annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a narrow, specific domain (Airflow data lineage) with concrete actions and explicit trigger guidance. It uses third person voice correctly, includes domain-specific trigger terms that users would naturally use, and has a well-structured 'Use when' clause that covers the key scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific concrete actions: 'Annotate Airflow tasks with data lineage using inlets and outlets', 'add lineage metadata to tasks', 'specify input/output datasets', and 'enable lineage tracking for operators without built-in OpenLineage extraction'. These are multiple distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (annotate Airflow tasks with data lineage using inlets and outlets) and 'when' (explicit 'Use when' clause covering adding lineage metadata, specifying input/output datasets, or enabling lineage tracking for operators without built-in OpenLineage extraction). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Airflow tasks', 'data lineage', 'inlets', 'outlets', 'lineage metadata', 'input/output datasets', 'lineage tracking', 'operators', 'OpenLineage'. These cover the domain-specific terms a user working with Airflow lineage would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Airflow task lineage annotation using inlets/outlets and OpenLineage. This is unlikely to conflict with other skills due to the very specific domain (Airflow + data lineage) and specific technical concepts (inlets, outlets, OpenLineage). | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent code examples covering the full range of inlet/outlet usage patterns. Its main weaknesses are moderate verbosity (redundant naming helper examples, marketing content) and the lack of any verification/validation steps to confirm lineage annotations are working correctly. The content would benefit from being split across bundle files given its length.
Suggestions
Add a verification step showing how to confirm lineage annotations are emitted correctly (e.g., checking OpenLineage events in logs, viewing in the Astro/Airflow UI lineage tab).
Remove the duplicate naming helpers content under Best Practices—keep it in one place and reference it from the other.
Remove or minimize the 'On Astro' marketing paragraph, which doesn't provide actionable guidance.
Consider splitting the naming helpers and custom operator sections into separate bundle files to reduce the main SKILL.md length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some redundancy—the naming helpers section is shown twice (once as a standalone section and again under Best Practices), and the 'On Astro' marketing paragraph adds little actionable value. The decision table and precedence rules are useful but could be more compact. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready code examples for every scenario: basic usage, multiple inputs/outputs, custom operators with both approaches, and naming helpers with concrete output comments. Import paths and constructor arguments are all specified. | 3 / 3 |
Workflow Clarity | The decision table for when to use inlets/outlets is helpful, and the precedence rules clarify fallback behavior. However, there are no explicit validation or verification steps—no guidance on how to confirm lineage annotations are working (e.g., checking the OpenLineage events, verifying in the UI), which is important for a metadata-annotation workflow. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a logical flow from simple to advanced. However, at ~250 lines it's quite long for a single file with no bundle files to offload detail into. The naming helpers section and custom operator patterns could be split into referenced files. The 'Related Skills' section at the end is a good touch for cross-referencing. | 2 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- astronomer/agents
- Commit
535a040
- 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.