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.

Quality

63%

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 ./skills/dbt-transformation-patterns/SKILL.md

Quality

Content

51%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 concise, well-organized overview that correctly defers detail to a reference, but it lacks executable specifics and a sequenced workflow with validation, and its single detail reference is a path to a file that is absent from the bundle.

Suggestions

Add a brief sequenced workflow with validation checkpoints (e.g., model → `dbt run` → `dbt test` → review failures → re-run), since dbt is a batch/database operation where missing validation caps workflow clarity.

Include one or two concrete executable snippets or commands (e.g., a sample `dbt_project.yml` layer config or `dbt run --select staging.+`) so the instructions are actionable without the missing reference file.

Provide the referenced `resources/implementation-playbook.md` (or correct the path) so the progressive-disclosure pointer resolves to a real file rather than a broken reference.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows dbt, and avoids padding, but the opening line and "Use this skill when" list largely restate the frontmatter description, a minor instance of redundancy that could be trimmed, keeping it just below anchor 5.	4 / 5
Actionability	The instruction bullets name concrete dbt concepts (staging/intermediate/marts layers, materializations, selectors, freshness checks, CI workflows), but they are high-level directives ("Define...", "Implement...", "Choose...") with no specific commands, config, or executable detail, deferring all specifics to the reference file.	3 / 5
Workflow Clarity	The instructions are a parallel task list with no sequenced ordering and no validation checkpoints, and because dbt runs are batch/database operations the missing test-or-validate feedback loop caps the score well below the clearer-sequence anchors.	2 / 5
Progressive Disclosure	The structure is clean with a single one-level-deep reference clearly signaled in both Instructions and Resources, but the referenced file `resources/implementation-playbook.md` does not exist in the bundle, so the disclosure path the skill relies on for all detailed patterns is broken and navigation is incomplete.	3 / 5
	Total	12 / 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 solid, well-scoped description that states both what the skill does and when to use it with concrete dbt-specific triggers. It is specific and distinctive, with only minor gaps in action concreteness and trigger synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the dbt domain plus several concrete capabilities ("model organization, testing, documentation, and incremental strategies"), but these are domain areas rather than crisp executable actions, leaving minor coverage gaps versus the comprehensive anchor 5.	4 / 5
Completeness	It answers both "what" (master dbt with the listed capabilities) and "when" (three explicit "Use when" trigger phrases), but the "when" clauses lean slightly abstract ("analytics engineering best practices") rather than fully concrete trigger phrases, falling just short of anchor 5.	4 / 5
Trigger Term Quality	"Use when building data transformations, creating data models, or implementing analytics engineering best practices" gives good natural-term coverage including the dbt/data build tool name, though synonyms like ELT or data pipelines are missing.	4 / 5
Distinctiveness Conflict Risk	dbt (data build tool) is a clearly named niche tool with distinct triggers, but broader phrases like "data transformations" and "data models" carry minor overlap risk with general data-engineering or SQL skills, so it sits at anchor 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/dbt-transformation-patterns/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.