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

70%

Does it follow best practices?

Impact

95%

1.20x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/data-engineering/skills/dbt-transformation-patterns/SKILL.md

The canonical home for this skill is dbt-transformation-patterns in wshobson/agents

Quality

Content

65%Weight 40%Scale 1-5

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

Highly actionable reference with complete, executable dbt code across all model layers, but it is a monolithic document. It lacks an explicit build/validate workflow with error-recovery steps and keeps material in SKILL.md that would be better split into one-level-deep reference files.

Suggestions

Add an explicit workflow with validation checkpoints, e.g. 1) dbt run --select staging 2) dbt test --select staging 3) fix failing tests and re-run before building downstream layers.

Split bulk material into reference files (e.g. references/incremental-strategies.md, references/macros.md, references/testing.md) and keep SKILL.md as a concise overview with clearly signaled links.

Trim the dbt Commands section and obvious best practices (e.g. version control, don't test in prod) that restate knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and dbt-specific, but the "dbt Commands" section and best practices like "Version control - dbt project in Git" and "Don't test in prod" restate knowledge Claude already has. Mostly efficient with noticeable trimmable sections, matching anchor 3 rather than the minor-gaps anchor 4.	3 / 5
Actionability	Provides complete, copy-paste-ready artifacts: dbt_project.yml, source/staging/intermediate/mart SQL with configs, Jinja macros, test YAML, and CLI commands covering the common dbt workflow. This matches the fully-executable anchor 5.	5 / 5
Workflow Clarity	The layer progression (sources → staging → intermediate → marts → tests) implies a build order, but there is no explicit numbered workflow and no validate-fix-retry loop around `dbt build`/`dbt test`. Per the rubric's feedback-loop note, batch database operations without validation cap this at 3.	3 / 5
Progressive Disclosure	Sections are clearly headed and ordered, but everything is inlined in a ~560-line SKILL.md with no references/ files; incremental strategies, macros, and testing patterns are bulk content that belongs in separate reference files. This matches anchor 3 (some structure, should-be-separate content inline), not the well-split anchor 4.	3 / 5
	Total	14 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly covers both capabilities and use-when triggers with mostly concrete language. Its main weaknesses are the vague leading verb "Master", a soft catch-all trigger ("best practices"), and missing common synonyms like ELT or data pipeline.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas — "model organization, testing, documentation, and incremental strategies" — though the leading verb "Master dbt" is vague. Fits anchor 4 (several specific actions, minor gaps), not 5 (not fully comprehensive) or 3 (more than 1-2 concrete actions named).	4 / 5
Completeness	Explicitly answers both what ("Master dbt... with model organization, testing, documentation, and incremental strategies") and when ("Use when building data transformations, creating data models..."). The trigger "implementing analytics engineering best practices" is soft, keeping it below the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Includes natural user phrases like "building data transformations", "creating data models", "analytics engineering", and "dbt" itself. Missing common synonyms such as "ELT", "data pipeline", or "warehouse" — good but not comprehensive coverage, matching anchor 4.	4 / 5
Distinctiveness Conflict Risk	"dbt (data build tool)" carves a clear niche, but broad triggers like "data transformations" and "data models" could overlap generic data-engineering or SQL skills. Mostly distinct with minor overlap risk, matching anchor 4.	4 / 5
	Total	16 / 20 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
Path: tests/ext_conformance/artifacts/agents-wshobson/data-engineering/skills/dbt-transformation-patterns/SKILL.md
Commit: a65ce00

Reviewed: 6 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.