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.
68
83%
Does it follow best practices?
Impact
—
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 and Airflow via Astronomer Cosmos. It includes an explicit 'Use when' clause, relevant exclusions, and prerequisite verification steps. The main weakness is that it could be more specific about the concrete implementation actions it performs beyond the high-level 'turning into a DAG/TaskGroup'.
Suggestions
Add 2-3 more specific concrete actions the skill performs, such as 'configures DbtTaskGroup operators, sets up Cosmos profiles, handles render config and execution config settings'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (dbt Core to Airflow DAG/TaskGroup using Astronomer Cosmos) and mentions some actions like 'turning a dbt Core project into an Airflow DAG/TaskGroup' and verification steps, but it doesn't list multiple concrete implementation actions (e.g., configuring operators, setting up profiles, defining task dependencies). | 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, plus exclusion criteria like 'Does not cover dbt Fusion' and prerequisite checks). The 'Use when' trigger is explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'dbt Core', 'Airflow', 'DAG', 'TaskGroup', 'Astronomer Cosmos', 'manifest', 'dbt Fusion'. These are the exact terms a user working in this space would use when asking for help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: the intersection of dbt Core, Airflow, and Astronomer Cosmos. The explicit exclusion of dbt Fusion further reduces conflict risk. This is unlikely to be confused with general dbt skills or general Airflow skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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, highly actionable skill that provides a clear sequential workflow for implementing Cosmos + dbt Core in Airflow. Its main strength is the combination of decision tables and executable code at each step, plus the safety checklist at the end. Its primary weakness is length—the skill could be more concise by offloading the lengthy Option C example and some appendix content to reference files, improving both conciseness and progressive disclosure.
Suggestions
Move the lengthy Option C (individual operators example with S3 check) to a reference file like `reference/cosmos-operators-example.md` and link to it, reducing the main skill's token footprint.
Consider trimming Appendix B operational extras into a separate reference file, keeping only a brief mention and link in the main skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient and avoids explaining basic concepts, but it's quite long (~300+ lines) with some redundancy. The three full DAG assembly examples (Options A, B, C) are verbose, and Option C in particular is very lengthy with an S3 check example that may not be needed. The tables are well-structured but some could be tighter. | 2 / 3 |
Actionability | Every step includes fully executable Python code with correct imports, concrete configuration objects, and copy-paste ready examples. The tables clearly map constraints to choices, and the code examples cover DbtDag, DbtTaskGroup, and individual operators with real-world patterns including XCom usage and task chaining. | 3 / 3 |
Workflow Clarity | The 8-step sequential workflow is clearly numbered and logically ordered (configure project → parsing → execution → connection → testing → operator_args → assemble → safety checks). Step 8 provides an explicit safety checklist with validation checkpoints covering secrets, mode compatibility, and asset URIs. The 'Before starting' prerequisites add a critical pre-flight check. | 3 / 3 |
Progressive Disclosure | The skill references `reference/cosmos-config.md` for detailed configuration in steps 3-6, which is good progressive disclosure. However, no bundle files were provided, so we can't verify these references resolve. The appendices are well-structured but the main body is still quite long—some of the detailed operator examples (especially Option C) could be offloaded to reference files. The related skills section at the end is a nice touch. | 2 / 3 |
Total | 10 / 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
535a040
- 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.