authoring-language-sdk-tasks

The language-neutral foundation for Airflow language SDKs — implement task logic in a non-Python language while the DAG stays in Python. Use when the user wants to run an Airflow task in another language (Java, Kotlin, Go, or other JVM/native languages), asks how the Python `@task.stub` pairs with native task code, how task/DAG IDs must match across the two sides, how data passes via XCom as JSON, or which language SDKs exist. This skill owns the shared Python-stub pattern and conceptual model; for a specific language's native API, build, and runtime, use that language's skill (e.g. authoring-java-sdk-tasks, authoring-go-sdk-tasks).

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

78%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 well-structured conceptual foundation skill with an executable Python example, concrete contract guidance, and excellent progressive disclosure to per-language companion skills. Main weakness is minor redundancy between the rules and pitfalls lists.

Suggestions

Consolidate the overlapping items between 'Rules that apply regardless of language' and 'Language-agnostic pitfalls' (ID matching, queue/retries on stub, upstream reference) into a single list to remove redundancy.

Add one short native-side snippet or a concrete pointer to where the matching native IDs appear in a companion skill, so the two-sided contract is shown end-to-end rather than only on the Python side.

Dimension	Reasoning	Score
Conciseness	Lean and assumes competence (no basic Airflow/DAG explanations), but the 'Rules that apply regardless of language' list and the 'Language-agnostic pitfalls' list overlap on IDs-matching, queue/retries-on-stub, and upstream-reference points — minor redundancy that could be tightened.	4 / 5
Actionability	Provides a complete, copy-paste-ready Python stub DAG example and a concrete XCom type table; the native-side code is absent but its absence is explicitly justified as living in per-language companion skills, leaving only minor gaps.	4 / 5
Workflow Clarity	The two-sided model is clearly sequenced (Python stub then native implementation) and the pitfalls list functions as a verification checklist for the cross-side contract; no explicit validate-fix-retry loop is present, but no destructive/batch operation requires one here.	4 / 5
Progressive Disclosure	A clear overview that deliberately stops at shared concepts and routes native API, type mapping, build, and runtime details to well-signaled one-level-deep companion skills via dedicated 'Per-language skills' and 'Related Skills' sections; content is appropriately split with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

95%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, third-person description with explicit 'what' and 'when' coverage, comprehensive natural trigger terms, and clear boundary guidance against sibling per-language skills. Specificity is slightly conceptual but still concrete.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('implement task logic in a non-Python language', '@task.stub pairs with native task code', 'task/DAG IDs must match', 'data passes via XCom as JSON'), but the actions lean conceptual rather than distinct operations, leaving minor gaps versus a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both what ('language-neutral foundation... implement task logic in a non-Python language while the DAG stays in Python', 'owns the shared Python-stub pattern and conceptual model') and when (a concrete 'Use when...' clause with multiple trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms and language names — 'run an Airflow task in another language (Java, Kotlin, Go...)', '@task.stub', 'task/DAG IDs must match', 'XCom as JSON', 'language SDKs' — that a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (shared language-neutral foundation) with an explicit boundary clause routing per-language native API/build/runtime to companion skills, minimizing conflict risk with the sibling skills it names.	5 / 5
	Total	19 / 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: astronomer/agents
Path: skills/authoring-language-sdk-tasks/SKILL.md
Commit: dbd9bb7

Reviewed: ~23 hours 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.