data-engineering-skills MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

7 dbt skills — create, debug, test, document, migrate, refactor, incremental
2 Snowflake skills — find expensive queries, optimize by text/id
Skills auto-activate based on task context
Benchmarked: 53% real-world dbt pass rate, 84% Snowflake optimization pass rate
Includes dependency tracking and output verification steps

Живое демо

Как выглядит на практике

data-engineering-skill.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "data-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AltimateAI/data-engineering-skills",
        "~/.claude/skills/data-engineering-skills"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "data-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AltimateAI/data-engineering-skills",
        "~/.claude/skills/data-engineering-skills"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "data-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AltimateAI/data-engineering-skills",
        "~/.claude/skills/data-engineering-skills"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "data-engineering-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AltimateAI/data-engineering-skills",
        "~/.claude/skills/data-engineering-skills"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "data-engineering-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/AltimateAI/data-engineering-skills",
        "~/.claude/skills/data-engineering-skills"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "data-engineering-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/AltimateAI/data-engineering-skills",
          "~/.claude/skills/data-engineering-skills"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add data-engineering-skill -- git clone https://github.com/AltimateAI/data-engineering-skills ~/.claude/skills/data-engineering-skills

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: data-engineering-skills

Debug a failing dbt model without thrashing

👤 Analytics engineers facing a red CI run ⏱ ~20 min intermediate

Когда использовать: dbt run just failed with a cryptic error and you don't know if it's schema, lineage, or SQL.

Предварительные требования

dbt project accessible — cd into your dbt repo so Claude can see models/
Skill installed — git clone https://github.com/AltimateAI/data-engineering-skills ~/.claude/skills/data-engineering-skills

Поток

Feed Claude the error + model

Use debugging-dbt-errors. Here's the stderr and models/marts/fct_orders.sql. Diagnose the root cause — don't guess.✓ Скопировано

→ Claude reads upstream refs, diagnoses in order: schema → lineage → SQL
Apply the fix and verify

Apply the fix and run dbt build --select fct_orders+. Show me the before/after row counts.✓ Скопировано

→ Clean run + row count verification

Итог: Green CI plus a note of the root cause so it doesn't recur.

Подводные камни

Fixing a symptom downstream when the bug is upstream — The skill enforces an upstream-first diagnosis; don't skip the lineage step

Сочетать с: bigquery-server · github

Find and fix your top expensive Snowflake queries

👤 Analytics leads with a climbing Snowflake bill ⏱ ~60 min intermediate

Когда использовать: Finance flagged the Snowflake bill and you need to cut it without breaking dashboards.

Предварительные требования

Snowflake role with ACCOUNT_USAGE access — ACCOUNTADMIN typically, or a dedicated cost role

Поток

Identify worst offenders

Use finding-expensive-queries to list the top 20 queries in the past 30 days by credit cost. Group by app/user.✓ Скопировано

→ Ranked table with credits, runtime, warehouse
Optimize each top one

For the top offender, use optimizing-query-by-id <query_id>. Propose rewrites with estimated savings.✓ Скопировано

→ Rewritten SQL + before/after explain plan
Validate and deploy

Run the rewrite in a test warehouse — confirm same row count and shape before we swap.✓ Скопировано

→ Safe swap candidate

Итог: A prioritized list of fixes with measurable $ savings.

Подводные камни

Rewrites change row count silently — Always diff before deploying — the skill enforces this

Сочетать с: bigquery-server

Migrate a pile of stored procs into dbt models

👤 Teams moving off legacy SQL to dbt ⏱ ~90 min advanced

Когда использовать: You've inherited a warehouse of nested CTEs and want them as documented, tested dbt models.

Поток

Point the skill at the source SQL

Use migrating-sql-to-dbt. Here's proc_monthly_revenue.sql. Convert it to dbt models with refs, documentation, and at least 2 tests per model.✓ Скопировано

→ One or more .sql files, schema.yml with docs and tests
Build and verify

dbt build the new models and compare row counts to the legacy output.✓ Скопировано

→ Row counts match within tolerance

Итог: Legacy logic lives as testable dbt models.

Подводные камни

Hidden side effects in the proc (UPDATEs) — The skill flags side effects — separate them out, don't blindly convert

Сочетать с: github

Convert a slow full-refresh model to incremental

👤 Analytics engineers with long-running dbt runs ⏱ ~45 min advanced

Когда использовать: A daily model has grown too big for full refresh.

Поток

Analyze the model

Use developing-incremental-models on models/events.sql. Pick a strategy (merge / insert_overwrite / delete+insert) and justify.✓ Скопировано

→ Strategy + unique_key + partition / cluster keys recommended
Implement and back-fill

Apply the incremental config; outline a safe back-fill plan.✓ Скопировано

→ Model + back-fill steps

Итог: Daily runs that finish in minutes, not hours.

Подводные камни

unique_key gets duplicates on late data — Use merge and test it

Комбинации

Сочетайте с другими MCP — эффект x10

data-engineering-skill + bigquery-server

Apply the same optimize-by-id pattern to BigQuery expensive queries

Adapt finding-expensive-queries for BigQuery INFORMATION_SCHEMA.JOBS and list top 20.✓ Скопировано

data-engineering-skill + github

Open a PR per migrated model so each is reviewable

For every migrated model, open a GitHub PR with dbt test output attached.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
creating-dbt-models	model spec	New model	0
debugging-dbt-errors	error log, model	CI or local run failed	0
testing-dbt-models	model	Untested model	0
documenting-dbt-models	model	Undocumented model	0
migrating-sql-to-dbt	legacy SQL	Legacy migration	0
refactoring-dbt-models	model	Hard-to-read model	0
developing-incremental-models	full-refresh model	Runtime too long	0
finding-expensive-queries	lookback window	Cost hunt	ACCOUNT_USAGE query
optimizing-query-text	SQL text	Know the SQL, not the id	0
optimizing-query-by-id	query_id	Have the id from the UI	1 explain

Стоимость и лимиты

Во что обходится

Квота API: Snowflake queries cost credits like any other — ACCOUNT_USAGE reads are cheap
Токенов на вызов: 5–15k per dbt skill invocation
Деньги: Free skill
Совет: Run finding-expensive-queries once weekly, not on every session

Безопасность

Права, секреты, радиус поражения

Минимальные скоупы: dbt: read + write to your project Snowflake: ACCOUNT_USAGE for cost skills

Хранение учётных данных: dbt profiles.yml / Snowflake key-pair in env; the skill doesn't store secrets

Исходящий трафик: None from the skill directly

Никогда не давайте: SYSADMIN to the Claude session unless absolutely needed

Устранение неполадок

Частые ошибки и исправления

dbt compile succeeds, run fails with column not found

Stale lineage — dbt deps + dbt clean + dbt build --select model+

finding-expensive-queries returns nothing

ACCOUNT_USAGE has ~45min delay; also confirm role has SNOWFLAKE.ACCOUNT_USAGE

Проверить: SHOW GRANTS TO ROLE <role>

Альтернативы

data-engineering-skills в сравнении

Альтернатива	Когда использовать	Компромисс
dbt Cloud IDE	You prefer managed UI over terminal	No Claude in the loop
SQL query optimizers (Select.dev, etc.)	You want visual query plans	Separate tool, separate context

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills