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.

0.95x

Quality

80%

Does it follow best practices?

Impact

90%

0.95x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/data-engineering/skills/airflow-dag-patterns/SKILL.md

The canonical home for this skill is airflow-dag-patterns in wshobson/agents

Quality

Content

72%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.

Highly actionable code examples, but the single-file structure inlines material that belongs in referenced files and the batch workflows lack explicit inline validation checkpoints.

Suggestions

Add explicit validation/feedback-loop checkpoints within the pipeline workflow steps (e.g., validate DAG integrity before deployment, re-run tests on failure) to lift workflow_clarity above 3.

Split large pattern groups (operators, sensors, testing, deployment) into one-level-deep referenced files and link them from SKILL.md to improve progressive_disclosure.

Trim redundant or repetitive code blocks and the intro line that restates the description to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first content with light comments and little over-explanation of known concepts, though six full repeated code blocks and a redundant intro line could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code across six patterns (TaskFlow, dynamic DAGs, branching, sensors, error handling, testing) covering the common cases.	5 / 5
Workflow Clarity	Batch/pipeline operations lack inline validation checkpoints and feedback loops within the workflow steps; the standalone testing section does not substitute for per-step validation, capping the score at 3.	3 / 5
Progressive Disclosure	All content is inlined in one ~520-line file with no bundle files or references; section structure exists but clearly separable material (operators, sensors, testing, deployment) is not split out.	3 / 5
	Total	15 / 20 Passed

Description

87%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 description that clearly states capability and use triggers with concrete, natural language. Minor specificity gains could come from naming concrete operator/sensor actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete domains ('operators, sensors, testing, and deployment') tied to the action of building production DAGs, with minor gaps in enumerating specific actions per domain.	4 / 5
Completeness	Explicitly answers both 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.	5 / 5
Trigger Term Quality	Natural trigger phrases 'creating data pipelines, orchestrating workflows, scheduling batch jobs' align with how users would phrase the need, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Narrows to a clear niche (Apache Airflow DAGs) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 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	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/data-engineering/skills/airflow-dag-patterns/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.