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.
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 well-crafted description for a niche technical skill. It excels at completeness with explicit 'Use when' guidance, exclusion criteria, and prerequisites. The main weakness is that it describes scope and constraints rather than listing concrete actions the skill enables (e.g., configuring profiles, setting up DAGs, troubleshooting).
Suggestions
Add specific concrete actions the skill performs, e.g., 'Configures Cosmos operators, sets up dbt profiles, defines Airflow DAG settings for Fusion execution.'
| 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' (explicit 'Use when running a dbt Fusion project with Astronomer Cosmos'). Also includes helpful exclusion criteria ('Does not cover dbt Core') and prerequisites to verify. | 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 + Astronomer Cosmos + specific warehouses + specific execution mode. The explicit exclusion of dbt Core further reduces conflict risk with any dbt Core-related 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 well-structured, highly actionable skill that provides a clear step-by-step checklist for configuring Cosmos with dbt Fusion. Its main strengths are executable code examples at every step and explicit validation checkpoints. Weaknesses include some redundancy (warehouse support and execution mode constraints repeated multiple times) and the absence of the referenced bundle file, though the references themselves are well-signaled.
Suggestions
Reduce repetition of warehouse support list and LOCAL-only constraint — state each once prominently rather than restating in constraints table, step headers, and final checklist.
Provide the referenced 'reference/cosmos-config.md' bundle file to support the progressive disclosure references, or remove the references if the file won't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the constraint table and inline warnings repeat information (e.g., warehouse support mentioned 3+ times, LOCAL-only mentioned multiple times). The full DbtDag example in step 7 re-declares all configs already shown in steps 4-6, adding token cost. However, it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code for every step: Dockerfile install, Python config objects, complete DAG examples with imports. Commands for validation (pip show, dbt --version) are concrete and specific. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced with explicit validation checkpoints after critical steps (version check, binary install, final checklist). The final validation section includes a comprehensive checklist and troubleshooting guidance. The 'Before starting' gate conditions prevent wasted effort on unsupported configurations. | 3 / 3 |
Progressive Disclosure | References to 'reference/cosmos-config.md' are well-signaled with anchor links, and related skills are listed. However, no bundle files were provided, so the referenced file doesn't exist, and the main SKILL.md is fairly long (~180 lines) with full inline examples that could potentially be split out. The structure is reasonable but the content is somewhat monolithic. | 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.