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.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill dbt-transformation-patterns79
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies its domain (dbt/analytics engineering) and provides explicit 'Use when' guidance. The main weakness is that the capabilities listed are somewhat categorical rather than listing specific concrete actions. The trigger terms are strong and the skill is clearly distinguishable from other data-related skills.
Suggestions
Add more specific concrete actions like 'write Jinja macros', 'configure materializations', 'set up source freshness checks', or 'define schema tests' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt/analytics engineering) and lists some actions (model organization, testing, documentation, incremental strategies), but these are somewhat high-level categories rather than concrete specific actions like 'write ref() functions' or 'configure materializations'. | 2 / 3 |
Completeness | Clearly answers both what (model organization, testing, documentation, incremental strategies) AND when ('Use when building data transformations, creating data models, or implementing analytics engineering best practices') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'dbt', 'data build tool', 'analytics engineering', 'data transformations', 'data models'. Users would naturally use these terms when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on dbt tooling. The explicit mention of 'dbt (data build tool)' and analytics engineering terminology creates distinct triggers unlikely to conflict with general SQL or data processing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable dbt skill with excellent code examples that are production-ready and copy-paste executable. The main weaknesses are its length (could benefit from splitting into multiple files) and the lack of explicit validation workflows for incremental model development and testing cycles. The content assumes appropriate Claude competence but could be more concise in introductory sections.
Suggestions
Add explicit validation checkpoints for incremental model development (e.g., 'Run dbt run --full-refresh in dev first, verify row counts, then test incremental logic')
Split the 7 patterns into a separate PATTERNS.md or individual pattern files, keeping SKILL.md as a concise overview with references
Remove or condense the 'When to Use This Skill' section - these use cases are self-evident from the skill title and description
Add a troubleshooting workflow for common incremental model failures with explicit fix-and-retry steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity. The 'When to Use This Skill' section restates obvious use cases, and some explanations (like the medallion architecture diagram) could be more compact. However, most content is practical and avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout. Every pattern includes complete, copy-paste ready SQL and YAML configurations. The dbt commands section provides specific CLI commands with clear explanations of what each does. | 3 / 3 |
Workflow Clarity | The model layers and project structure are well-sequenced, but the skill lacks explicit validation checkpoints. For a tool that involves data transformations and incremental processing, there should be clearer 'validate before proceeding' steps, especially around incremental model testing and schema changes. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, but it's monolithic at ~400 lines. The patterns section could be split into separate reference files (e.g., INCREMENTAL_STRATEGIES.md, TESTING.md). External links are provided but internal progressive disclosure to separate files is missing. | 2 / 3 |
Total | 9 / 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 | |
- 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.