CtrlK
BlogDocsLog inGet started
Tessl Logo

authoring-go-sdk-tasks

Writes Airflow task logic in Go using the Airflow Go SDK. Use when the user wants to implement Airflow tasks in Go, asks about `BundleProvider`/`RegisterDags`, the `bundlev1` Registry/Dag interfaces, registering Go tasks (`AddTask`/`AddTaskWithName`), dependency injection by parameter type (`context.Context`, `sdk.TIRunContext`, `*slog.Logger`, `sdk.Client`), or reading connections/variables/XComs from Go. This skill covers the Go-specific native API; the shared Python-stub pattern and conceptual model live in authoring-language-sdk-tasks. For building/packing/shipping the bundle see deploying-go-sdk-bundles; for coordinator config see configuring-airflow-language-sdks.

75

Quality

93%

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

93%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.

Tight, executable, and well-structured Go SDK authoring guidance with complete code examples and clean deferral to sibling skills for shared concepts. It lacks explicit validation feedback loops, but the skill is authoring/reference-oriented rather than a destructive batch workflow, so that gap is minor.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it assumes Go/Airflow competence, never explains what Go or Airflow is, and every section (entry point, DI table, client surface, context, pitfalls) earns its place.

5 / 5

Actionability

Provides fully executable, copy-paste-ready Go code for the bundle entry point, task functions, and runtime context, plus concrete API tables covering the common cases.

5 / 5

Workflow Clarity

The body follows a clear recap→entry-point→task-functions→client→context→pitfalls sequence with a pitfalls guardrail section, but it is API authoring guidance rather than a destructive/batch operation, so explicit validate-then-proceed checkpoints are not present.

4 / 5

Progressive Disclosure

A single, well-organized SKILL.md with clearly signaled one-level pointers to sibling skills (authoring-language-sdk-tasks, deploying-go-sdk-bundles, configuring-airflow-language-sdks) for shared/deploy/config concerns — appropriate for a self-contained skill with no bundle files.

5 / 5

Total

19

/

20

Passed

Description

92%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 high-quality description with a clear 'what' and explicit 'when' triggers, comprehensive concrete capability enumeration, and strong boundary discipline against sibling skills. Trigger phrasings lean slightly technical, keeping trigger_term_quality just below the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and API surfaces — BundleProvider/RegisterDags, AddTask/AddTaskWithName, DI by parameter type, reading connections/variables/XComs — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (writes Airflow task logic in Go) and 'when' with concrete trigger phrases and named APIs, matching the top anchor.

5 / 5

Trigger Term Quality

Opens with the natural phrase 'Use when the user wants to implement Airflow tasks in Go' and enumerates asks-about triggers (API names, DI types), but several triggers are API jargon rather than the plain phrasings a user would naturally say.

4 / 5

Distinctiveness Conflict Risk

Carves a clear Go-specific niche and explicitly off-loads the shared Python-stub pattern, bundle deployment, and coordinator config to named sibling skills, minimizing conflict risk.

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.

Validation16 / 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.