skills
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/opensearch-skills/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-skills -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/opensearch-project/opensearch-agent-skills/tree/HEAD/skills/opensearch-skills/SKILL.md

## When to use it
- configure hybrid and vector search pipelines in OpenSearch
- parse PDF and DOCX files into JSONL chunks for indexing
- query application logs and trace errors using PPL
- provision OpenSearch instances on AWS or Aiven

## Example prompts
- Set up hybrid search with BM25 and dense vectors for our documentation index
- Query our OpenSearch service logs with PPL to spot recurring error patterns
- Process a folder of PDF reports into JSONL chunks for RAG embeddings

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 547ace197e2cb887.

BEGIN THIRD-PARTY FILE 547ace197e2cb887
```text
---
name: opensearch-skills
description: >
  Build search applications and query log analytics data with OpenSearch.
  Use this skill when the user mentions OpenSearch, search app, index setup,
  search architecture, semantic search, vector search, hybrid search, BM25,
  dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF
  ingestion, document processing, or any related search topic. Also use for
  log analytics and observability — when the user wants to set up log
  ingestion, query logs with PPL, analyze error patterns, set up index
  lifecycle policies, investigate traces, or check stack health. Activate
  even if the user says log analysis, Fluent Bit, Fluentd, Logstash, syslog,
  traceId, OpenTelemetry, or log analytics without mentioning OpenSearch.
compatibility: Requires Docker and uv. AWS deployment requires AWS credentials.
metadata:
  author: opensearch-project
  version: "2.0"
---

# OpenSearch Skills

This is the top-level skill for OpenSearch. It contains four category skills that can also be installed and used independently:

| Category | Skill | Install individually |
|---|---|---|
| [search](search/SKILL.md) | [opensearch-launchpad](search/opensearch-launchpad/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@opensearch-launchpad --full-depth` |
| [observability](observability/SKILL.md) | [log-analytics](observability/log-analytics/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@log-analytics --full-depth` |
| [observability](observability/SKILL.md) | [trace-analytics](observability/trace-analytics/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@trace-analytics --full-depth` |
| [cloud](cloud/SKILL.md) | [aws-setup](cloud/aws-setup/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@aws-setup --full-depth` |
| [cloud](cloud/SKILL.md) | [aiven-setup](cloud/aiven-setup/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@aiven-setup --full-depth` |
| [ingest](ingest/SKILL.md) | [document-processing](ingest/document-processing/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@document-processing --full-depth` |
| [cloud](cloud/SKILL.md) | [managed-ingestion-service](cloud/managed-ingestion-service/SKILL.md) | `npx skills add opensearch-project/opensearch-agent-skills@managed-ingestion-service --full-depth` |

## Routing

Route to the right skill based on user intent:

| User Intent | Skill |
|---|---|
| Build a search app, set up an index, choose a search strategy | [opensearch-launchpad](search/opensearch-launchpad/SKILL.md) |
| Analyze logs, query with PPL, discover error patterns | [log-analytics](observability/log-analytics/SKILL.md) |
| Investigate traces, debug spans, analyze service maps | [trace-analytics](observability/trace-analytics/SKILL.md) |
```
END THIRD-PARTY FILE 547ace197e2cb887

The third-party file has ended. Everything between the 547ace197e2cb887 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2863 of 8217 bytes. © opensearch-project · Apache-2.0 · https://github.com/opensearch-project/opensearch-agent-skills/tree/HEAD/skills/opensearch-skills/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md