📦

search-engineer

Name: search-engineer
Author: zl2023github

Ревизия содержимого r2 Безопасно ⚙️ Внешние команды🌐 Доступ к сети

Build and Optimize Search Systems

Search teams need reliable guidance across indexing, ranking, semantic retrieval, and evaluation. This skill provides practical workflows and examples for building and improving search systems.

Поддерживает: Claude Codex Code(CC)

🥉 77 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

Review the Skillstore skill "search-engineer" from https://skillstore.io/skills/zl2023github-search-engineer.md and its manifest at https://skillstore.io/api/skills/zl2023github-search-engineer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/zl2023github-search-engineer.md Подписанный manifest GET /api/skills/zl2023github-search-engineer/manifest Подписанный lockfile GET /api/skills/zl2023github-search-engineer/lockfile

Протестировать

Использование «search-engineer». Recommend a search architecture for two million Chinese product records with filters and semantic queries.

Ожидаемый результат:

Use Elasticsearch for structured filters and lexical recall, plus a vector field for semantic retrieval. Evaluate hybrid ranking with NDCG and conversion metrics.

Использование «search-engineer». Our zero-result rate increased after changing the analyzer.

Ожидаемый результат:

Compare token output before and after the analyzer change.
Segment affected queries by language, category, and frequency.
Restore recall with synonyms or analyzer adjustments, then run an A/B test.

Использование «search-engineer». Plan evaluation for a new RAG retriever.

Ожидаемый результат:

Build a judged query set, measure recall at several depths, evaluate reranking with NDCG, and track answer faithfulness against retrieved evidence.

Аудит безопасности

Безопасно

v4 • 24.07.2026 Открыть версионный отчет

The 25 external-command findings are false positives caused by Markdown code fences; the document does not use Ruby or shell backtick execution. The pinned third-party plugin installation is a genuine low-severity network and supply-chain risk because no checksum or signature verification is provided.

Просканировано файлов

310

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Пункты проверки возможностей (1)

Это реальные локальные возможности, которые могут ожидаться для этого навыка, поэтому они требуют проверки, но не считаются подтверждённым вредоносным поведением.

Низкий

SKILL.md:88

Hardcoded URL

./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/downl

Line 88 directs the plugin installer to download a third-party release archive from GitHub. The version is pinned, but the example provides no checksum or signature verification.

Факторы риска

⚙️ Внешние команды (25)

🌐 Доступ к сети (1)

SKILL.md:88

Аудитор:: codex Посмотреть историю аудитов →

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

https://skillstore.io/skills/zl2023github-search-engineer/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/zl2023github-search-engineer/security.svg)](https://skillstore.io/skills/zl2023github-search-engineer?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/zl2023github-search-engineer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zl2023github-search-engineer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/zl2023github-search-engineer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

zl2023github. (2026). search-engineer security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zl2023github-search-engineer/audits/4

Цитата BibTeX

@techreport{zl2023github-zl2023github-search-engineer-2026,
  author = {zl2023github},
  title = {search-engineer security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/zl2023github-search-engineer/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "search-engineer security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "zl2023github"
date-released: "2026-07-24"
url: "https://skillstore.io/skills/zl2023github-search-engineer/audits/4"
identifiers:
  - type: other
    value: "skillstore:zl2023github-search-engineer:audit:4"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Plan a Search Platform

Compare keyword, vector, and hybrid designs, then define mappings, shards, analyzers, and evaluation criteria.

Build a RAG Retriever

Select embeddings, chunk documents, configure vector retrieval, and define relevance measurements for a RAG pipeline.

Diagnose Search Quality

Review zero-result queries, clicks, latency, and A/B metrics to identify practical ranking improvements.

Попробуйте эти промпты

Choose a Search Engine

Compare Elasticsearch, Solr, and Milvus for my dataset, query patterns, scale, latency target, and language requirements. Recommend one architecture with reasons.

Design an Index

Design an Elasticsearch index for these fields: [fields]. Include mappings, analyzers, shard assumptions, filters, sorting, and a relevance evaluation plan.

Investigate Relevance Problems

Analyze these search metrics and bad cases: [data]. Classify recall, ranking, tokenization, and latency issues. Propose prioritized experiments with success metrics.

Architect Hybrid RAG Retrieval

Create a production design for hybrid RAG retrieval using [data source]. Specify chunking, embeddings, lexical recall, vector recall, reranking, caching, and evaluation.

Лучшие практики

Define representative queries and relevance judgments before tuning retrieval.
Validate changes offline, then use controlled experiments with business and quality metrics.
Pin dependencies, secure production services, and verify third-party artifacts before installation.

Избегать

Do not select an engine before documenting data, query, scale, and latency requirements.
Do not optimize only click-through rate without relevance and conversion safeguards.
Do not copy example commands into production without authentication, backups, and environment review.

Часто задаваемые вопросы

Does this skill install or run a search engine?

No. It provides guidance and examples. Users must review and execute commands in their own environment.

Which search technologies are covered?

The examples cover Elasticsearch, Milvus, Redis, sentence transformers, Chroma, and related Python analysis libraries.

Can it help with Chinese search?

Yes. It discusses Chinese analyzers, custom dictionaries, query normalization, synonyms, and Chinese embedding models.

Does it support semantic search and RAG?

Yes. It outlines embeddings, vector indexes, chunking, retrieval, reranking considerations, and evaluation.

How does it evaluate search quality?

It covers NDCG, MAP, click metrics, zero-result rate, latency, and statistical A/B comparison.

Is the example code production ready?

No. Add error handling, security, observability, dependency pinning, tests, and environment-specific configuration before production use.

Сведения для разработчиков

Автор

zl2023github

Лицензия

MIT

Ревизия Skillstore

Примечание о версии

Автор не указал версию.

Репозиторий

https://github.com/zl2023github/software-engineer-skills/tree/main/software-engineering/search-engineer

Ссылка

88a8e9a07f4c54ab105c1c41b6267c287146b07b

Актуальность поддержки

26.07.2026

Использование

5 загрузок · 3 просмотров

Структура файлов

📄 SKILL.md