airflow-dag-structure-to-orchestra

Use this skill when converting any Airflow DAG to Orchestra YAML to handle DAG-level configuration. Triggers: any Airflow DAG definition containing schedule_interval, default_args, max_active_runs, catchup, params, start_date, or DAG-level tags. Must be applied before converting individual tasks — it establishes the pipeline root fields that wrap all task conversions.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

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

A thorough, highly actionable conversion reference with concrete mappings, real API validation evidence, and a clear ordered checklist. Its main weaknesses are a somewhat duplicative Gotchas section and the absence of an explicit output-validation step in the conversion workflow.

Suggestions

Add an explicit final checklist step such as 'Validate the generated Orchestra YAML against the /pipelines/schema endpoint; fix and re-validate on any error' to close the validate→fix→retry loop.

De-duplicate the Gotchas section against the mapping tables — either shorten each gotcha to a one-line pointer back to its section, or consolidate so each pitfall appears once.

Turn the named sibling-skill pointers into actual file links (e.g. [airflow-alerts-to-orchestra](../airflow-alerts-to-orchestra/SKILL.md)) so navigation between conversion skills is explicit.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with no padding of general concepts Claude already knows; the only over-explanation is purposeful repetition of a few key pitfalls (6-field cron, retry_delay cap, TaskGroup non-nesting, tags-on-stage) between the mapping sections and the Gotchas section, which could be trimmed.	4 / 5
Actionability	Provides concrete Airflow→Orchestra field-mapping tables, complete YAML snippets, a full before/after example, and exact API error strings (e.g. 'Incorrect number of values ... 6 required, 5 provided'), yielding copy-paste-ready guidance across the common DAG-config cases.	5 / 5
Workflow Clarity	An ordered 'Conversion Checklist' sequences the work and the skill repeatedly anchors rules to live schema validation and manual-review flagging, but there is no explicit 'validate the generated YAML against the Orchestra schema' checkpoint or validate→fix→retry loop in the workflow itself.	4 / 5
Progressive Disclosure	The file is well-organized with clear section headers and an overview up top, and inlining the mapping tables is appropriate for a converter skill that loads the whole body; however everything lives in one ~300-line file and cross-skill pointers (slack-airflow-to-orchestra, airflow-alerts-to-orchestra) are named but not linked as navigable references.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

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, well-scoped description that explicitly states what it does, when to trigger it, and how it relates to adjacent conversion skills. The only mild gap is that the stated actions are phrased at a configuration-level altitude rather than listing concrete per-field conversions.

Dimension	Reasoning	Score
Specificity	Names the domain ('converting any Airflow DAG to Orchestra YAML') and several concrete actions ('handle DAG-level configuration', 'establishes the pipeline root fields that wrap all task conversions') with an explicit field list, but the actions themselves stay somewhat abstract rather than enumerating each mapping.	4 / 5
Completeness	Clearly answers 'what' (convert Airflow DAG to Orchestra YAML, handle DAG-level configuration) and 'when' (an explicit Triggers clause plus 'Must be applied before converting individual tasks'), satisfying the top anchor for both what and when.	5 / 5
Trigger Term Quality	Explicit 'Triggers:' list names the actual Airflow fields a user would have in their DAG (schedule_interval, default_args, max_active_runs, catchup, params, start_date, DAG-level tags), giving strong keyword coverage, but it lacks synonyms or natural-language phrasings users might say.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (DAG-level/root fields only) and explicitly scopes itself against sibling task-level skills ('before converting individual tasks'), minimizing the chance of firing for the wrong skill.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: orchestra-hq/orchestra-skills
Path: skills/migrate-to-orchestra/skills/airflow-dag-structure-to-orchestra/SKILL.md
Commit: 3a29fe4

Reviewed: 3 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.