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.
78
71%
Does it follow best practices?
Impact
90%
0.95xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/data-engineering/skills/airflow-dag-patterns/SKILL.mdQuality
Discovery
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.
This is a strong skill description that concisely covers specific capabilities (DAGs, operators, sensors, testing, deployment), includes an explicit 'Use when' clause with natural trigger terms (data pipelines, orchestrating workflows, batch jobs), and is clearly distinguishable from other skills through the explicit mention of Apache Airflow. It uses proper third-person voice and avoids vague language or unnecessary verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building DAGs, working with operators, sensors, testing, and deployment. These are concrete, domain-specific capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment) and 'when' (explicit 'Use when' clause covering data pipelines, orchestrating workflows, or scheduling batch jobs). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Airflow', 'DAGs', 'data pipelines', 'orchestrating workflows', 'scheduling batch jobs', 'operators', 'sensors'. These cover the primary terms a user working with Airflow would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Apache Airflow' and 'DAGs', which clearly carve out a niche. Unlikely to conflict with general data engineering or other workflow tools since the technology is explicitly named. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable Airflow patterns but suffers significantly from verbosity and poor progressive disclosure. It reads more like a comprehensive tutorial or cookbook than a concise skill file, with ~400 lines of inline code that should be split into referenced files. The content quality is good but the structure and token efficiency are poor for a SKILL.md context.
Suggestions
Extract the six pattern examples into separate referenced files (e.g., patterns/taskflow.md, patterns/dynamic_dags.md) and keep only the Quick Start example and a brief pattern index in SKILL.md.
Remove the Core Concepts table and task dependency syntax section - Claude already knows these Airflow fundamentals.
Add an explicit workflow section: 'Creating a new DAG' with steps like 1) Choose pattern, 2) Create file in dags/, 3) Run `pytest tests/test_dags.py` to validate, 4) Deploy with specific validation checkpoints.
Trim the 'When to Use This Skill' section - it largely restates the skill's purpose and adds little actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with many patterns that are largely boilerplate code Claude already knows how to write. The 'Core Concepts' table explains basic principles (idempotent, atomic) that Claude understands, and the task dependency syntax is standard Airflow documentation. Six full patterns with complete code examples is excessive for a SKILL.md. | 1 / 3 |
Actionability | All code examples are fully executable, copy-paste ready Python with proper imports, realistic configurations, and complete DAG definitions. The testing pattern includes runnable pytest code, and the project structure is concrete and specific. | 3 / 3 |
Workflow Clarity | While individual patterns are well-structured, there's no clear workflow for creating a new DAG from scratch with validation checkpoints. The skill presents patterns but doesn't guide through a sequenced process of building, testing, and deploying a DAG. The testing section exists but isn't integrated into a workflow with explicit validation steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with six full code patterns inline that should be split into separate reference files. The SKILL.md should be a concise overview pointing to pattern files (e.g., TASKFLOW.md, DYNAMIC_DAGS.md, SENSORS.md) rather than embedding hundreds of lines of code examples directly. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (526 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.