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-crafted skill description that clearly defines its niche at the intersection of dbt Core and Airflow via Astronomer Cosmos. It excels at completeness with an explicit 'Use when' clause, exclusion criteria, and prerequisite checks. The main weakness is that it could be more specific about the concrete actions it performs beyond the high-level 'turning into a DAG/TaskGroup'.
Suggestions
Add more specific concrete actions the skill performs, e.g., 'Generates DbtTaskGroup configurations, sets up render configs, configures operator arguments, handles profile connections' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (dbt Core to Airflow DAG/TaskGroup using Astronomer Cosmos) and mentions some actions like verifying prerequisites, but it doesn't list multiple concrete actions beyond 'turning a dbt Core project into an Airflow DAG/TaskGroup'. The verification checklist adds some specificity but these are preconditions rather than actions the skill performs. | 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). It also specifies when NOT to use it (does not cover dbt Fusion) and lists prerequisite checks, making the trigger guidance very explicit. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: 'dbt Core', 'Airflow', 'DAG', 'TaskGroup', 'Astronomer Cosmos', 'dbt Fusion', 'manifest', 'warehouse', 'execution environment'. These are highly specific technical terms that a user working in this domain would naturally use. | 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 other 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 step-by-step implementation checklist with executable code at every stage. The decision tables for choosing load modes, execution modes, and testing behaviors are particularly effective. The main weakness is length—Option C's full operator example and some appendix content could be moved to reference files to improve token efficiency.
Suggestions
Move the full Option C (individual operators) example to the reference file or a separate examples file, keeping only a brief snippet in the main skill to reduce token usage.
Trim Appendix B operational extras to one-line descriptions with links to the reference file, since these are supplementary and inflate the main skill's token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient but includes some redundancy—e.g., the full Option C operator example is quite long and could be trimmed or moved to a reference file. The tables and config blocks are well-structured but the overall length (~300 lines) pushes beyond what's strictly necessary for a checklist-style skill. | 2 / 3 |
Actionability | Every step includes executable Python code with real imports, concrete parameter names, and copy-paste-ready examples. The decision tables clearly map constraints to choices, and three complete DAG assembly patterns (DbtDag, DbtTaskGroup, individual operators) are fully runnable. | 3 / 3 |
Workflow Clarity | The 8-step numbered sequence is clear and logically ordered (configure → parse → execute → connect → test → assemble → verify). Step 8 provides an explicit safety checklist with validation checkpoints, and critical warnings are called out with bold markers throughout. | 3 / 3 |
Progressive Disclosure | The main content serves as a concise overview with decision tables, while detailed configuration is delegated to a single reference file (reference/cosmos-config.md) with clearly signaled section anchors. Appendices handle version compatibility and operational extras without cluttering the main flow. Related skills are linked at the bottom. | 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
166c98a
- 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.