airflow-conditions-to-orchestra

Use this skill when an Airflow DAG contains conditional execution logic: trigger_rule (all_done, one_failed, none_failed, one_success, none_skipped), BranchPythonOperator, ShortCircuitOperator, or LatestOnlyOperator. Triggers: any Airflow task with a non-default trigger_rule; any DAG using branching or short-circuit patterns; any task that should only run based on upstream status rather than simple success.

Quality

86%

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 high-quality migration reference with executable code for every pattern and sharp gotchas. It is slightly let down by a duplicated quick-reference card, the absence of a pick-the-right-pattern decision flow, and no use of separate reference files for the longer reference material.

Suggestions

Add a short 'which pattern do I have?' decision flow near the top so a reader can map an Airflow construct to the right section without scanning all sections.

Move the Condition Expression Reference (variable types, built-in functions) and the full Branch/ShortCircuit pattern examples into files under references/, keeping SKILL.md an overview with one-level-deep links.

Remove or merge the Trigger Rule Quick-Reference Card into the trigger_rule mapping table to eliminate the duplicated condition expressions.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient with mapping tables and code, but the Trigger Rule Quick-Reference Card duplicates the trigger_rule mapping table and a few prose glosses could be trimmed, keeping it just below a 5.	4 / 5
Actionability	It provides fully executable, copy-paste-ready YAML and Python for each pattern (input-driven branch, output-driven branch, short-circuit, trigger rules) including complete OrchestraSDK usage and the critical `set_outputs: true` requirement, covering the common cases.	5 / 5
Workflow Clarity	Each Airflow construct maps to a clear Orchestra pattern with full before/after code, but it is a multi-pattern reference catalog rather than a single sequenced workflow, so it lacks an explicit decision flow for picking the right pattern.	4 / 5
Progressive Disclosure	Section structure is clear with well-signaled one-level external URL references, but no bundle files exist and all ~270 lines are inline — the Condition Expression Reference and full pattern examples could reasonably live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

91%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, trigger-rich description that names the exact Airflow constructs and natural keywords a user would mention, with explicit when-guidance. Its only gap is that the transformation action (convert to Orchestra condition expressions) is implied rather than stated.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete constructs — "trigger_rule (all_done, one_failed, none_failed, one_success, none_skipped), BranchPythonOperator, ShortCircuitOperator, or LatestOnlyOperator" — giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	It has exemplary explicit "Use this skill when..." / "Triggers:..." guidance (strong "when"), but the "what" — that the skill converts these constructs to Orchestra condition expressions — is only implied by the skill name and never stated in the description text, so it is not a full 5.	4 / 5
Trigger Term Quality	It uses the exact natural terms an Airflow user would say — "Airflow DAG", "trigger_rule", "BranchPythonOperator", "branching or short-circuit patterns", "upstream status" — covering the relevant operators and rule names comprehensively.	5 / 5
Distinctiveness Conflict Risk	The niche is narrow and trigger-specific (Airflow conditional-execution operators and non-default trigger_rules), so it is clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: orchestra-hq/orchestra-skills
Path: skills/migrate-to-orchestra/skills/airflow-conditions-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.