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.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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, rich natural trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clear boundaries to distinguish it from related skills. It serves as a strong example of a well-crafted skill description.
| 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. | 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 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. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 skill that serves as an effective operations hub for Airflow CLI usage. Its greatest strengths are the fully executable command examples, clear workflow sequences with validation steps, and excellent progressive disclosure to sub-skills. The main weakness is some verbosity in the User Intent Patterns section and the Instance Configuration section, which could be trimmed or moved to separate reference files to improve token efficiency.
Suggestions
Consider moving the extensive 'User Intent Patterns' section to a separate reference file or condensing it significantly — the quick reference table already maps commands to descriptions, and Claude can infer intent-to-command mappings.
The 'Instance Configuration' section is quite detailed (config layering, scopes, migration); consider extracting it to a dedicated reference file and keeping only the most common patterns (env vars + basic add/use) inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive and most content earns its place, but the extensive 'User Intent Patterns' section is verbose — it maps natural language phrases to commands that could be inferred from the quick reference table. The instance configuration section is also quite detailed with config layering nuances that could be in a separate file. | 2 / 3 |
Actionability | Excellent actionability throughout — every command is concrete and copy-paste ready with real arguments, specific flags, and jq filtering examples. Workflows include exact command sequences with realistic run IDs and dag IDs. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly numbered and sequenced (e.g., 'Investigate a Failed Run' has a logical 4-step flow from listing to diagnosing to reading logs to clearing). The 'Validate DAGs Before Deploying' workflow provides a validation checkpoint before deployment. The 'discover --dry-run' pattern includes an explicit safety gate requiring user consent. | 3 / 3 |
Progressive Disclosure | The skill serves as a well-organized hub, with a quick reference table for immediate use and clear one-level-deep references to 10+ related skills and an api-reference.md file. Content is appropriately split — DAG authoring, debugging, deploying, and migration each route to dedicated sub-skills with clear 'use when' guidance. | 3 / 3 |
Total | 11 / 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.
- Repository
- astronomer/agents
- Commit
535a040
- 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.