dbt-transformation-patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
82
62%
Does it follow best practices?
Impact
96%
1.15xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/data-engineering/skills/dbt-transformation-patterns/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has a solid structure with an explicit 'Use when...' clause and identifies the dbt domain clearly. However, it leans toward category-level language rather than listing concrete specific actions, and its trigger terms could be more comprehensive to cover the natural vocabulary dbt users employ. The broader data transformation language introduces some overlap risk with other data-related skills.
Suggestions
Replace category labels with more concrete actions, e.g., 'Write and organize staging/marts SQL models, configure materializations (incremental, table, view), define schema tests and source freshness checks, generate documentation.'
Add more natural trigger terms users would say, such as 'dbt run', 'dbt test', 'ref()', 'sources.yml', 'schema.yml', 'materializations', 'staging models', 'marts', or '.sql models'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt/analytics engineering) and mentions some actions like 'model organization, testing, documentation, and incremental strategies,' but these are more like category labels than concrete specific actions. Compare to a score-3 example which would list things like 'create staging models, write schema tests, configure incremental materializations, generate dbt docs.' | 2 / 3 |
Completeness | Clearly answers both 'what' (model organization, testing, documentation, incremental strategies) and 'when' with an explicit 'Use when...' clause covering building data transformations, creating data models, or implementing analytics engineering best practices. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'dbt', 'data build tool', 'data transformations', 'data models', and 'analytics engineering', which are good. However, it misses common natural variations users might say such as 'SQL models', 'ref()', 'sources', 'materializations', 'dbt run', 'dbt test', 'staging/marts layers', or '.yml schema files'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'dbt' and 'analytics engineering' provides some distinctiveness, but phrases like 'data transformations' and 'creating data models' are broad enough to overlap with general SQL skills, ETL tools, or other data pipeline skills. The term 'data build tool' helps but the broader trigger terms could cause conflicts. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with comprehensive, executable dbt patterns covering the full model lifecycle. However, it suffers from being a monolithic document (~400 lines) that would benefit significantly from splitting detailed patterns into separate files. The workflow lacks explicit validation checkpoints between steps, which is important for data transformation pipelines where errors compound downstream.
Suggestions
Split detailed patterns (source definitions, staging models, intermediate models, marts, testing, macros, incremental strategies) into separate referenced files, keeping SKILL.md as a concise overview with quick-start examples
Add an explicit end-to-end workflow section with validation checkpoints, e.g., '1. Define sources → 2. Build staging + run dbt test --select staging → 3. Build intermediate → 4. Build marts + run dbt build → 5. Check freshness with dbt source freshness'
Remove the 'When to Use This Skill' section as it restates the description and adds no actionable value
Trim inline comments in SQL examples that state the obvious (e.g., '-- ids', '-- strings', '-- timestamps') to reduce token usage
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400 lines) with extensive code examples that are thorough but could be more concise. The 'When to Use This Skill' section and some inline comments add tokens without much value for Claude. However, it avoids explaining what dbt is at a basic level and mostly stays focused on patterns. | 2 / 3 |
Actionability | Excellent actionability with fully executable SQL models, complete YAML configurations, working macros, and specific dbt commands. Every pattern includes copy-paste ready code with realistic examples (Stripe, Shopify) that could be directly adapted. | 3 / 3 |
Workflow Clarity | The patterns are presented in a logical progression (sources → staging → intermediate → marts → testing), but there's no explicit workflow with validation checkpoints. Missing guidance on verifying each step (e.g., run tests after staging before building marts, validate incremental models with --full-refresh first). The dbt commands section lists commands but doesn't sequence them into a workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to external files. All seven patterns, commands, and best practices are inline. The extensive code examples for each pattern (source definitions, staging, intermediate, marts, testing, macros, incremental strategies) would benefit greatly from being split into separate reference files with the SKILL.md serving as an overview. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (557 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
70444e5
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.