airflow

Queries, manages, and troubleshoots Apache Airflow using the af CLI. Covers listing DAGs, triggering runs, reading task logs, diagnosing failures, debugging DAG import errors, checking connections, variables, pools, and monitoring health. Also routes to sub-skills for writing DAGs, debugging, deploying, and migrating Airflow 2 to 3. Use when user mentions "Airflow", "DAG", "DAG run", "task log", "import error", "parse error", "broken DAG", or asks to "trigger a pipeline", "debug import errors", "check Airflow health", "list connections", "retry a run", or any Airflow operation. Do NOT use for warehouse/SQL analytics on Airflow metadata tables — use analyzing-data instead.

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, well-structured operations reference skill. It excels at actionability with concrete, executable commands throughout, and provides excellent progressive disclosure by routing to specialized sub-skills. The main weakness is length — the User Intent Patterns section and Instance Configuration section are thorough but could be more concise, though the reference-style format partially justifies the verbosity.

Dimension	Reasoning	Score
Conciseness	The skill is quite long (~300+ lines) and includes extensive intent-mapping tables that border on verbose. However, most content is reference material (command tables, workflows) rather than explanatory fluff. The 'User Intent Patterns' section is large but arguably useful for routing. Some tightening is possible (e.g., the instance configuration section is very detailed).	2 / 3
Actionability	Nearly every command is concrete and copy-paste ready with real CLI syntax, flags, and jq filters. Workflows include specific commands with actual arguments and run IDs. The registry discovery section shows executable jq pipelines. Very little is left to guesswork.	3 / 3
Workflow Clarity	Multi-step workflows (failed run investigation, morning health check, validate before deploy, trigger and monitor) are clearly numbered with logical sequencing. The 'Investigate a Failed Run' workflow includes a validation/retry step (clear the run after fixing). The discover command includes an explicit safety checkpoint (--dry-run first, ask for consent).	3 / 3
Progressive Disclosure	The skill serves as a clear hub, with well-signaled references to 10+ sub-skills (authoring-dags, debugging-dags, deploying-airflow, etc.) organized in a summary table. It references api-reference.md for detailed API docs. Content is appropriately split — the main file covers operations and routing while deferring specialized topics to dedicated skills.	3 / 3
	Total	11 / 12 Passed

Description

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 an excellent skill description that hits all the marks. It provides comprehensive specific actions, abundant natural trigger terms, explicit 'Use when' and 'Do NOT use' guidance, and clear boundaries to distinguish it from related skills. The description is thorough without being padded, and uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: listing DAGs, triggering runs, reading task logs, diagnosing failures, debugging DAG import errors, checking connections/variables/pools, monitoring health, and routing to sub-skills for writing/debugging/deploying/migrating.	3 / 3
Completeness	Clearly answers both 'what' (queries, manages, troubleshoots Airflow via af CLI with specific operations listed) and 'when' (explicit 'Use when...' clause with detailed trigger terms). Also includes a 'Do NOT use' boundary condition, which further aids selection accuracy.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'Airflow', 'DAG', 'DAG run', 'task log', 'import error', 'parse error', 'broken DAG', 'trigger a pipeline', 'debug import errors', 'check Airflow health', 'list connections', 'retry a run'. These are highly natural phrases.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Apache Airflow CLI operations). The explicit exclusion clause ('Do NOT use for warehouse/SQL analytics on Airflow metadata tables — use analyzing-data instead') directly addresses potential overlap and reduces conflict risk.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: astronomer/agents
Commit: 789b454

Reviewed: 8 days 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.