airflow

Queries, manages, and troubleshoots Apache Airflow using the `af` CLI. Use when working with anything related to Airflow - a DAG, a DAG run, a task log, an import or parse error, a broken DAG, or any Airflow operation. Covers listing and triggering DAGs, retrying runs, reading task logs, diagnosing failures, debugging import and parse errors, checking connections, variables and pools, exploring the REST API, and monitoring health (for example "trigger a pipeline", "retry a run", "list connections", "check Airflow health", "why did my DAG fail"). This is the entrypoint that routes to sibling skills for authoring, testing, deploying, and migrating Airflow 2 to 3. Not for warehouse/SQL analytics on Airflow metadata tables (use analyzing-data); for deep root-cause reports use debugging-dags or airflow-investigation.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is a highly actionable CLI reference with well-sequenced workflows and explicit validation for sensitive operations, but it carries redundancy across its command-listing sections and signals an api-reference.md file that is not present in the bundle.

Suggestions

Add the missing api-reference.md bundle file (referenced on line 377) or remove the reference, so the signaled progressive-disclosure pointer resolves.

Consolidate the overlapping command listings in Quick Reference, User Intent Patterns, and Common Workflows to reduce redundancy and token cost.

Move the long Direct API Access / instance configuration detail into a separate reference file, keeping SKILL.md as a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept explanations Claude already knows, but the Quick Reference table, User Intent Patterns, and Common Workflows sections repeat overlapping command listings, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready `af`/`astro` commands with concrete jq filters and flag examples throughout, e.g. 'af runs list \| jq ".dag_runs[] \| select(.state == \"failed\")"'.	3 / 3
Workflow Clarity	Multi-step workflows are numbered (e.g. 'Investigate a Failed Run' steps 1-4 ending in clear-and-retry) and the sensitive `instance discover` operation has an explicit validation checkpoint ('Always run with --dry-run first and ask for user consent').	3 / 3
Progressive Disclosure	Section organization is clear and one reference is signaled ('See api-reference.md'), but no bundle files exist so that referenced file is missing, and a large amount of API/command reference material remains inline rather than split out.	2 / 3
	Total	10 / 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.

A strong, third-person description that states concrete capabilities, provides natural trigger phrases, and explicitly scopes when to use it versus sibling skills. It answers what, when, and how it differs from neighbors without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'listing and triggering DAGs, retrying runs, reading task logs, diagnosing failures, debugging import and parse errors, checking connections, variables and pools, exploring the REST API, and monitoring health' — matching the top anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('Queries, manages, and troubleshoots Apache Airflow using the `af` CLI') and 'when' ('Use when working with anything related to Airflow...'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes natural phrasing a user would say — 'trigger a pipeline', 'retry a run', 'list connections', 'check Airflow health', 'why did my DAG fail' — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Airflow ops via `af` CLI) with explicit disambiguation — 'Not for warehouse/SQL analytics... use analyzing-data; for deep root-cause reports use debugging-dags or airflow-investigation' — making conflicts unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: astronomer/agents
Commit: 8827e93

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.