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.
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill airflow-dag-patterns60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise but lacks actionability - it reads more like a table of contents than executable guidance. The instructions are abstract directives without concrete code examples, DAG templates, or specific commands. While it appropriately references external resources, the skill body itself provides insufficient value for Claude to act on without consulting the playbook.
Suggestions
Add a concrete, executable DAG example showing a minimal production-ready pattern (e.g., a simple ETL DAG with proper error handling and retries)
Replace abstract instructions like 'Design idempotent tasks' with specific patterns: show actual code for idempotent operators, retry configurations, and dependency definitions
Include specific CLI commands for common operations: testing DAGs locally, triggering backfills, checking task status
Add validation checkpoints to the workflow: 'Run `airflow dags test dag_id execution_date` before deploying' with expected output examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding unnecessary explanations of what Airflow is or how DAGs work. Every section serves a purpose and assumes Claude's competence with the technology. | 3 / 3 |
Actionability | The instructions are vague and abstract ('Identify data sources', 'Design idempotent tasks') with no concrete code examples, executable commands, or copy-paste ready DAG templates. It describes rather than instructs. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence (identify, design, implement, validate) but lack validation checkpoints, specific commands, or feedback loops for error recovery. The workflow is too high-level to guide actual implementation. | 2 / 3 |
Progressive Disclosure | References to external resources are present and one-level deep, but the main content is too sparse - it defers almost everything to the playbook without providing a useful quick-start or concrete examples in the skill itself. | 2 / 3 |
Total | 8 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.