using-dbt-for-analytics-engineering

Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes. Use for analytics pipelines, data transformations, and data modeling.

Install with Tessl CLI

npx tessl i github:dbt-labs/dbt-agent-skills --skill using-dbt-for-analytics-engineering

What are skills?

Quality

69%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/using-dbt-for-analytics-engineering/SKILL.md

SKILL.md

Review

Evals

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description with explicit trigger guidance and good keyword coverage for dbt-related work. The main weakness is that some actions are described at a category level rather than with concrete specifics, and broader data engineering terms could cause overlap with other skills.

Suggestions

Add more specific concrete actions like 'generate ref() macros', 'create schema.yml tests', 'build incremental models', or 'configure sources.yml'

Consider adding file extensions or patterns like '.sql models', 'dbt_project.yml', or 'profiles.yml' to increase distinctiveness from general SQL skills

Dimension	Reasoning	Score
Specificity	Names the domain (dbt) and lists several actions (building models, debugging errors, writing tests, evaluating impact), but these are somewhat general categories rather than highly specific concrete actions like 'generate incremental models' or 'create schema.yml files'.	2 / 3
Completeness	Explicitly answers both what (building/modifying models, debugging, exploring data, writing tests, evaluating changes) AND when with clear 'Use when...' clause at the start. The trigger guidance is explicit and comprehensive.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'dbt', 'models', 'debugging errors', 'data sources', 'tests', 'analytics pipelines', 'data transformations', 'data modeling'. Good coverage of terms a user working with dbt would naturally use.	3 / 3
Distinctiveness Conflict Risk	While 'dbt' is distinctive, terms like 'analytics pipelines', 'data transformations', and 'data modeling' could overlap with general SQL skills or other data engineering tools. The dbt-specific focus helps but broader terms create some conflict risk.	2 / 3
	Total	10 / 12 Passed

Implementation

57%

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

This skill provides solid guidance for dbt analytics engineering with excellent progressive disclosure through well-organized reference links. However, it lacks concrete executable examples in the main file, relying heavily on referenced guides for implementation details. The workflow guidance would benefit from explicit numbered steps with validation checkpoints rather than scattered mentions of best practices.

Suggestions

Add a concrete, executable example workflow showing the full cycle: discover data → plan model → write SQL → validate with dbt show → iterate

Include at least one copy-paste ready code snippet demonstrating proper ref/source usage and CTE structure

Convert the 'Model building guidelines' into a numbered checklist with explicit validation gates (e.g., '1. Read YAML docs ✓ 2. Run dbt show on source ✓ 3. Write initial CTE...')

Consolidate the 'Common Mistakes' and 'Rationalizations to Resist' tables to reduce redundancy

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but includes some redundancy - the 'Common Mistakes' and 'Rationalizations to Resist' tables overlap conceptually, and some guidelines repeat points (e.g., using dbt show is mentioned multiple times across sections). However, it avoids explaining what dbt is or basic concepts Claude would know.	2 / 3
Actionability	Provides clear guidance and specific commands (dbt show, --limit, --defer flags) but lacks executable code examples. The content describes what to do rather than showing complete, copy-paste ready examples. Most concrete implementation details are deferred to reference guides.	2 / 3
Workflow Clarity	Multi-step processes are implied but not explicitly sequenced with validation checkpoints. The 'Model building guidelines' mention reading YAML first and using dbt show, but there's no numbered workflow with explicit validation gates. The iterative approach is mentioned but not structured as a clear feedback loop.	2 / 3
Progressive Disclosure	Excellent structure with a clear overview and well-organized reference table pointing to one-level-deep guides. The table format makes navigation easy, and content is appropriately split between the main skill and detailed reference files.	3 / 3
	Total	9 / 12 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
license_field	'license' field is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
body_examples	No examples detected (no code fences and no 'Example' wording)	Warning
body_steps	No step-by-step structure detected (no ordered list); consider adding a simple workflow	Warning

	Total	11 / 16 Passed

Reviewed: about 1 month 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.