● Communauté
AltimateAI
⚡ Instantané
data-engineering-skills
par AltimateAI · AltimateAI/data-engineering-skills
9 Claude Code skills for analytics engineering: 7 dbt workflows + 2 Snowflake query optimizers. 53% pass on real dbt tasks, 84% on Snowflake tuning.
Skills for the daily grind of analytics engineering. dbt skills cover creating, debugging, testing, documenting, migrating, refactoring, and incremental models. Snowflake skills find expensive queries and optimize either by text or by query_id. Philosophy: 'Read before you write. Build after you write. Verify your output.'
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
Cas d'usage
Usages concrets : data-engineering-skills
Quand l'utiliser : dbt run just failed with a cryptic error and you don't know if it's schema, lineage, or SQL.
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
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
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
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
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 +
githubOpen a PR per migrated model so each is reviewable
For every migrated model, open a GitHub PR with dbt test output attached.✓ Copié
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 |