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, and migrating.

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 strengthens completeness.

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 users would actually use.

Highly distinctive with a clear niche around 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.

The skill is fairly comprehensive but includes some sections that could be tightened. The 'User Intent Patterns' section is quite long and somewhat redundant with the quick reference table. The instance configuration section is thorough but verbose. However, most content earns its place given the breadth of the CLI tool.

Excellent actionability throughout — every command is concrete and copy-paste ready with real CLI syntax. The workflows section provides fully executable step-by-step sequences, and jq filtering examples show exact usage patterns. Registry discovery examples include complete jq pipelines.

Multi-step workflows are clearly sequenced with numbered steps and logical progression (e.g., 'Investigate a Failed Run' goes from listing runs → diagnosing → reading logs → clearing to retry). The 'Validate DAGs Before Deploying' workflow provides validation checkpoints. The instance discover workflow includes an explicit safety checkpoint (--dry-run first, ask for consent).

Excellent progressive disclosure with a clear overview structure, quick reference table for scanning, and well-signaled one-level-deep references to sub-skills (authoring-dags, debugging-dags, deploying-airflow, etc.) and supplementary files (api-reference.md). The Related Skills table at the end provides clean navigation with 'Use when...' context.