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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced command reference that avoids explaining concepts Claude already knows, but it is longer than an entrypoint skill needs to be due to overlapping command listings, and its one external reference is broken.

Suggestions

Consolidate the overlapping command listings: the Quick Reference table, User Intent Patterns, and Common Workflows repeat many of the same `af` commands - fold User Intent Patterns into the Quick Reference or trim duplicates to cut tokens.

Fix or remove the broken reference at "See [api-reference.md](api-reference.md) for all options, common endpoints (XCom, event-logs, backfills), and examples" - the file is absent from the bundle; either add it or inline the needed API details.

Move the large Quick Reference and `af api` command tables into a bundle file (e.g. references/commands.md) and keep SKILL.md as a leaner overview that links to it, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is free of basic-concept padding (it never explains what Airflow or a DAG is), but the Quick Reference table, User Intent Patterns, and Common Workflows sections re-list many of the same `af` commands three times over, so not every token earns its place.	2 / 3
Actionability	Dense with concrete, copy-paste-ready commands and worked examples (e.g. `af runs diagnose my_dag manual__2024-01-15T10:00:00+00:00` followed by `af tasks logs ...`), with jq pipelines and flag syntax spelled out - fully executable guidance.	3 / 3
Workflow Clarity	Multi-step workflows like "Investigate a Failed Run" are numbered with per-step comments, and the sensitive `instance discover` operation carries an explicit checkpoint: "Always run with --dry-run first and ask for user consent before running discover without it."	3 / 3
Progressive Disclosure	Sections are well-organized and sibling-skill routing is clearly signaled, but the only bundle-file reference - "See [api-reference.md](api-reference.md) for all options" - points at a file that does not exist, and large command/API tables sit inline rather than in a referenced file.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, gives explicit "Use when" triggers with natural user phrases, and actively disambiguates from sibling skills. It does not over-claim or pad with fluff.

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" - well beyond a vague domain label.	3 / 3
Completeness	Clearly answers "what" ("Queries, manages, and troubleshoots Apache Airflow using the `af` CLI") and "when" with an explicit "Use when working with anything related to Airflow - a DAG, a DAG run, a task log..." clause, satisfying both halves.	3 / 3
Trigger Term Quality	Embeds natural user phrases like "trigger a pipeline", "retry a run", "list connections", "check Airflow health", and "why did my DAG fail" alongside concrete nouns (DAG, DAG run, task log), giving strong coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	Explicit disambiguation - "This is the entrypoint that routes to sibling skills" and "Not for warehouse/SQL analytics on Airflow metadata tables (use analyzing-data); for deep root-cause reports use debugging-dags or airflow-investigation" - carves a clear niche unlikely to trigger the wrong skill.	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
Path: skills/airflow/SKILL.md
Commit: dbd9bb7

Reviewed: 10 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.