data-engineering-skills MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

data-engineering-skill.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.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 utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

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
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "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
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.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 utilise un tableau d'objets serveur plutôt qu'une 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"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : data-engineering-skills

Debug a failing dbt model without thrashing

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

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

Prérequis

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

Déroulement

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.✓ Copié

→ 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.✓ Copié

→ Clean run + row count verification

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

Pièges

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

Combiner avec : bigquery-server · github

Find and fix your top expensive Snowflake queries

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

Quand l'utiliser : Finance flagged the Snowflake bill and you need to cut it without breaking dashboards.

Prérequis

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

Déroulement

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.✓ Copié

→ 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.✓ Copié

→ 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.✓ Copié

→ Safe swap candidate

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

Pièges

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

Combiner avec : bigquery-server

Migrate a pile of stored procs into dbt models

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

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

Déroulement

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.✓ Copié

→ 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.✓ Copié

→ Row counts match within tolerance

Résultat : Legacy logic lives as testable dbt models.

Pièges

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

Combiner avec : github

Convert a slow full-refresh model to incremental

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

Quand l'utiliser : A daily model has grown too big for full refresh.

Déroulement

Analyze the model

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

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

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

→ Model + back-fill steps

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

Pièges

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

Combinaisons

Associez-le à d'autres MCPs pour un effet 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.✓ Copié

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.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: Snowflake queries cost credits like any other — ACCOUNT_USAGE reads are cheap
Tokens par appel: 5–15k per dbt skill invocation
Monétaire: Free skill
Astuce: Run finding-expensive-queries once weekly, not on every session

Sécurité

Permissions, secrets, portée

Portées minimales : dbt: read + write to your project Snowflake: ACCOUNT_USAGE for cost skills

Stockage des identifiants : dbt profiles.yml / Snowflake key-pair in env; the skill doesn't store secrets

Sortie de données : None from the skill directly

Ne jamais accorder : SYSADMIN to the Claude session unless absolutely needed

Dépannage

Erreurs courantes et correctifs

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

Vérifier : SHOW GRANTS TO ROLE <role>

Alternatives

data-engineering-skills vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills