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.

1.20x

Quality

—

Does it follow best practices?

Impact

95%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with comprehensive, executable dbt patterns and commands, and is largely token-efficient. Its main gaps are the absence of an explicit validate→fix→retry feedback loop for batch dbt runs and the lack of progressive disclosure into separate reference files for a skill this size.

Suggestions

Add an explicit validation feedback loop for batch/destructive operations, e.g. 'dbt build → if tests fail, review failures → fix model → re-run --select <failing>' to lift workflow clarity above 2.

Split large detail blocks (full SQL model examples, the macro library, incremental strategies) into one-level-deep reference files in references/ and link to them from SKILL.md to improve progressive disclosure.

Trim the 'Core Concepts' section and consolidate the structurally similar staging/intermediate/mart SQL examples to reduce length without sacrificing actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable code and config with little conceptual fluff, but at ~560 lines it includes a 'Core Concepts' section and several structurally similar full SQL models that could be tightened without losing clarity.	2.5 / 3
Actionability	Provides fully executable, copy-paste-ready material — dbt_project.yml, sources.yml, complete SQL models with config blocks, macros, and annotated dbt commands — matching the anchor for concrete executable guidance.	3 / 3
Workflow Clarity	Patterns follow a clear source→staging→intermediate→mart sequence, but batch/destructive dbt operations lack an explicit validate→fix→retry feedback loop, so per the guidelines workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Content is internally well-sectioned but entirely inline in SKILL.md with no one-level-deep bundle references; material such as full model examples, the macro library, and incremental strategies that could be split into reference files lives in the single file.	2 / 3
	Total	9.5 / 12 Passed

Description

92%

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 strong: specific, third-person, and complete with an explicit 'Use when' trigger that names both capabilities and activation contexts. Its only soft spot is trigger-term naturalness, where slightly jargon-heavy phrasing and missing common variations keep it just short of ideal.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'model organization, testing, documentation, and incremental strategies' — matching the anchor for listing several specific capabilities rather than a vague single domain.	3 / 3
Completeness	Explicitly answers both what ('Master dbt ... with model organization, testing, documentation, and incremental strategies') and when via a dedicated 'Use when building data transformations, creating data models, ...' clause.	3 / 3
Trigger Term Quality	Natural triggers like 'building data transformations, creating data models' are present, but the phrasing leans technical ('analytics engineering best practices') and omits common variations a user might say such as 'dbt models' or 'data pipelines', keeping it just below full coverage.	2.5 / 3
Distinctiveness Conflict Risk	The dbt-specific niche and explicit 'dbt (data build tool)' triggers make it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11.5 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 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	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.