airflow-hitl
Use when the user needs human-in-the-loop workflows in Airflow (approval/reject, form input, or human-driven branching). Covers ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator. Requires Airflow 3.1+. Does not cover AI/LLM calls (see airflow-ai).
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 an excellent skill description that clearly defines its scope, provides specific trigger terms, and explicitly states both when to use it and when not to use it. The cross-reference to the airflow-ai skill for excluded functionality is a particularly strong touch that minimizes conflict risk. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: 'approval/reject, form input, human-driven branching' and names four specific operators (ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator). Also specifies version requirement (Airflow 3.1+). | 3 / 3 |
Completeness | Explicitly answers both 'what' (human-in-the-loop workflows covering approval/reject, form input, branching with specific operators) and 'when' ('Use when the user needs human-in-the-loop workflows in Airflow'). Also includes a helpful exclusion boundary ('Does not cover AI/LLM calls'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'human-in-the-loop', 'approval', 'reject', 'form input', 'branching', plus specific operator names. The abbreviation 'HITL' and 'Airflow' are terms users in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (HITL workflows in Airflow 3.1+), specific operator names as triggers, and an explicit boundary excluding AI/LLM calls with a cross-reference to 'airflow-ai', which directly reduces conflict risk. | 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, actionable skill with excellent executable examples for all four HITL operators and a clear sequential workflow. The main weakness is that it's somewhat long for a SKILL.md—the optional features and detailed examples for each operator could be split into reference files. Minor verbosity in sections like callbacks and markdown body examples, which cover standard Airflow features Claude likely already knows.
Suggestions
Consider moving the detailed operator examples (Step 2) and optional features (Step 3) into a separate REFERENCE.md, keeping only the ApprovalOperator example inline as a quick-start pattern.
Remove the callbacks section entirely—standard Airflow callback usage is not HITL-specific and Claude already knows how to use on_failure_callback/on_success_callback.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary verbosity like the callbacks section (standard Airflow feature Claude already knows), the markdown body example, and some explanatory text that could be trimmed. The overall length is reasonable but could be tightened. | 2 / 3 |
Actionability | Every operator has a fully executable, copy-paste-ready code example with proper imports, DAG structure, and downstream task consumption. The API integration section includes concrete HTTP requests. Parameter requirements are clearly called out. | 3 / 3 |
Workflow Clarity | The content follows a clear 5-step sequential workflow (Choose → Implement → Optional features → API → Safety checks) with an explicit safety checklist at the end that serves as a validation checkpoint. The decision table in Step 1 clearly guides operator selection. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical progression, but it's quite long (~200 lines of substantive content) and could benefit from splitting detailed operator examples or optional features into separate reference files. The cross-references to related skills are good, but the main file tries to be comprehensive rather than an overview. | 2 / 3 |
Total | 10 / 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
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.