CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cosmos-dbt-core/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

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

A strong, highly actionable checklist: concrete executable code, explicit decision tables, and validation checklists at the start and end. The two real defects are the broken references to a nonexistent reference/cosmos-config.md file and some inlined long-form content (the 80-line Option C example, Appendix B) that should live in that reference file.

Suggestions

Create the referenced reference/cosmos-config.md file (or fix the path to an existing references/ file) — all four in-body links to it currently dead-end.

Move the long Option C example (individual operators + S3 check, ~80 lines) and Appendix B's operational extras into the reference file, keeping a one-line pointer plus a minimal inline snippet per section.

Merge the two RenderConfig sections (§2 parsing strategy and §5 testing behavior) or cross-reference them so the config object is configured in one place.

DimensionReasoningScore

Conciseness

The body is dense with decision tables and code and assumes Claude's competence ("Execute steps in order. Prefer the simplest configuration that meets the user's constraints"), with no re-explanation of known concepts. It sits at 4 rather than 5 because the ~80-line Option C example (S3 file checks, clone operator) and duplicated RenderConfig coverage in sections 2 and 5 could be trimmed.

4 / 5

Actionability

Every section gives copy-paste-ready code with concrete arguments (ProjectConfig, DbtDag, DbtTaskGroup, operator_args dict) plus decision tables specifying required params and exact env vars (AIRFLOW__COSMOS__REMOTE_TARGET_PATH, DBT_DOCS_PROJECTS JSON). This matches the fully-executable anchor covering the common cases.

5 / 5

Workflow Clarity

The workflow is explicitly ordered ("Execute steps in order", numbered sections 1-8) with validation checkpoints at both ends: an upfront "Before starting, confirm: (1)...(6)" checklist and a closing Safety Checks checklist. This matches the anchor requiring explicit validation steps and checklists for complex processes; no meaningful checkpoint gaps remain.

5 / 5

Progressive Disclosure

References are clearly signaled and one level deep ("See [reference/cosmos-config.md](...#execution-modes-executionconfig)"), but the bundle contains no reference file at all — the four links to reference/cosmos-config.md point to a nonexistent path, and the detail that would live there is inlined in the body. Structure is good, but broken navigation fits anchor 3 rather than 4.

3 / 5

Total

17

/

20

Passed

Description

70%Weight 40%Scale 1-5

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

The description clearly states what the skill does and is well-scoped against sibling skills, but the second sentence is ungrammatical filler that repeats the what instead of providing trigger guidance. Adding a proper "Use when..." clause would fix both the completeness cap and the awkward phrasing.

Suggestions

Replace the garbled second sentence ("Use turning a dbt Core project into...") with a proper trigger clause, e.g., "Use when converting a dbt Core project to an Airflow DAG or TaskGroup, or when orchestrating dbt with Airflow/Cosmos."

Add natural trigger synonyms such as "orchestrate dbt in Airflow", "run dbt models as Airflow tasks", or file/tool extensions users might mention.

Trim the verification-item list from the description; those checks are already stated in the body's "Before starting" note and add tokens without improving triggering.

DimensionReasoningScore

Specificity

"Turns a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos" names a concrete action with specific technologies, and the verification list (dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, manifest availability) adds concrete detail. It stays at 4 rather than 5 because it describes a single core action without covering related capabilities (testing, individual operators), and above 3 because the detail level clearly exceeds a bare 1-2 action listing.

4 / 5

Completeness

The "what" is clear from the first sentence, but there is no valid "when" clause: "Use turning a dbt Core project into an Airflow DAG or TaskGroup with Astronomer Cosmos" is a garbled restatement of the what rather than trigger guidance, and the remaining text is pre-work instructions. Per the rubric guideline, a missing "Use when..." clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural keywords users would say for this task: "dbt Core", "Airflow", "DAG", "TaskGroup", "Astronomer Cosmos", "manifest", "warehouse". A few natural terms and synonyms are missing (e.g., "orchestrate dbt", "convert dbt to Airflow"), keeping it below the comprehensive anchor 5, but coverage is clearly better than the partial anchor 3.

4 / 5

Distinctiveness Conflict Risk

"dbt Core" + "Airflow" + "Astronomer Cosmos" defines a clear niche, and explicitly scoping to dbt Core (vs. dbt Fusion, which has a sibling skill) minimizes conflict risk. This matches the clear-niche anchor with minimal overlap.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
astronomer/agents
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.