Skip to content
Back to search

data-engineering-skills

MarketplaceWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/altimateai--data-engineering-skills/badge.svg)](/listings/altimateai--data-engineering-skills)

HTML

<a href="/listings/altimateai--data-engineering-skills"><img src="/api/listings/altimateai--data-engineering-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

/plugin marketplace add AltimateAI/data-engineering-skills

Install individual skill packs:

# Install dbt skills
/plugin install dbt-skills@data-engineering-skills

# Install Snowflake skills
/plugin install snowflake-skills@data-engineering-skills

# Install altimate-code delegation skill
/plugin install altimate-code@data-engineering-skills

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 62 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "data-engineering-skills",
  3. "owner": {
  4. "name": "Altimate AI",
  5. "email": "support@altimate.ai"
  6. },
  7. "metadata": {
  8. "description": "Skills for data engineering workflows",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "dbt-skills",
  14. "description": "Skills for dbt development, testing, debugging, and refactoring",
  15. "source": "./",
  16. "strict": false,
  17. "skills": [
  18. "./skills/dbt/creating-dbt-models",
  19. "./skills/dbt/debugging-dbt-errors",
  20. "./skills/dbt/testing-dbt-models",
  21. "./skills/dbt/documenting-dbt-models",
  22. "./skills/dbt/migrating-sql-to-dbt",
  23. "./skills/dbt/refactoring-dbt-models",
  24. "./skills/dbt/developing-incremental-models",
  25. "./skills/dbt/dbt-model-enhancement",
  26. "./skills/dbt/mssql-to-snowflake-dbt-migration"
  27. ]
  28. },
  29. {
  30. "name": "snowflake-skills",
  31. "description": "Skills for Snowflake query optimization",
  32. "source": "./",
  33. "strict": false,
  34. "skills": [
  35. "./skills/snowflake/optimizing-query-by-id",
  36. "./skills/snowflake/optimizing-query-text",
  37. "./skills/snowflake/finding-expensive-queries",
  38. "./skills/snowflake/snowflake-dbt-model-refactoring",
  39. "./skills/snowflake/snowflake-query-optimization",
  40. "./skills/snowflake/end-to-end-snowflake-pipeline"
  41. ]
  42. },
  43. {
  44. "name": "databricks-skills",
  45. "description": "Skills for Databricks SQL query optimization",
  46. "source": "./",
  47. "strict": false,
  48. "skills": [
  49. "./skills/databricks/optimizing-databricks-sql"
  50. ]
  51. },
  52. {
  53. "name": "altimate-code",
  54. "description": "Delegate data engineering tasks to altimate-code — a specialized CLI agent with 100+ data tools (warehouse profiling, column lineage, dbt build/test, FinOps)",
  55. "source": "./",
  56. "strict": false,
  57. "skills": [
  58. "./skills/altimate-code"
  59. ]
  60. }
  61. ]
  62. }
README.md · README · 220 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Data Engineering Skills
  2. **Claude Code skills for Analytics & Data engineers working with dbt and Snowflake**
  3. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  4. [![Claude Code](https://img.shields.io/badge/Claude%20Code-Skills-blueviolet)](https://claude.ai/claude-code)
  5. Altimate Data Skills is a collection of Claude Code skills that encode the workflows and best practices of experienced analytics engineers. These skills transform Claude from a code generator into a capable data engineering assistant.
  6. ## Key Results
  7. - **53% accuracy** on [ADE-bench](https://github.com/dbt-labs/ade-bench) (43 real-world dbt tasks)
  8. - **3x improvement** on model creation tasks vs baseline
  9. - **84% pass rate** on Snowflake query optimization (62 TPC-H queries, 1TB dataset)
  10. - **3.6x better performance** gains vs baseline (16.8% avg improvement vs 4.7%)
  11. - Skills that teach Claude *how* to work, not just *what* to write
  12. ## Quick Start
  13. ```bash
  14. /plugin marketplace add AltimateAI/data-engineering-skills
  15. ```
  16. Install individual skill packs:
  17. ```bash
  18. # Install dbt skills
  19. /plugin install dbt-skills@data-engineering-skills
  20. # Install Snowflake skills
  21. /plugin install snowflake-skills@data-engineering-skills
  22. # Install altimate-code delegation skill
  23. /plugin install altimate-code@data-engineering-skills
  24. ```
  25. ## Available Skills
  26. ### dbt Skills
  27. | Skill | Purpose | Key Behaviors |
