using-dbt-for-analytics-engineering
tessl install github:dbt-labs/dbt-agent-skills --skill using-dbt-for-analytics-engineeringUse 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.
Review Score
71%
Validation Score
11/16
Implementation Score
57%
Activation Score
82%
Generated
Validation
Total
11/16Score
Passed| Criteria | Score |
|---|---|
metadata_version | 'metadata.version' is missing |
license_field | 'license' field is missing |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata |
body_examples | No examples detected (no code fences and no 'Example' wording) |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow |
Implementation
Suggestions 3
Score
57%Overall Assessment
This skill demonstrates strong organization and progressive disclosure with a well-structured reference table, but sacrifices actionability by delegating most concrete guidance to external files. The content would benefit from at least one complete executable example in the main file and a clearer step-by-step workflow with explicit validation checkpoints.
Suggestions
- Add at least one complete, executable dbt command example (e.g., a full 'dbt show' command with realistic flags and expected output format) directly in the main skill file
- Convert the 'Model building guidelines' section into an explicit numbered workflow with validation checkpoints (e.g., '1. Read YAML docs → 2. Plan approach → 3. Write SQL → 4. Validate with dbt show → 5. If errors, fix and re-validate')
- Consolidate the 'Common Mistakes' and 'Rationalizations to Resist' tables to reduce redundancy - they cover similar ground about user requests and verification
| Dimension | Score | Reasoning |
|---|---|---|
Conciseness | 2/3 | The content is mostly efficient but includes some redundancy - the 'Common Mistakes' and 'Rationalizations to Resist' tables overlap conceptually, and some guidance is repeated across sections (e.g., 'use dbt show' appears multiple times). The tables add structure but could be tighter. |
Actionability | 2/3 | Provides clear guidance and principles but lacks executable code examples. Commands like 'dbt show' and 'dbt build --select' are mentioned but not shown with complete, copy-paste ready examples. The skill relies heavily on external reference files for concrete implementation details. |
Workflow Clarity | 2/3 | Multi-step processes are implied but not explicitly sequenced with validation checkpoints. The 'Model building guidelines' section mentions following a reference guide and using 'dbt show' but doesn't provide an explicit numbered workflow with feedback loops for error recovery. |
Progressive Disclosure | 3/3 | Excellent structure with a clear reference table pointing to one-level-deep guides for specific tasks. The main skill provides an overview with well-signaled links to detailed materials (planning, discovering, testing, debugging, etc.). |
Activation
Suggestions 2
Score
82%Overall Assessment
This is a solid description that clearly communicates when to use the skill with explicit trigger guidance and good keyword coverage for dbt users. The main weaknesses are moderate specificity (actions could be more concrete) and some overlap risk with other data engineering skills due to generic terms like 'analytics pipelines' and 'data transformations'.
Suggestions
- Add more dbt-specific concrete actions like 'generate incremental models', 'configure sources and seeds', 'write schema.yml documentation', or 'run dbt test/build commands'
- Strengthen distinctiveness by emphasizing dbt-specific artifacts like '.sql model files', 'dbt_project.yml', 'ref() and source() functions' to reduce overlap with general SQL or data pipeline skills
| Dimension | Score | Reasoning |
|---|---|---|
Specificity | 2/3 | Names the domain (dbt) and lists several actions (building models, debugging errors, writing tests, evaluating impact), but uses somewhat general terms rather than highly specific concrete actions like 'generate incremental models' or 'configure source freshness checks'. |
Completeness | 3/3 | Explicitly answers both what (dbt work including building/modifying models, debugging, exploring data, writing tests, evaluating changes) and when ('Use when doing any dbt work' plus specific trigger scenarios). Has clear 'Use when...' clause. |
Trigger Term Quality | 3/3 | 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. |
Distinctiveness Conflict Risk | 2/3 | While 'dbt' is a distinct tool, terms like 'analytics pipelines', 'data transformations', and 'data modeling' could overlap with general SQL skills, Airflow skills, or other data engineering tools. The dbt-specific triggers help but broader terms create some conflict risk. |