dbt-transformation-patterns

Production-ready patterns for dbt (data build tool) including model organization, testing strategies, documentation, and incremental processing.

Quality

38%

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

The canonical home for this skill is dbt-transformation-patterns in rmyndharis/antigravity-skills

Quality

Content

32%Scale 1-5

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

This skill is essentially a table of contents with no actionable content. It correctly identifies when to use dbt patterns and references an external playbook, but the body itself provides zero concrete guidance — no code examples, no specific commands, no executable patterns. The skill fails its primary purpose of teaching Claude how to perform dbt transformations.

Suggestions

Add concrete, executable dbt code examples inline — at minimum a staging model template, a basic test configuration in schema.yml, and an incremental model pattern with the is_incremental() macro.

Provide specific dbt commands for common workflows (e.g., `dbt run --select staging+`, `dbt test --select tag:critical`, `dbt build --defer --state prod-manifest/`).

Include the referenced `resources/implementation-playbook.md` bundle file, or inline the essential patterns if the file doesn't exist.

Add validation checkpoints to the workflow, such as verifying model compilation with `dbt compile`, running tests after builds, and checking freshness with `dbt source freshness`.

Dimension	Reasoning	Score
Conciseness	The content is fairly lean and doesn't over-explain concepts Claude already knows. The 'Use this skill when' and 'Do not use this skill when' sections add some bulk but are reasonable for scoping. Minor trimming possible in the description repeating the frontmatter.	4 / 5
Actionability	The instructions are entirely vague and abstract — 'Define model layers,' 'Implement tests,' 'Choose materializations' — with zero concrete code, commands, examples, or specific guidance. Everything actionable is deferred to a bundle file that doesn't exist.	1 / 5
Workflow Clarity	There is a rough sequence implied in the instructions (define layers → implement tests → choose materializations → optimize runs), but steps are poorly defined with no specifics, no validation checkpoints, and no concrete commands. The workflow is essentially a high-level outline.	2 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable structure, but no bundle files are provided so the reference is unverifiable and potentially broken. The SKILL.md itself contains almost no substantive content — it's an empty shell pointing to a file that may not exist.	2 / 5
	Total	9 / 20 Passed

Description

45%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.

The description identifies the dbt domain clearly and lists relevant topic areas, providing reasonable distinctiveness. However, it lacks concrete actions (listing categories like 'model organization' rather than specific capabilities) and entirely omits a 'Use when...' clause, making it harder for Claude to know when to select this skill over others.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks about dbt projects, SQL models, data transformations, dbt testing, or incremental models'.

Replace category labels with concrete actions, e.g., 'Creates and organizes dbt models, configures schema tests, writes documentation blocks, and implements incremental materialization strategies'.

Include additional natural trigger terms and synonyms such as 'SQL models', 'staging/marts layers', 'dbt project', 'sources', 'snapshots', '.yml schema files'.

Dimension	Reasoning	Score
Specificity	Names the domain (dbt) and lists several areas (model organization, testing strategies, documentation, incremental processing), but these are categories rather than concrete actions. It doesn't specify what actions are performed—e.g., 'creates models', 'configures tests', 'generates documentation'.	3 / 5
Completeness	Provides a reasonable 'what' (production-ready patterns for dbt covering several areas), but there is no 'when' clause at all—no 'Use when...' or equivalent trigger guidance. Per rubric guidelines, missing 'Use when' caps completeness at 3, and since the 'what' is also somewhat vague (patterns rather than actions), a score of 2 is appropriate.	2 / 5
Trigger Term Quality	Includes 'dbt', 'data build tool', 'model', 'testing', 'incremental' which are relevant keywords. However, it misses natural user phrases like 'SQL models', 'dbt project', 'staging models', 'marts', 'sources', 'snapshots', 'dbt run', 'ref()', or file extensions like '.sql', '.yml'.	3 / 5
Distinctiveness Conflict Risk	The explicit mention of 'dbt (data build tool)' creates a fairly distinct niche. It could potentially overlap with general SQL or data engineering skills, but the dbt-specific framing reduces conflict risk significantly.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/dbt-transformation-patterns/SKILL.md
Commit: 57c135b

Reviewed: 3 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.