  28. |-------|---------|---------------|
  29. | **creating-dbt-models** | Model creation | Convention discovery → Write → Build → Verify output |
  30. | **debugging-dbt-errors** | Error troubleshooting | Read full error → Check upstream → Apply fix → Rebuild |
  31. | **testing-dbt-models** | Schema tests | Study existing test patterns → Match project style |
  32. | **documenting-dbt-models** | Documentation | Analyze model → Generate descriptions |
  33. | **migrating-sql-to-dbt** | Legacy SQL conversion | Parse SQL → Create proper dbt model |
  34. | **refactoring-dbt-models** | Safe restructuring | Track dependencies → Apply changes → Verify downstream |
  35. | **developing-incremental-models** | Incremental models | Strategy selection → unique_key design → Handle edge cases |
  36. | **dbt-model-enhancement** | Ticket-driven enhancement of one existing model → PR | Ticket as data (allow-list) → non-prod `--target` → `dbt build --select <model>+` → self-review → PR |
  37. | **mssql-to-snowflake-dbt-migration** | T-SQL → Snowflake dbt with isolated-schema deploy | Medallion or Data Vault → convert with TRAP-aware rewrites → compile → confirm → build to isolated schema → engine-neutral parity → dashboard |
  38. ### Snowflake Skills
  39. | Skill | Purpose | Key Behaviors |
  40. |-------|---------|---------------|
  41. | **finding-expensive-queries** | Cost analysis | Find and rank queries by cost/time/data scanned |
  42. | **optimizing-query-by-id** | Performance tuning | Optimize using query ID from history |
  43. | **optimizing-query-text** | Performance tuning | Profile query → Identify bottlenecks → Apply patterns |
  44. | **snowflake-dbt-model-refactoring** | Snowflake-specific safe dbt model refactor | Downstream analysis → parity → outcome-axes report |
  45. | **snowflake-query-optimization** | End-to-end query tuning (fetch → rewrite → parity → benchmark) | SELECT-only guard → `HASH_AGG` + multiplicity parity → cache-off benchmark via `INFORMATION_SCHEMA` |
  46. | **end-to-end-snowflake-pipeline** | Ticket → dbt + orchestration + PR, in one pass | Auto-detect orchestrator (Airflow/Prefect/Dagster) + VCS → non-prod `--target` + `--select` → DAG parse → self-review → PR → ticket comment |
  47. ### altimate-code Delegation
  48. | Skill | Purpose | Key Behaviors |
  49. |-------|---------|---------------|
  50. | **altimate-code** | Hand off data tasks to altimate-code | Verify install → Invoke `altimate-code run --yolo` non-interactively → Read output file → Summarize for user |
  51. Use this skill when a task needs altimate-code's wired-up warehouse tools, column lineage, multi-step data exploration, or its 100+ specialized data tools.
  52. **Requires altimate-code:** `npm install -g altimate-code` (Node 20+). Docs: [docs.altimate.sh](https://docs.altimate.sh) · Source: [AltimateAI/altimate-code](https://github.com/AltimateAI/altimate-code). The skill will detect a missing install and surface the exact command to the user.
  53. ## How Skills Work
  54. Skills are markdown files that teach Claude **how to approach tasks**, not just what syntax to use. Each skill has two parts:
  55. ### 1. Trigger Conditions
  56. When should this skill activate?
  57. ```yaml
  58. ---
  59. name: creating-dbt-models
  60. description: |
  61. Guide for creating dbt models. ALWAYS use this skill when:
  62. (1) Creating ANY new model (staging, intermediate, mart)
  63. (2) Task mentions "create", "build", "add" with model/table
  64. (3) Modifying model logic or columns
  65. ---
  66. ```
  67. ### 2. Workflow Instructions
  68. What steps should Claude follow?
  69. ```markdown
  70. # dbt Model Development
  71. **Read before you write. Build after you write. Verify your output.**
  72. ## Critical Rules
  73. 1. ALWAYS run `dbt build` after creating models - compile is NOT enough
  74. 2. ALWAYS verify output after build using `dbt show`
  75. 3. If build fails 3+ times, stop and reassess your approach
  76. ...
  77. ```
  78. ## Usage Examples
  79. Skills activate automatically based on your request:
  80. | Your Request | Skill Activated |
  81. |--------------|-----------------|
  82. | "Create a new orders model" | `creating-dbt-models` |
  83. | "Fix this compilation error" | `debugging-dbt-errors` |
  84. | "Add tests to the customers model" | `testing-dbt-models` |
  85. | "Document the revenue metrics" | `documenting-dbt-models` |
