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

66%

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 ./skills/airflow-dag-patterns/SKILL.md

Quality

Content

50%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.

The body is concise and well-sectioned but offers only vague instructional guidance with no executable code or concrete patterns, and its single detailed reference points to a file that is not present in the bundle.

Suggestions

Add concrete, executable examples in the Instructions (e.g. a minimal DAG skeleton with operator names, retries, and sensors) instead of deferring all detail to the playbook.

Provide the missing resources/implementation-playbook.md (or correct the path) so the inline reference resolves to a real bundle file.

Turn the workflow into an explicit validate-fix-retry loop with checkpoints, e.g. validate DAG with `airflow dags test` in staging before promoting, and re-run on failure.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows (no 'what Airflow is' padding) and assumes competence, fitting the 'efficient; minor instances that could be trimmed' anchor. Not a 5 because the Use/Do-not-use/Limitations sections somewhat restate the description's scope.	4 / 5
Actionability	The numbered instructions ('Identify data sources...', 'Design idempotent tasks...') are high-level hints with no concrete code, commands, operator names, or templates, matching 'minimal concrete guidance; missing the specific steps to execute'. Not a 3 because nothing executable is provided and the concrete material is deferred to a missing playbook.	2 / 5
Workflow Clarity	A rough four-step sequence exists with one validation mention ('Validate in staging'), but checkpoints are implicit and there is no validate-fix-retry feedback loop; given this is a batch/destructive-operations skill, the missing-feedback-loops cap at 3 applies and prevents a 4.	3 / 5
Progressive Disclosure	Section structure is clean and a one-level reference is intended ('Refer to resources/implementation-playbook.md'), but no resources/ directory or file exists, so the primary detailed reference is broken and unresolvable, matching 'references present but not clearly signaled/organized' rather than a 4.	3 / 5
	Total	12 / 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, well-structured description that clearly states both capabilities and trigger conditions in third person. Minor weaknesses are generic trigger phrasing that could overlap with other orchestration tools and slightly incomplete synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('production Apache Airflow DAGs') and several concrete capability areas ('operators, sensors, testing, and deployment'), matching the 'several specific actions; minor gaps' anchor. Not a 5 because coverage is not exhaustive of DAG-building actions.	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, matching the top anchor.	5 / 5
Trigger Term Quality	'Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs' gives good natural phrases a user would say. Not a 5 because synonyms and Airflow-specific natural terms (e.g. 'DAGs', 'backfill') are partly missing.	4 / 5
Distinctiveness Conflict Risk	The 'what' pins a clear niche (Apache Airflow DAGs), but the 'when' triggers ('orchestrating workflows', 'scheduling batch jobs') are generic enough to overlap with rival orchestrators (Prefect, Dagster), so it is 'mostly distinct; minor overlap risk' rather than a clean 5.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/airflow-dag-patterns/SKILL.md
Commit: 1f67c44

Reviewed: about 16 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.