claude

search

Elasticsearch specialist layer: ES/Lucene performance, relevance (Korean nori), and vector/hybrid search pitfall hubs, review commands, and a user-invoked agent-team orchestrator

1 on GitHubby Dokkabei97v2.0.2Apache-2.0updated 16 days agodevelop
/

Plugin search from marketplace dokkabei-harness in Dokkabei97/dokkabei-harness. Commands read from the repo's manifest — 13 days ago.

What it installs

Skills (4)

  • es-deep-patterns

    Elasticsearch·Lucene 스페셜리스트 트리아지 허브 — 느린 쿼리·타임아웃·p99 튐, 샤드 크기·개수, 대량 색인(refresh·replicas·bulk), 매핑 폭발·keyword/doc_values·nested, terms 집계 오차, 깊은 페이지네이션, force merge·세그먼트, JVM 힙·서킷 브레이커·429, Kotlin/Java·Go 클라이언트·BulkIngester/BulkIndexer, 샤드 부분 실패, Kafka→ES 색인. 증상에서 ID 붙은 함정 항목으로 안내한다. Specialist tria

  • search-relevance-engineering

    검색 관련성·한국어 분석 허브 — 순위가 이상함·엉뚱한 결과·0건, nori 형태소(decompound_mode·사용자 사전·품사 필터), 동의어(synonym_graph·Synonyms API), 자동완성(edge_ngram·자모), BM25·multi_match·minimum_should_match, 점수 흔들림(샤드 IDF·preference), rescore·RRF·리랭커, _rank_eval·CTR 평가. 증상에서 ID 붙은 함정 항목(KO-*/ES-REL/ES-RNK/ES-EVL)으로 안내한다. Hub for search

  • search-team-orchestrator

    검색팀 오케스트레이터(사용자 호출 전용) — 영역이 겹치는 검색 작업을 전문 에이전트 3명에 병렬 분배하고 보고서 하나로 통합. Fans out cross-domain ES work to specialist agents and merges one report. Use when: running /search-team-orchestrator.

  • vector-hybrid-search-patterns

    벡터·하이브리드 검색 허브(Elasticsearch) — kNN 이 느림·재현율 낮음·필터 걸면 결과가 k보다 적음, dense_vector 메모리 산정(HNSW·int8/int4/BBQ 양자화), num_candidates·oversample, _source 벡터 제외, RRF·하이브리드 점수 융합, 한국어 임베딩(ELSER 영어 전용, E5 접두어). 증상에서 ID 붙은 함정 항목(VEC-*)으로 안내한다. Hub for Elasticsearch vector (kNN/HNSW/quantization) and hybrid (RRF

Slash commands (5)

  • /search:es-mapping-review

    Elasticsearch 매핑·분석기 리뷰 — 필드 타입·매핑 폭발·nested 비용·nori 체인과 재색인 필요 변경을 항목 ID(ES-MAP/KO)로 판정. Reviews ES mappings and analyzers, flags reindex-requiring changes. Use when: running /es-mapping-review.

  • /search:es-query-review

    Elasticsearch 쿼리 DSL·집계 비용 리뷰 — es-deep-patterns 항목 ID(ES-QRY/ES-AGG/LUC-EXE)로 판정하고 리라이트 제안. Reviews ES query DSL and aggregation cost by item ID. Use when: running /es-query-review.

  • /search:index-lifecycle

    인덱스 수명주기·색인 경로 점검 — 샤드 산정, ILM, 무중단 재색인 런북, Kafka/Spark→ES 색인 정합성(ES-SHD/ES-IDX/ES-ING). 구 /index-pipeline-check 통합. Shard sizing, ILM, reindex runbook, and ingestion-path checks. Use when: running /index-lifecycle.

  • /search:search-quality

    검색 품질 평가 설계 — 골든 질의셋, 판정 기준, _rank_eval 요청, 위치 편향을 고려한 온라인 지표. Designs golden sets, _rank_eval requests, and online metrics. Use when: running /search-quality.

