● Сообщество
AltimateAI
⚡ Сразу
data-engineering-skills
автор 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.'
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
Сценарии использования
Реальные сценарии: data-engineering-skills
Когда использовать: dbt run just failed with a cryptic error and you don't know if it's schema, lineage, or SQL.
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
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
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
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
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 +
githubOpen a PR per migrated model so each is reviewable
For every migrated model, open a GitHub PR with dbt test output attached.✓ Скопировано
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 |