Claude Code를 가르치는 Markdown 기반 기술로 REST API를 통해 Elasticsearch 클러스터와 상호 작용하는 방법. SDK 없음, 클라이언트 라이브러리 없음, MCP 서버 없음 - 그냥 curl 및 지식.

그것에 있는 것

| 파일 | 취급 상품| 인포메이션 | SKILL.md | Auth, search, CRUD, Bulk ops, index management, 클러스터 건강, ILM, ES|QL, ingest 파이프라인 | | references/query-dsl.md | Full Query DSL - bool, match, term, range, Nested, geo, wildcards, runtime 필드, search after | | references/aggregations.md | 미터, 버킷, 파이프라인 집계 - 플러스 SRE 패턴 (error rate, top-N 리더보드) |

설치

Claude Code는 GitHub URL에서 로컬 디렉터리의 기술을 로드합니다. 이 재포를 복제 한 다음 지원된 기술 위치 중 하나에 파일을 복사합니다.

선택권 A: 개인 기술 (모든 프로젝트에서 유효한)

선택권 B: 프로젝트 기술 (하나의 repo에서만 유효한)

프로젝트의 루트 디렉토리 안에:

그런 다음 .claude/skills/elasticsearch/] 디렉토리를 repo로 커밋하여 팀도 얻게 됩니다.

인증

Restart Claude 부호는, 그 후에 기술을 적재됩니다:

목록에서 elasticsearch을 볼 수 있습니다.

Elasticsearch Skill for Claude Code

A markdown-based skill that teaches Claude Code how to interact with Elasticsearch clusters via REST API. No SDK, no client library, no MCP server — just curl and knowledge.

What’s in it

Installation

Claude Code loads skills from local directories, not from GitHub URLs. Clone this repo, then copy the files to one of the supported skill locations.

Option A: Personal skill (available in all projects)

git clone https://github.com/davidgeorgehope/elasticsearch-skill.git
mkdir -p ~/.claude/skills/elasticsearch
cp elasticsearch-skill/SKILL.md ~/.claude/skills/elasticsearch/
cp -r elasticsearch-skill/references ~/.claude/skills/elasticsearch/

Option B: Project skill (available in one repo only)

From within your project’s root directory:

git clone https://github.com/davidgeorgehope/elasticsearch-skill.git /tmp/elasticsearch-skill
mkdir -p .claude/skills/elasticsearch
cp /tmp/elasticsearch-skill/SKILL.md .claude/skills/elasticsearch/
cp -r /tmp/elasticsearch-skill/references .claude/skills/elasticsearch/

Then commit the .claude/skills/elasticsearch/ directory to your repo so your team gets it too.

Verify

Restart Claude Code, then check the skill is loaded:

/skills

You should see elasticsearch in the list.

Note: Adding a GitHub URL to the skills array in ~/.claude/settings.json does not work. Skills must be local files — there is no remote fetching.

Configuration

Set your cluster credentials as environment variables before starting Claude Code:

export ES_URL="https://your-cluster.es.cloud.elastic.co:443"
export ES_API_KEY="your-base64-api-key"

Optionally, for Kibana API access:

export KIBANA_URL="https://your-cluster.kb.cloud.elastic.co:443"

No server to run, no dependencies to install, no Docker container to spin up.

Why a Skill and Not MCP?

This is a deliberate choice, not a limitation.

The token tax

MCP servers expose tools via JSON schemas that get injected into the LLM’s context window on every request. Anthropic’s own testing found that a modest five-server setup with 58 tools consumed ~55,000 tokens before the conversation even started. That’s your context window being eaten alive by tool definitions you might not even use.

A skill loads its main instructions only when triggered, and deeper reference files only when the LLM actually needs them. Progressive disclosure by design — not by workaround.

The full circle