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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/data-engineering/skills/airflow-dag-patterns/SKILL.md

Quality

Content

68%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 well-structured, mostly actionable patterns skill that keeps the overview lean and defers worked examples to a real one-level-deep reference. The main gap is workflow clarity: it lacks explicit sequenced steps and validation checkpoints for building and verifying DAGs.

Suggestions

Add an explicit numbered build/verify workflow in the Quick Start (e.g., 1. write DAG, 2. load with DagBag, 3. run `pytest tests/test_dags.py`, 4. only then deploy) with a validation checkpoint, which would raise workflow_clarity.

Link the details.md reference as a markdown link (references/details.md) and optionally split the large details.md into per-topic files (operators, sensors, testing) so each pattern class has its own clearly signaled entry point.

Replace the stub `# Extract logic here` with a minimal but real callable so the Quick Start example is fully copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with code-forward sections and little over-explanation of concepts Claude already knows, but the opening line restates the frontmatter description and a few code comments are slightly redundant, keeping it just below the lean 5.	4 / 5
Actionability	The Quick Start provides a concrete, mostly copy-paste-ready DAG and the Best Practices give specific directives (mode='reschedule', {{ ds }}), but the example callable is a stub ("# Extract logic here") and the deeper patterns are deferred to details.md, leaving minor gaps versus fully executable 5.	4 / 5
Workflow Clarity	The Quick Start implies a build-a-DAG sequence but presents it as a single code block rather than explicit numbered steps, and there are no validation or verification checkpoints (e.g., how to confirm the DAG loads or passes integrity checks), matching the anchor with sequence present but checkpoints missing.	3 / 5
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level-deep reference to references/details.md (a real file), and content is appropriately split; the reference is given as a plain path rather than a navigable link, a minor organization gap that keeps it below 5.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong, concise description that answers both what and when with concrete triggers and third-person voice. The main weakness is that the trigger clause uses generic pipeline/orchestration language rather than naming Airflow/DAGs, slightly raising overlap risk and missing the most natural user terms.

Suggestions

Add Airflow-specific trigger terms to the 'Use when' clause (e.g., 'Use when creating Airflow DAGs, data pipelines, or scheduling batch jobs') so the skill triggers on the words users actually say.

Consider naming one or two more concrete actions (e.g., 'designing DAG dependencies, writing custom operators and sensors, testing DAG runs') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment" names the domain plus several concrete capability areas (operators, sensors, testing, deployment), which is several specific actions with minor gaps rather than the comprehensive multi-action list of a 5.	4 / 5
Completeness	It clearly states what ("Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment") and when ("Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs" provides good natural keyword coverage, but the trigger clause omits tool-specific terms a user might actually say like "Airflow" or "DAG", leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The what-clause names Apache Airflow explicitly giving it a clear niche, but the tool-agnostic trigger terms ("data pipelines, orchestrating workflows, scheduling batch jobs") could overlap with closely related orchestration skills (Prefect, Dagster), so it is mostly distinct with minor overlap risk rather than minimal.	4 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/data-engineering/skills/airflow-dag-patterns/SKILL.md
Commit: d6837ae

Reviewed: about 12 hours 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.