  • /search:vector-search-review

    Elasticsearch 벡터·하이브리드 리뷰 — dense_vector 메모리 산정, 양자화, kNN 필터, RRF 융합, 임베딩 규약을 VEC 항목 ID 로 판정. Reviews vector/hybrid search with a memory estimate. Use when: running /vector-search-review.

Subagents (4)

  • es-query-optimizer

    Elasticsearch 쿼리·클러스터 성능 전문 에이전트 — 느린 쿼리·timeout·p99 튐을 _profile/hot_threads 로 절단, 쿼리 DSL·집계 안티패턴(필터 캐시, track_total_hits, 깊은 페이지, 스크립트 컴파일, terms 오차), 매핑 비용(keyword vs 숫자, nested/join, 매핑 폭발), 샤드 크기·세그먼트·force merge, JVM 힙·서킷 브레이커·429 진단. Specialist agent for Elasticsearch query and cluster perform

  • search-code-reviewer

    검색 서비스 Kotlin 코드 리뷰 전문가 — 테크 리드 스타일(완곡형+명령형 혼합, 근거+대안 제시, [Sug]/[Q]/[High] 태그). 네이밍/헥사고날 경계/DTO/Nullable/하드코딩/검색 도메인 관점에서 로컬 on-demand 리뷰 수행. 개발자가 작성 완료 후 PR 전 셀프 리뷰 용도로 명시 호출. Tech-lead-style Kotlin code reviewer for search services — gives rationale plus alternatives with [Sug]/[Q]/[High] tags, re

  • search-relevance-engineer

    검색 관련성·한국어 분석·벡터/하이브리드 전문 에이전트 — 무결과·순위 이상 원인 분석, nori 분석기·사용자 사전·동의어·자동완성 설계, BM25/multi_match 튜닝, rescore·RRF·리랭커, dense_vector 메모리·양자화·kNN 필터, _rank_eval 기반 품질 평가. Specialist agent for search relevance, Korean (nori) analysis, and vector/hybrid search on Elasticsearch. Use when: results are missi

  • search-service-architect

    Kotlin(Spring Boot)·Go 검색 서비스와 색인 파이프라인 설계 전문 에이전트 — Elasticsearch Java/Kotlin·go-elasticsearch 클라이언트 설정(트랜스포트·커넥션 풀·타임아웃·직렬화), bulk/BulkIngester/BulkIndexer 실패 분류, Kafka·Spark→ES 색인의 유실·중복·순서 역전, 재색인·alias 스왑, 회복 탄력성. Specialist agent for search-service architecture and ES ingestion pipelines. Use

View source on GitHub dokkabei97.github.io

More from Dokkabei97/dokkabei-harness

All 14 plugins →

workflow

claude

Development lifecycle workflows: project rules (AGENTS.md stack facts + specialist core for Claude Code, Codex and Antigravity; Claude path-scoped rules), spec/planning/shipping guides, MR review, handoff, release notes, retrospectives, and CLAUDE.md sync

11 skills · 3 commands · hooks

1

Shared backend specialist layer: PostgreSQL, Kafka, Valkey and distributed-call pitfalls, migration safety, DTO/serialization rules, plus user-invoked API design, docs, test, and perf commands

4 skills · 8 commands · 2 agents

1

analyze

claude

Comprehensive static analysis of code quality, performance, architecture, and SQL

4 skills · 4 commands · 3 agents

1

wiki-ops

claude

Operates a cited llm-wiki knowledge vault through gated feed, audit, curation-loop, and Q&A

7 skills · 3 agents

1

harness

claude

Meta-plugin for harness design (v2 execution modes), evolution, generation, validation, and lightweight loops

4 skills · 4 commands · hooks

1

base

claude

Foundational guard-hook & LSP layer for the loop harness

hooks · LSP

1

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

Maintain search?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins14 plugins