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

76%

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.

A highly actionable, code-rich reference that excels at executable examples but is held back by verbosity from repeated incremental demos, missing validation checkpoints on batch/incremental operations, and a monolithic single-file structure with no bundle references.

Suggestions

Consolidate the three incremental demonstrations (Patterns 2, 4, and 7) into a single incremental-strategies section to remove redundancy and tighten token usage.

Add explicit validation checkpoints after batch/incremental operations, e.g. verify row counts and uniqueness with `dbt test --select fct_orders` before considering a run complete.

Move the extended pattern library (macros, incremental strategies, full schema YAML) into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-forward content, but incremental materialization is demonstrated three times (Pattern 2 payments, Pattern 4 fct_orders, and Pattern 7's three strategies) and the Do's/Don'ts section restates earlier guidance, so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready SQL/YAML/bash covering the common dbt cases: source defs, staging/intermediate/mart models, tests, macros, and incremental strategies with real config blocks.	5 / 5
Workflow Clarity	The staging→intermediate→mart layering is clear, but incremental materialization is a batch operation on data and no validation/verification checkpoint is shown (e.g. verify row counts or duplicates after an incremental run), capping workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and ~560 lines are inlined into a single file with only external doc links; the per-pattern code that would naturally live in reference files is all inline, though section structure is reasonable.	3 / 5
	Total	14 / 20 Passed

Description

87%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 clearly states both capability and trigger conditions in third person, with concrete action areas and a distinct niche. Minor improvements possible by adding common synonyms (ETL, data warehouse) and making the lead verb more concrete.

Dimension	Reasoning	Score
Specificity	Lists several concrete action areas ("model organization, testing, documentation, and incremental strategies") but the lead verb "Master dbt" is somewhat abstract, leaving minor coverage gaps versus a fully concrete action list.	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, or implementing analytics engineering best practices") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "building data transformations, creating data models, or implementing analytics engineering best practices" give good keyword coverage, though common synonyms like ETL or data warehouse are absent.	4 / 5
Distinctiveness Conflict Risk	dbt analytics engineering is a clear niche with distinct triggers ("dbt", "data models", "analytics engineering") and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: 6453c0b

Reviewed: about 9 hours 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.