CtrlK
BlogDocsLog inGet started
Tessl Logo

authoring-java-sdk-tasks

Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about `@Builder.Dag`/`@Builder.Task`/`@Builder.XCom`, the `Task`/`BundleBuilder` interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type mapping, or logging from Java tasks. This skill covers the Java-specific native API; the shared Python-stub pattern and conceptual model live in authoring-language-sdk-tasks. For building/shipping the bundle see deploying-java-sdk-bundles; for coordinator config see configuring-airflow-language-sdks.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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-crafted reference skill: fully executable code for both authoring APIs, precise signature/type tables, and disciplined cross-skill delegation. The main improvement opportunities are trimming the repeated ID-matching reminders and pushing deployment-owned details (logging artifacts) fully to the deploy skill.

DimensionReasoningScore

Conciseness

The body is efficient — compact tables, illustrative code with inline comments, no padding — but the ID-matching rule is repeated in the recap, code comments, annotation table, and pitfalls, and the logging section restates details owned by deploying-java-sdk-bundles. These are minor instances that could be trimmed, matching the anchor-4 example rather than the fully lean anchor 5.

4 / 5

Actionability

Every code block is complete and executable (Python stub, annotation class, Task/BundleBuilder implementations, main entry point, logger declaration), and the Client and XCom type-mapping tables give exact signatures, return types, and failure behavior. Copy-paste ready and covering both APIs plus common cases like Object casts and retry-aware tryNumber logic.

5 / 5

Workflow Clarity

The sections form a coherent authoring sequence (Python stub recap → Java task APIs → bundle entry point → client/XCom/log details → pitfalls) and no destructive or batch operations are involved, so no validation cap applies. However, there is no compile/run verification checkpoint within this skill — verification is deferred to deploying-java-sdk-bundles and the SDK's worked example — leaving a minor checkpoint gap at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist, so all guidance lives in SKILL.md; it stays appropriately compact (tables rather than an inlined API-reference dump) and consistently defers shared concepts, build/deploy details, and coordinator config to well-signaled, bolded sibling skills plus a Related Skills section. Minor gap: deployment-owned detail such as the logging artifact list (airflow-sdk-jpl/slf4j/log4j2/jul) is inlined here rather than left to the deploy skill.

4 / 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 description: concrete domain and capability list, explicit and natural trigger phrasing including JVM-language synonyms, and explicit boundary lines against three sibling skills. The only minor gap is that the two Java authoring APIs (annotation vs interface) are only implied via the interface names rather than stated as distinct actions.

DimensionReasoningScore

Specificity

"Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK" names the domain and lists several concrete capability areas ("reading connections/variables/XComs from Java, the JSON-to-Java type mapping, or logging"), with minor coverage gaps such as the annotation-vs-interface API split not being named as a distinct action.

4 / 5

Completeness

It explicitly answers what ("Writes Airflow task logic... using the Airflow Java SDK") and when ("Use when the user wants to implement Airflow tasks in Java/JVM, asks about...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Java, Kotlin, or any JVM language" covers synonyms, and the triggers "implement Airflow tasks in Java/JVM", "asks about @Builder.Dag/@Builder.Task/@Builder.XCom", "connections/variables/XComs", "type mapping", and "logging" are all phrases a user would naturally say, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

"This skill covers the Java-specific native API; the shared Python-stub pattern and conceptual model live in authoring-language-sdk-tasks" carves out a clear JVM niche and explicitly separates the sibling skills, so conflict risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.