data-engineering-skills MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

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

Demo ao vivo

Como fica na prática

data-engineering-skill.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.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 usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

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
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "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
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um 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"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: data-engineering-skills

Debug a failing dbt model without thrashing

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

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

Pré-requisitos

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

Fluxo

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.✓ Copiado

→ 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.✓ Copiado

→ Clean run + row count verification

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

Armadilhas

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

Combine com: bigquery-server · github

Find and fix your top expensive Snowflake queries

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

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

Pré-requisitos

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

Fluxo

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.✓ Copiado

→ 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.✓ Copiado

→ 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.✓ Copiado

→ Safe swap candidate

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

Armadilhas

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

Combine com: bigquery-server

Migrate a pile of stored procs into dbt models

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

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

Fluxo

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.✓ Copiado

→ 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.✓ Copiado

→ Row counts match within tolerance

Resultado: Legacy logic lives as testable dbt models.

Armadilhas

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

Combine com: github

Convert a slow full-refresh model to incremental

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

Quando usar: A daily model has grown too big for full refresh.

Fluxo

Analyze the model

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

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

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

→ Model + back-fill steps

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

Armadilhas

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

Combinações

Combine com outros MCPs para 10× de alavancagem

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.✓ Copiado

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.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

Cota de API: Snowflake queries cost credits like any other — ACCOUNT_USAGE reads are cheap
Tokens por chamada: 5–15k per dbt skill invocation
Monetário: Free skill
Dica: Run finding-expensive-queries once weekly, not on every session

Segurança

Permissões, segredos, alcance

Escopos mínimos: dbt: read + write to your project Snowflake: ACCOUNT_USAGE for cost skills

Armazenamento de credenciais: dbt profiles.yml / Snowflake key-pair in env; the skill doesn't store secrets

Saída de dados: None from the skill directly

Nunca conceda: SYSADMIN to the Claude session unless absolutely needed

Solução de problemas

Erros comuns e correções

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

Verificar: SHOW GRANTS TO ROLE <role>

Alternativas

data-engineering-skills vs. outros

Alternativa	Quando usar	Troca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills