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.
74
62%
Does it follow best practices?
Impact
95%
1.20xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 is competent with a clear 'Use when' clause and identifies the dbt domain, but it stays at a somewhat high level in describing capabilities—listing categories rather than concrete actions. Trigger terms cover the basics but miss many natural user phrases associated with dbt workflows, and the broader data transformation language could cause overlap with other data-related skills.
Suggestions
Add more specific concrete actions like 'write schema tests, configure incremental materializations, set up staging/marts layer organization, generate documentation sites' instead of category-level terms.
Expand trigger terms to include natural user phrases like 'dbt run', 'dbt test', 'ref()', 'sources.yml', 'schema.yml', 'materializations', 'staging models', 'marts' to improve matching precision.
Sharpen distinctiveness by emphasizing dbt-specific concepts (e.g., 'Jinja SQL templating', 'dbt Cloud/Core') to reduce overlap with generic SQL or ETL skills.
| 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 data transformations, data models, and 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 models' could also conflict with database design or ER modeling skills. | 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.
This skill provides highly actionable, production-quality dbt patterns with excellent executable code examples covering the full model lifecycle. However, it suffers from being a monolithic document that should leverage progressive disclosure by splitting patterns into separate files, and it lacks explicit validation/verification workflows between steps (e.g., testing after each layer build). Some introductory content explains concepts Claude already knows.
Suggestions
Split the 7 detailed patterns into separate referenced files (e.g., patterns/staging.md, patterns/incremental.md) and keep SKILL.md as a concise overview with links
Add explicit validation workflow: e.g., 'After building staging: run `dbt test --select staging` → fix failures → only then build intermediate'
Remove the 'When to Use This Skill' and 'Core Concepts' sections or compress them significantly—Claude understands dbt's purpose and medallion architecture
Add a quick-reference decision tree for choosing incremental strategies rather than just listing all three options
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) with extensive inline code examples that could be split into referenced files. Some sections like 'When to Use This Skill' and 'Core Concepts' explain things Claude already knows about dbt. However, the code examples themselves are lean and well-commented. | 2 / 3 |
Actionability | Excellent actionability with fully executable SQL models, complete YAML configurations, working macros, and copy-paste ready dbt commands. Every pattern includes real, runnable code with proper dbt Jinja syntax. | 3 / 3 |
Workflow Clarity | The model layers are clearly sequenced (sources → staging → intermediate → marts), and dbt commands are listed. However, there are no explicit validation checkpoints in the workflow—no 'run dbt test after each layer' or 'validate before promoting to production' feedback loops for what are potentially destructive batch data operations. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with 7 detailed patterns all inline. The extensive YAML and SQL examples for sources, staging, intermediate, marts, testing, macros, and incremental strategies should be split into separate referenced files. The Resources section links externally but no internal file references exist for the detailed patterns. | 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 (564 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- 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.