dbt-transformation-patterns

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

Quality

60%

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/AI-Agents-Safe-Coding-Skills-claude/skills/dbt-transformation-patterns/SKILL.md

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

Quality

Content

55%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.

The skill body is concise and well-structured with clear use/don't-use triggers, but the Instructions are abstract directives with no executable code, commands, or sequenced validation workflow, and the single detailed reference points to a file that is not present in the bundle. Adding concrete dbt examples and a real playbook file would most improve it.

Suggestions

Add concrete, executable guidance — e.g. example SQL/YAML for a staging model, a sample schema.yml test block, and commands like `dbt run --select staging.+` / `dbt test --select mart_my_model`.

Convert the Instructions checklist into a numbered workflow with validation checkpoints (e.g. run `dbt compile` → `dbt run` → `dbt test` → fix and re-run on failure) appropriate to dbt batch/database operations.

Create the referenced `resources/implementation-playbook.md` (or correct the path to an existing bundle file) so the one-level-deep reference resolves and progressive disclosure is fully navigable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse bullets, no explanation of what dbt is or how libraries work; the only mild redundancy is the intro line echoing the frontmatter description, which is a header convention rather than padding.	5 / 5
Actionability	Instructions are high-level directives ('Define model layers, naming, and ownership', 'Choose materializations and incremental strategies') with no concrete code, SQL/YAML snippets, or dbt commands, and the only detailed reference points to a missing playbook file — minimal concrete guidance matching the anchor 2.	2 / 5
Workflow Clarity	The Instructions are an unordered checklist rather than a sequenced workflow, with no validation checkpoints or feedback loops; because dbt involves batch/database operations the rubric caps this at 3, and the absence of any real sequence places it at anchor 2.	2 / 5
Progressive Disclosure	Structure is good with a clear overview, well-labeled sections (Use/Do-not-use when, Instructions, Resources) and a clearly signaled one-level-deep reference; the gap is that the referenced resources/implementation-playbook.md does not exist in the bundle, so navigation is partially broken.	4 / 5
	Total	13 / 20 Passed

Description

66%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.

The description clearly conveys what the skill covers across several concrete dbt capability areas and targets a distinct niche, but it omits any explicit 'when to use it' trigger guidance, which caps completeness at 3. Adding a Use-when clause with natural trigger phrases would lift the weakest dimension.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when building dbt pipelines, organizing staging/intermediate/marts models, or setting up dbt tests and incremental materializations.'

Add common user phrasings and synonyms (e.g. 'dbt models', 'data transformation pipelines', '.sql models', 'dbt run') to strengthen trigger-term coverage toward anchor 5.

Reframe capability categories as discrete actions (e.g. 'Organize models into staging/intermediate/marts layers; add data-quality tests; configure incremental materializations') to nudge specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the dbt domain and lists several concrete capability areas — 'model organization, testing strategies, documentation, and incremental processing' — but these are capability categories rather than discrete executable actions, leaving minor coverage gaps versus the comprehensive anchor 5.	4 / 5
Completeness	Provides a clear 'what' but no explicit 'when'/'Use when...' clause; per the rubric, a missing explicit trigger guidance caps completeness at 3, matching the anchor 'Has a clear what but when is missing'.	3 / 5
Trigger Term Quality	Includes the natural core terms 'dbt (data build tool)' plus capability keywords (model organization, testing, incremental processing); a few natural user phrasings like 'dbt models' or 'data transformation pipelines' are absent, so it falls just below the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The dbt niche is clearly distinct with specific triggers, but without an explicit use-when clause and given minor overlap with general SQL/data-warehouse engineering skills, it sits just below the minimal-conflict anchor 5.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/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.