Name: cosmos-dbt-core
Rating: 64.8 (1 reviews)
Author: astronomer

cosmos-dbt-core

Turns a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Use turning a dbt Core project into an Airflow DAG or TaskGroup with Astronomer Cosmos. Before implementing, verify dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, and manifest availability.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with concrete executable code and a clear sequenced checklist, but held back by length that should live in (missing) reference files and by broken references to a non-existent reference/cosmos-config.md.

Suggestions

Create the referenced reference/cosmos-config.md (or remove the broken "See reference/cosmos-config.md" links) so the signaled progressive disclosure is real and the per-mode ProfileConfig/operator_args detail can move out of SKILL.md.

Add mid-process validation checkpoints with fix-and-retry guidance (e.g., confirm the manifest loads and the warehouse connection resolves before assembling the full DAG), not just the final §8 checklist, to satisfy the feedback-loop expectation for dbt/database operations.

Trim §7's three full DAG examples and Appendix B operational extras to a single canonical pattern, offloading variants to reference files, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The ~450-line body is mostly efficient (dense tables, no basic-concept explanations) but includes multiple full code examples (three DAG assemblies in §7) and operational appendices that could be tightened or moved to reference files; not every token earns its place.	2 / 3
Actionability	Concrete, executable Python with imports throughout (ProjectConfig, RenderConfig, DbtDag, DbtTaskGroup, operators) plus when-to-use tables make the guidance copy-paste ready.	3 / 3
Workflow Clarity	There is a clear numbered sequence (§1–§8), a pre-flight confirmation, and a final §8 safety checklist, but no mid-process validate→fix→retry feedback loops; for dbt (database) operations the missing feedback loops cap this at 2 per the rubric notes.	2 / 3
Progressive Disclosure	The body repeatedly signals "See reference/cosmos-config.md" (§3, §4, §5, §6), but no references/ directory or cosmos-config.md exists, so the links are broken and the detail stays inline; sections are well organized but the file split is not actually realized.	2 / 3
	Total	9 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description with natural trigger terms and an explicit "Use..." clause; its main weakness is a redundant restatement of the single core action rather than a broader set of concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes "Turns a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos" name the domain and a core action, but it is essentially one transformation restated ("Use turning a dbt Core project into an Airflow DAG or TaskGroup..."), not a list of multiple distinct concrete actions.	2 / 3
Completeness	It states the what ("Turns a dbt Core project into an Airflow DAG/TaskGroup...") and provides an explicit "Use..." trigger clause, so the when is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Natural terms a user would say are well covered: "dbt Core", "Airflow DAG", "TaskGroup", "Astronomer Cosmos", and "manifest".	3 / 3
Distinctiveness Conflict Risk	The niche is precise (dbt Core + Airflow + Cosmos) and the verification of "dbt engine" (Core, not Fusion) clearly distinguishes it from the related Fusion skill, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: astronomer/agents
Commit: 8827e93

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.