authoring-dags

Workflow and best practices for writing Apache Airflow DAGs. Use when creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a follow-up/downstream task. ANY request shaped like 'add a DAG named X', 'write a pipeline', 'add a task that runs after Y', or 'extend the DAG'. For testing and debugging DAGs, see the testing-dags skill.

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.

A well-structured, actionable skill body with a clear sequenced workflow and validation feedback loops. Its main weaknesses are duplicated command listings and a referenced best-practices file that does not exist in the bundle.

Suggestions

Remove the CLI Quick Reference table (or the duplicated Discovery command list in Phase 1) since the same commands appear inline in their phases — keep one canonical location.

Add the missing reference/best-practices.md file (or correct the path to the actual bundle location) so the signaled progressive-disclosure reference resolves to real content.

Consider replacing the large ASCII workflow diagram with a compact bulleted phase list to save tokens while preserving the sequencing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with command tables and no concept-explaining fluff, but the CLI Quick Reference table repeats Discover/Validate commands verbatim from earlier phases and the ASCII workflow diagram is decorative, so it could be tightened.	2 / 3
Actionability	Provides concrete, executable `af` CLI commands (e.g. `af dags errors`, `af dags get <dag_id>`) plus a real install path (`uv tool install astro-airflow-mcp`), copy-paste ready with placeholders.	3 / 3
Workflow Clarity	A clear six-phase sequence with explicit validation feedback loops ("af dags errors" -> fix -> retry) and explicit checkpoints ("Get user approval before implementing", "Only proceed when validation passes").	3 / 3
Progressive Disclosure	The overview correctly points detailed patterns to a one-level-deep reference ("[reference/best-practices.md]"), but that referenced file is not present in any bundle directory (references/, reference/, scripts/, assets/ all absent), so the signaled navigation is broken.	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 with explicit capabilities, natural trigger phrasing, and clear distinctiveness via cross-references to sibling skills. It capably answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "creating a new DAG, write pipeline code, handling questions about DAG patterns and conventions or extending an existing DAG with a follow-up/downstream task" — matching the anchor for naming several specific actions.	3 / 3
Completeness	Explicitly answers both what ("Workflow and best practices for writing Apache Airflow DAGs") and when ("Use when creating a new DAG..."), with an explicit trigger clause present.	3 / 3
Trigger Term Quality	Natural user-shaped phrases are quoted directly: "add a DAG named X", "write a pipeline", "add a task that runs after Y", "extend the DAG", giving good coverage of how a user would actually ask.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear authoring niche and actively reduces conflict by redirecting testing/debugging to the separate testing-dags skill, making wrong-skill triggering 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link 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.