cosmos-dbt-core
Use when turning a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Does not cover dbt Fusion. Before implementing, verify dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, and manifest availability.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 strong, well-targeted skill description that clearly identifies its niche at the intersection of dbt Core, Airflow, and Astronomer Cosmos. It excels at trigger term quality and distinctiveness with explicit scope boundaries. The main weakness is that it could list more concrete actions/capabilities beyond the high-level 'turning a project into a DAG/TaskGroup'.
Suggestions
Add 2-3 more specific concrete actions the skill performs, such as 'configures DbtTaskGroup operators, sets up rendering strategies, handles profile/connection mapping' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt Core to Airflow DAG/TaskGroup using Astronomer Cosmos) and mentions some actions like verifying prerequisites, but doesn't list multiple concrete actions beyond 'turning a dbt Core project into an Airflow DAG/TaskGroup'. The checklist items (verify dbt engine, warehouse, etc.) are prerequisites rather than distinct capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (turning a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos) and 'when' (explicit 'Use when' clause at the start). Also includes scope boundaries (does not cover dbt Fusion) and prerequisite checks, making the trigger guidance explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'dbt Core', 'Airflow', 'DAG', 'TaskGroup', 'Astronomer Cosmos', 'manifest', 'dbt Fusion' (as exclusion). These are highly specific terms that match what a user working in this domain would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining dbt Core + Airflow + Astronomer Cosmos. The explicit exclusion of dbt Fusion further reduces conflict risk. This is unlikely to be confused with generic dbt skills, generic Airflow skills, or other integration skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides a clear sequential workflow for implementing Cosmos + dbt Core in Airflow. The decision tables at each step are excellent for guiding choices, and the code examples are complete and executable. The main weakness is that Option C's example is quite lengthy and could be moved to a reference file to improve conciseness, and a few sections include slightly more detail than necessary for Claude's competence level.
Suggestions
Consider moving the full Option C (direct operators) example to a reference file and keeping only a brief snippet in the main skill, as it's significantly longer than the other options and adds ~50 lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient but includes some unnecessary verbosity—Option C's full example with S3 checking is quite long and could be trimmed or moved to a reference file. The tables are well-structured but some sections (like the operator_args example) include comments that add marginal value. Overall mostly lean but could be tightened. | 2 / 3 |
Actionability | Every step includes fully executable Python code with real imports, concrete configuration objects, and copy-paste ready examples. The tables clearly map decision criteria to specific enum values and parameters. All three DAG assembly options (DbtDag, DbtTaskGroup, direct operators) are complete and runnable. | 3 / 3 |
Workflow Clarity | The 8-step sequential workflow is clearly numbered and logically ordered from project config through assembly to safety checks. Step 8 provides an explicit validation checklist before finalizing. The decision tables at each step guide the user to the correct option based on their constraints, and critical warnings are clearly marked. | 3 / 3 |
Progressive Disclosure | The skill uses a clear overview structure with well-signaled one-level-deep references to 'reference/cosmos-config.md' for detailed configuration. Appendices appropriately separate operational extras and compatibility notes from the main workflow. Related skills are linked at the bottom for navigation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- astronomer/agents
- Commit
0642adb
- Reviewed
Table of Contents
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.