Name: cosmos-dbt-fusion
Rating: 68.8 (1 reviews)
Author: astronomer

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.

Quality

83%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

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, actionable skill with clear step-by-step workflow, executable code examples, and explicit validation checkpoints. Its main weaknesses are moderate redundancy (config objects declared twice across steps and the full example) and the inability to verify the referenced bundle file. Overall it serves as an effective implementation checklist for the specific Cosmos + dbt Fusion use case.

Suggestions

Remove the redundant re-declaration of config objects in Step 7's DbtDag example by referencing the variables already defined in Steps 3-6, or consolidate into a single complete example and make Steps 3-6 explanatory only.

Include the referenced 'reference/cosmos-config.md' bundle file so progressive disclosure can be fully validated, or inline the essential ProfileConfig details if the file doesn't exist.

Dimension	Reasoning	Score
Conciseness	Generally efficient but has some redundancy — the full DbtDag example in Step 7 re-declares all four config objects already shown in Steps 3-6, and some constraints are repeated (e.g., LOCAL-only is stated multiple times). The constraint table and version notes are well-structured, but the overall content could be tightened.	2 / 3
Actionability	Every step includes fully executable, copy-paste-ready code with specific imports, paths, and configuration. The Dockerfile install snippet, pip commands, and complete DAG examples are concrete and immediately usable.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced with explicit validation checkpoints ('Validate' callouts after Steps 1 and 2, a final validation checklist in Step 8 with both automated checks and user-must-test items). The checklist format with feedback loops for troubleshooting is well done.	3 / 3
Progressive Disclosure	References to 'reference/cosmos-config.md' are well-signaled with anchor links, but no bundle files were provided, so we cannot confirm the referenced file exists. The main SKILL.md is fairly long (~200 lines) and some content (e.g., the full DbtTaskGroup example) could potentially be split out, though it's not egregiously monolithic.	2 / 3
	Total	10 / 12 Passed

Description

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 trigger term coverage, completeness with explicit 'Use when' guidance, and distinctiveness through specific technology stack references and explicit exclusions. The main weakness is that it describes scope and prerequisites rather than listing concrete actions the skill performs.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Configures DbtDag render settings, sets up Snowflake/Databricks profiles, defines operator arguments for local execution.'

Dimension	Reasoning	Score
Specificity	The description names the domain (dbt Fusion with Astronomer Cosmos) and mentions some specifics like 'Cosmos 1.11+ configuration', 'Snowflake/Databricks', and 'ExecutionMode.LOCAL', but it doesn't list concrete actions (e.g., 'configure DAGs', 'set up profiles', 'define render config'). It describes scope and prerequisites more than specific actions.	2 / 3
Completeness	Clearly answers both 'what' (Cosmos 1.11+ configuration for Fusion on Snowflake/Databricks with ExecutionMode.LOCAL) and 'when' ('Use when running a dbt Fusion project with Astronomer Cosmos'). It also includes explicit pre-conditions and scope boundaries (does not cover dbt Core), which strengthens the 'when' guidance.	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 the exact terms a user working in this domain would use, and the explicit exclusion of 'dbt Core' helps prevent false matches.	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. This is unlikely to be confused with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: 789b454

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.