CtrlK
BlogDocsLog inGet started
Tessl Logo

airflow-dag-patterns

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A well-structured, token-efficient patterns skill with executable Quick Start code and a correctly signaled one-level-deep reference. Its only gap is the absence of an explicit validate-then-proceed workflow for batch DAG operations.

Suggestions

Add a short 'Verify your DAG' checkpoint sequence, e.g. `python -c 'from airflow.models import DagBag; DagBag("dags/")'` or `airflow dags test`, before treating a DAG as production-ready, so batch operations get an explicit validation step.

Turn the 'Test DAGs' bullet into a concrete workflow step (parse-check → unit test → `airflow dags test`) with a retry/fix loop to lift workflow_clarity above 2.

Note when to consult `references/details.md` for a specific need (e.g. custom sensors, XCom handling) so the navigation tier is signaled per-situation rather than only as a fallback.

DimensionReasoningScore

Conciseness

Lean body of tables, executable code, and terse bullet directives that assume Claude's competence; it never explains what Airflow or a DAG is, so every token earns its place.

3 / 3

Actionability

The Quick Start is fully executable Python (real imports, a complete DAG, EmptyOperator/PythonOperator) and the Best Practices give concrete directives like "Use `mode='reschedule'`" and "Don't use `depends_on_past=True`", making it copy-paste ready.

3 / 3

Workflow Clarity

Sections are logically organized (When to Use → Core Concepts → Quick Start → Best Practices) but there is no explicit validation/verification checkpoint sequence for what are inherently batch operations, which the guideline caps at 2.

2 / 3

Progressive Disclosure

A clear overview points to a single one-level-deep reference — 'Detailed pattern documentation lives in `references/details.md`' — and that file exists, so content is appropriately split with easy navigation.

3 / 3

Total

11

/

12

Passed

Description

100%

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 tight, third-person description that pairs a concrete capability statement with an explicit 'Use when...' trigger clause. It scores top marks across all four dimensions with no padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and domains — 'operators, sensors, testing, and deployment' — beyond a single vague capability, matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what ('Build production Apache Airflow DAGs with best practices...') and when ('Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.'), matching the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Includes natural phrasing a user would actually say — 'data pipelines', 'orchestrating workflows', 'scheduling batch jobs', 'Airflow DAGs' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

'Apache Airflow DAGs' is a clear niche with distinct triggers unlikely to conflict with unrelated skills; it would not fire for general document or code tasks.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wshobson/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.