blueprint
Define reusable Airflow task group templates with Pydantic validation and compose DAGs from YAML. Use when creating blueprint templates, composing DAGs from YAML, validating configurations, or enabling no-code DAG authoring for non-engineers.
90
88%
Does it follow best practices?
Impact
Pending
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 a strong skill description that clearly articulates specific capabilities (reusable task group templates, Pydantic validation, YAML DAG composition) and includes an explicit 'Use when' clause with relevant trigger scenarios. The description is concise, uses third-person voice, and targets a well-defined niche within the Airflow ecosystem, making it highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Define reusable Airflow task group templates', 'Pydantic validation', 'compose DAGs from YAML', 'validating configurations', 'no-code DAG authoring'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (define reusable task group templates with Pydantic validation, compose DAGs from YAML) and 'when' (explicit 'Use when' clause covering creating blueprint templates, composing DAGs from YAML, validating configurations, or enabling no-code DAG authoring). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Airflow', 'task group', 'templates', 'Pydantic', 'DAGs', 'YAML', 'blueprint', 'no-code', 'DAG authoring', 'configurations'. Good coverage of terms an Airflow user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Airflow task groups, Pydantic validation, YAML-based DAG composition, and no-code authoring. This is unlikely to conflict with other skills due to its very specific domain and technology stack. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent executable examples and clear workflow sequencing. Its main weakness is length — the document tries to be comprehensive in a single file rather than using progressive disclosure to split detailed sections into referenced files. The routing table at the top adds some unnecessary verbosity but does aid navigation within the monolithic structure.
Suggestions
Consider splitting detailed sections (Troubleshooting, Runtime Parameter Overrides, Customizing DAG-Level Configuration, Versioning) into separate referenced files to reduce the main skill's token footprint.
Remove or condense the 'Determine What the User Needs' routing table — Claude can infer user intent without an explicit lookup table, and this adds ~20 lines of overhead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some unnecessary verbosity, such as the routing table at the top (Claude can determine what the user needs without an explicit lookup table), and some explanatory text that could be trimmed. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable code examples throughout — complete Python classes, bash commands, YAML configurations, and CLI invocations. Every section gives copy-paste ready guidance with specific imports, class structures, and command-line usage. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced (Project Setup has numbered steps, validation workflow is explicit, versioning has clear progression). The verification checklist at the end provides validation checkpoints, and the troubleshooting section covers error recovery. The 'Before Starting' confirmation step and lint-before-deploy pattern constitute good feedback loops. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a routing table for navigation, but it's a long monolithic document (~300+ lines) with no references to external files for detailed content. Sections like Troubleshooting, Runtime Parameter Overrides, and Customizing DAG-Level Configuration could be split into separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (503 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- astronomer/agents
- Commit
0642adb
- 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.