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.
83
78%
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 clearly identifies the tool (Apache Airflow), lists specific capabilities (DAGs, operators, sensors, testing, deployment), and provides explicit trigger guidance via a 'Use when' clause. The trigger terms are natural and cover the main use cases users would describe. Minor improvement could include mentioning file types or additional synonyms, but overall this is well-crafted.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: building DAGs, using operators, sensors, testing, and deployment. Also mentions best practices, which adds practical context. | 3 / 3 |
Completeness | Clearly answers both 'what' (build production Airflow DAGs with best practices for operators, sensors, testing, deployment) and 'when' (explicit 'Use when' clause covering data pipelines, orchestrating workflows, scheduling batch jobs). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Airflow', 'DAGs', 'data pipelines', 'orchestrating workflows', 'scheduling batch jobs', 'operators', 'sensors'. These cover common variations of how users would describe Airflow-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific mention of 'Apache Airflow' and 'DAGs', which are unique to this orchestration tool. Unlikely to conflict with general coding or other pipeline skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent, actionable code examples covering a wide range of Airflow patterns, which is its primary strength. However, it suffers from being overly long and monolithic—all six patterns plus testing, project structure, and best practices are inlined without progressive disclosure. The content also lacks a clear development/deployment workflow with validation checkpoints, presenting patterns in isolation rather than as part of a guided process.
Suggestions
Split detailed patterns (dynamic DAGs, branching, sensors, error handling) into separate referenced files (e.g., PATTERNS.md or individual files), keeping only Quick Start and TaskFlow in the main SKILL.md
Add an explicit deployment workflow with validation steps: e.g., '1. Write DAG → 2. Run `python dags/my_dag.py` to check syntax → 3. Run pytest → 4. Deploy to staging → 5. Verify in Airflow UI'
Remove explanatory comments in code that Claude can infer (e.g., '# Linear', '# Fan-out', '# Extract logic here') and trim the Do's/Don'ts to only non-obvious guidance
Consolidate the Core Concepts section—task dependency syntax is basic Airflow knowledge and could be reduced to a single-line reference
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400 lines) with 6 full patterns, many of which are variations on similar themes. The DAG design principles table and 'Core Concepts' section add some value but the task dependency examples are basic knowledge. The Do's/Don'ts section includes some obvious advice. Could be significantly tightened by consolidating patterns and removing explanatory comments. | 2 / 3 |
Actionability | Every pattern includes fully executable, copy-paste ready Python code with proper imports, realistic configurations, and complete DAG definitions. The testing section includes runnable pytest examples, and the project structure gives a concrete layout to follow. | 3 / 3 |
Workflow Clarity | The patterns are presented as independent examples rather than a sequenced workflow. There are no explicit validation checkpoints for DAG development (e.g., 'run this test before deploying', 'validate DAG loads before pushing'). The testing pattern exists but isn't integrated into a deployment workflow with feedback loops. | 2 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single file with no references to separate detailed files. Six full code patterns, a project structure, best practices, and testing are all crammed into one document. The Resources section links to external docs but there's no splitting of content into referenced sub-files for advanced topics. | 1 / 3 |
Total | 8 / 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
47823e3
- 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.