  86. | "Create an incremental model for events" | `developing-incremental-models` |
  87. | "This query is slow, optimize it" | `optimizing-query-text` |
  88. ## Combining with Altimate MCP Tools
  89. Skills become even more powerful when combined with [Altimate's MCP server](https://docs.myaltimate.com/). The MCP server provides real-time access to your dbt project and data warehouse:
  90. | MCP Tool | What It Provides |
  91. |----------|------------------|
  92. | `dbt_project_info` | Project structure, model list, sources |
  93. | `dbt_model_details` | Column types, dependencies, compiled SQL |
  94. | `dbt_compile` | Compile models without CLI |
  95. | `snowflake_query_history` | Recent query executions and stats |
  96. | `snowflake_table_stats` | Row counts, clustering info |
  97. ## Kits
  98. Kits bundle skills, MCP servers, and instructions into a single activatable unit. Instead of installing skills one by one, activate a kit to get a complete development setup.
  99. ### Available Kits
  100. | Kit | Description | Skills | MCP |
  101. |-----|-------------|--------|-----|
  102. | [dbt-snowflake](kits/dbt-snowflake/) | Complete dbt + Snowflake setup | 15 skills | dbt MCP server |
  103. ### Quick Start
  104. ```bash
  105. # Install the kit
  106. altimate-code kit install AltimateAI/data-engineering-skills
  107. # Activate for your project
  108. altimate-code kit activate dbt-snowflake
  109. # Check what's active
  110. altimate-code kit status
  111. ```
  112. See [kits/README.md](kits/README.md) for the full kit format reference and how to create your own.
  113. ## Benchmark Results
  114. Evaluated using [ADE-bench](https://github.com/dbt-labs/ade-bench), a framework for evaluating AI agents on analytics engineering tasks. All tests were run using Claude Sonnet 4.5.
  115. ### Overall Results
  116. | Configuration | Accuracy | Tasks Resolved |
  117. |---------------|----------|----------------|
  118. | Baseline Claude (no skills) | 46.5% | 20/43 |
  119. | Claude + Skills | **53.5%** | 23/43 |
  120. ### Results by Task Category
  121. | Category | Baseline | With Skills | Improvement |
  122. |----------|----------|-------------|-------------|
  123. | Model Creation | 40% | 65% | **+25 pts** |
  124. | Bug Fixing | 60% | 70% | +10 pts |
  125. | Debugging | 35% | 50% | +15 pts |
  126. | Refactoring | 30% | 35% | +5 pts |
  127. | Analysis | 25% | 30% | +5 pts |
  128. ### Snowflake Query Optimization (TPC-H SF1000)
  129. Benchmark on TPC-H 1TB dataset (62 queries) testing `optimizing-query-text` skill. All tests were run using Claude Sonnet 4.5.
  130. | Configuration | Pass Rate | Avg Performance Improvement |
  131. |---------------|-----------|----------------------------|
  132. | Baseline Claude (no skills) | 77.4% (48/62) | 4.7% |
  133. | Claude + Skills | **83.9% (52/62)** | **16.8%** (3.6x better) |
  134. Skills provide structured optimization with query profiling, anti-pattern detection, and semantic preservation validation.
  135. > **Note:** This benchmark uses our internal evaluation framework. We plan to open-source it soon with additional evals.
  136. ## Contributing
  137. We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
  138. Ideas for contributions:
  139. - New skills for workflows we haven't covered
  140. - Improvements to existing skills based on your team's patterns
  141. - Benchmark results on different datasets
  142. - Bug reports and feature requests
  143. ## Roadmap
  144. We're actively developing:
  145. - **Airflow skills** — DAG development, debugging, testing
  146. - **Cross-platform migration** — dbt to/from SQL Server, Oracle
  147. - **Snowflake cost optimization** — Warehouse sizing, query patterns
  148. - **Data quality workflows** — Anomaly detection, freshness checks
  149. ## Resources
  150. - [Altimate MCP Server Docs](https://docs.myaltimate.com/)
  151. - [ADE-bench Framework](https://github.com/dbt-labs/ade-bench)
  152. - [dbt Slack Channel](https://getdbt.slack.com/archives/C05KPDGRMDW)
  153. - [Contact Us](https://app.myaltimate.com/contactus)
  154. ## License
  155. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
  156. ---
  157. *Built by the team at [Altimate AI](https://altimate.ai/) — Making data engineering delightful.*

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.