Tessl • The management layer for AI agent skills

SkillPublic

dbt-data-transformation

Complete guide for dbt data transformation including models, tests, documentation, incremental builds, macros, packages, and production workflows

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/luxor-data-engineering/skills/dbt-data-transformation/SKILL.md

Quality

Content

57%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 material undermined by severe monolithic bulk: no progressive disclosure (zero bundle files), redundant re-explanations of dbt basics, and reference-style rather than checkpoint-validated workflows. The code quality itself is strong and executable throughout.

Suggestions

Split the body into one-level-deep bundle files (e.g. references/incremental-models.md, references/macros.md, references/ci-cd.md, references/examples.md) and leave SKILL.md as a concise overview with clearly signaled links.

Delete or compress sections that teach what Claude already knows ('What is dbt?', 'Key dbt Entities', the generic version-control/modularity bullets) and consolidate the three separate incremental-model treatments into one.

Add explicit validation checkpoints and feedback loops to the workflow and CI sections (e.g. `dbt compile`/`dbt debug` before `dbt run`, run `dbt test` and fix/retry before promoting to prod).

Dimension	Reasoning	Score
Conciseness	The ~2,600-line body re-teaches concepts Claude already knows ("What is dbt?", "Key dbt Entities", generic modularity/version-control explanations) and covers incremental models three separate times (Materializations, Incremental Models, Performance Optimization). It is not a 1 because most of the bulk is concrete, non-prose code rather than pure padding.	2 / 5
Actionability	Nearly every section ships executable, copy-paste-ready material — complete model SQL with configs, YAML test and source definitions, macro definitions, packages.yml, GitHub Actions workflows, an Airflow DAG, and a command cheat sheet. This matches the fully-executable anchor covering common cases.	5 / 5
Workflow Clarity	A sequence exists (the Develop→Test→Document→Build→Deploy workflow, CI pipelines with `dbt debug`/`dbt test` steps), but checkpoints are implicit and there are no validate→fix→retry feedback loops for batch production operations (`dbt run --target prod`). Not a 4 because the main body is reference-style rather than a validated step sequence.	3 / 5
Progressive Disclosure	Internal structure is good (clear headers, comparison tables, a Resources section), but everything — 20 full examples, CI/CD configs, the command reference — is inlined in one 62KB SKILL.md with no references/, scripts/, or assets/ bundle files. Matches 'content that should be separate is inline' with some structure; not a 2 because the inline organization is far from minimal.	3 / 5
	Total	13 / 20 Passed

Description

70%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 specific, well-scoped description for the dbt niche with good keyword coverage, but it omits any explicit 'Use when...' trigger guidance and leans on "Complete guide" puffery instead of concrete action verbs.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when building or testing dbt models, writing macros, or setting up dbt CI/CD pipelines.'

Include natural synonyms users would say — 'data warehouse', 'ELT', 'analytics engineering', 'SQL transformations' — to broaden trigger coverage.

Replace 'Complete guide for' with action-oriented third-person verbs such as 'Build, test, and document dbt models; configure incremental materializations, macros, packages, and CI/CD workflows.'

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas — "models, tests, documentation, incremental builds, macros, packages, and production workflows" — giving minor gaps in coverage. It falls short of a 5 because these are topic nouns rather than stated actions and "Complete guide" is a mild over-claim.	4 / 5
Completeness	The "what" is clear (a dbt data transformation guide covering enumerated areas), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the "what" is concrete and multi-faceted.	3 / 5
Trigger Term Quality	"dbt", "data transformation", "models", "tests", "macros", and "packages" are terms users naturally say, giving good keyword coverage. It is not a 5 because common synonyms like "data warehouse", "ELT", "analytics engineering", and "SQL" are missing.	4 / 5
Distinctiveness Conflict Risk	"dbt" names a specific niche tool with distinct triggers (models, macros, dbt tests), so the risk of triggering for the wrong skill is minimal. Neighboring anchor 4's "minor overlap risk" does not apply since no closely related skill would compete for these triggers.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (2627 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: manutej/luxor-claude-marketplace
Path: plugins/luxor-data-engineering/skills/dbt-data-transformation/SKILL.md
Revision: 1861cc9

Reviewed: 26 days ago

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.

dbt-data-transformation

Table of Contents

Is this your skill?