cosmos-dbt-fusion
Use when running a dbt Fusion project with Astronomer Cosmos. Covers Cosmos 1.11+ configuration for Fusion on Snowflake/Databricks with ExecutionMode.LOCAL. Before implementing, verify dbt engine is Fusion (not Core), warehouse is supported, and local execution is acceptable. Does not cover dbt Core.
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 well-crafted description for a niche technical skill. It excels at completeness by providing explicit 'use when' guidance, prerequisites, and exclusions, and its trigger terms are highly specific to the domain. The main weakness is that it describes scope and constraints rather than listing concrete actions the skill enables (e.g., 'configure Cosmos operators', 'set up dbt profiles').
Suggestions
Add 2-3 concrete actions the skill performs, e.g., 'Configures Cosmos operators, sets up dbt profiles, and defines Airflow DAG integration for dbt Fusion projects.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt Fusion with Astronomer Cosmos) and mentions some specifics like 'Cosmos 1.11+ configuration', 'Snowflake/Databricks', and 'ExecutionMode.LOCAL', but doesn't list concrete actions (e.g., 'configure DAGs', 'set up profiles', 'define operators'). It describes scope and constraints more than specific actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (covers Cosmos 1.11+ configuration for Fusion on Snowflake/Databricks with ExecutionMode.LOCAL) and 'when' ('Use when running a dbt Fusion project with Astronomer Cosmos'). Also includes explicit exclusions ('Does not cover dbt Core') and prerequisites to verify before implementing. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'dbt Fusion', 'Astronomer Cosmos', 'Cosmos 1.11', 'Snowflake', 'Databricks', 'ExecutionMode.LOCAL', 'dbt Core'. These are highly specific technical terms that users working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: dbt Fusion (not Core) + Astronomer Cosmos + specific warehouses + specific execution mode. The explicit exclusion of dbt Core further reduces conflict risk with any general dbt skill. | 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 implementation checklist for Cosmos + dbt Fusion. Its main strengths are excellent workflow clarity with validation checkpoints at each step, fully executable code examples, and good progressive disclosure with references to detailed config docs. The primary weakness is moderate redundancy — config objects are fully redeclared in the DAG assembly step, and some constraints (LOCAL-only, binary path) are stated multiple times.
Suggestions
In Step 7's DbtDag example, reference the config objects from Steps 3-6 rather than re-declaring them, reducing ~15 lines of duplication while keeping the example self-contained via a comment like '# using configs from steps 3-6 above'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the full DbtDag example in Step 7 re-declares all config objects already shown in Steps 3-6, and some constraints are repeated (e.g., LOCAL-only and Fusion binary path mentioned multiple times). The constraint table and version notes are tight, but overall could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for every step: Dockerfile install, Python config objects, complete DAG examples for both DbtDag and DbtTaskGroup patterns. Commands for version checking and installation are concrete and specific. | 3 / 3 |
Workflow Clarity | Clear numbered sequence from version confirmation through binary installation, configuration, assembly, and final validation. Each step has explicit validation checkpoints (pip show, binary existence check, final checklist with checkboxes). The final validation section includes a comprehensive checklist and user testing requirements. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview, sequential steps, and one-level-deep references to cosmos-config.md for detailed ProfileConfig options. Related skills are signposted at the end. External docs are linked without nesting. Content is appropriately split between the main skill and reference files. | 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.