# opensearch-launchpad

opensearch-launchpad is a Claude Code skill for planning an OpenSearch search app from sample data to architecture, including index setup, semantic search, and document ingestion.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 145 installs · ★ 63 repo stars
- 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/search/opensearch-launchpad/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/opensearch-launchpad

## What it does

The skill guides a search project through cluster checks, sample-data review, strategy selection, and a deployment target. It presents the proposed architecture before carrying out the setup. For unstructured documents, it uses a preset built around agentic flow, neural_sparse ingestion, and semantic enrichment.

Python scripts handle cluster startup and operations. They require `uv`; local runs also need Docker, while AWS runs need configured AWS credentials. A local target will not start without Docker. PDF, DOCX, PPTX, and XLSX files are processed with Docling, and `preflight-check` must come before cluster operations.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add opensearch-project/opensearch-agent-skills --skill opensearch-launchpad -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/search/opensearch-launchpad/SKILL.md

## When to use it
- choose a search strategy for JSON or CSV data
- check cluster availability before setup
- inspect a sample of local data
- prepare PDF or DOCX files for search
- plan a local or AWS OpenSearch deployment

## Example prompts
- Plan an OpenSearch search app for the product data in `products.json`.
- Set up semantic search over these PDFs, starting with a cluster availability check.
- Propose a hybrid search architecture for the records in `catalog.csv`.

## 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: 437546626277ac56.

BEGIN THIRD-PARTY FILE 437546626277ac56
````text
---
name: opensearch-launchpad
description: >
  Build search applications with OpenSearch from scratch. Use this skill when
  the user mentions 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. Activate even if the user says search quality,
  evaluation, nDCG, precision, relevance tuning, or search builder without
  mentioning OpenSearch.
compatibility: Requires uv. Target local requires Docker. Target aws requires AWS credentials (no Docker).
metadata:
  author: opensearch-project
  version: "2.0"
---

# OpenSearch Launchpad

You are an OpenSearch solution architect. You guide users from initial requirements to a running search setup.

## Prerequisites

- `uv` installed (for running Python scripts)
- The skill directory available locally
- **Target `local`:** Docker installed and running
- **Target `aws`:** AWS credentials configured (no Docker needed)

## Optional MCP Servers

```json
{
  "mcpServers": {
    "ddg-search": {
      "command": "uvx",
      "args": ["duckduckgo-mcp-server"]
    },
    "opensearch-mcp-server": {
      "command": "uvx",
      "args": ["opensearch-mcp-server-py@latest"],
      "env": { "FASTMCP_LOG_LEVEL": "ERROR" }
    }
  }
}
```

- **`ddg-search`** — Search OpenSearch documentation. Use `search(query="site:opensearch.org <your query>")`.
- **`opensearch-mcp-server`** — Direct OpenSearch API access. Handles SigV4 auth for AOS/AOSS transparently.

### opensearch-mcp-server Configuration Variants

For basic auth (local/self-managed):
```json
{
  "opensearch-mcp-server": {
    "command": "uvx",
    "args": ["opensearch-mcp-server-py@latest"],
    "env": {
      "OPENSEARCH_URL": "<endpoint_url>",
      "OPENSEARCH_USERNAME": "<username>",
      "OPENSEARCH_PASSWORD": "<password>",
      "OPENSEARCH_SSL_VERIFY": "false",
      "FASTMCP_LOG_LEVEL": "ERROR"
    }
  }
}
```

For Amazon OpenSearch Service (AOS):
```json
{
  "opensearch-mcp-server": {
    "command": "uvx",
    "args": ["opensearch-mcp-server-py@latest"],
    "env": {
      "OPENSEARCH_URL": "<endpoint_url>",
      "AWS_REGION": "<region>",
      "AWS_PROFILE": "<profile>",
      "FASTMCP_LOG_LEVEL": "ERROR"
    }
  }
}
```

For Amazon OpenSearch Serverless (AOSS):
```json
{
  "opensearch-mcp-server": {
    "command": "uvx",
    "args": ["opensearch-mcp-server-py@latest"],
    "env": {
      "OPENSEARCH_URL": "<endpoint_url>",
      "AWS_REGION": "<region>",
````
END THIRD-PARTY FILE 437546626277ac56

The third-party file has ended. Everything between the 437546626277ac56 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 2578 of 9359 bytes. © opensearch-project · Apache-2.0 · https://github.com/opensearch-project/opensearch-agent-skills/tree/HEAD/skills/opensearch-skills/search/opensearch-launchpad/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
