airflow-plugins

Build Airflow 3.1+ plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI. Use this skill whenever the user wants to create an Airflow plugin, add a custom UI page or nav entry to Airflow, build FastAPI-backed endpoints inside Airflow, serve static assets from a plugin, embed a React app in the Airflow UI, add middleware to the Airflow API server, create custom operator extra links, or call the Airflow REST API from inside a plugin. Also trigger when the user mentions AirflowPlugin, fastapi_apps, external_views, react_apps, plugin registration, or embedding a web app in Airflow 3.1+. If someone is building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface, this skill almost certainly applies.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

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 thoroughly covers specific capabilities, provides abundant natural trigger terms, explicitly addresses both what and when, and occupies a clearly distinct niche. The description is comprehensive without being padded—every phrase adds meaningful selection criteria. It uses proper third-person voice throughout and includes both high-level use cases and specific technical identifiers that would help Claude accurately select this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: build plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links. Also details specific sub-tasks like serving static assets, adding middleware to the API server, and creating custom operator extra links.	3 / 3
Completeness	Clearly answers both 'what' (build Airflow 3.1+ plugins with FastAPI apps, UI pages, React components, middleware, macros, operator links) and 'when' with explicit 'Use this skill whenever...' and 'Also trigger when...' clauses providing comprehensive trigger guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'Airflow plugin', 'custom UI page', 'FastAPI', 'React app', 'AirflowPlugin', 'fastapi_apps', 'external_views', 'react_apps', 'plugin registration', 'nav entry', 'operator extra links', 'Airflow REST API'. These are terms a developer working with Airflow would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: Airflow 3.1+ plugin development specifically involving UI/browser-facing interfaces. The version specificity (3.1+), the specific class names (AirflowPlugin, fastapi_apps, external_views, react_apps), and the narrow domain make it very unlikely to conflict with other skills.	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 high-quality, highly actionable skill that provides comprehensive guidance for building Airflow 3.1+ plugins. Its greatest strengths are the executable code examples, clear step-by-step workflow, upfront safety warnings, and the excellent pitfalls table. The main weakness is that the document is quite long for a single SKILL.md — several sections (JWT management, API patterns, component types) could be extracted into separate reference files to improve token efficiency and progressive disclosure.

Suggestions

Extract the JWT token management section and common API endpoint patterns into separate reference files (e.g., AUTH.md, API_PATTERNS.md) and link to them from the main skill to reduce the monolithic size.

Trim explanatory comments that Claude already understands (e.g., 'Note that requests.get() is blocking', 'SQLAlchemy queries are blocking') to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive and mostly efficient, but includes some sections that could be tightened — e.g., the JWT token management block is very long, the streaming proxy example may not be core enough to warrant inclusion inline, and some explanatory notes (like explaining what asyncio.to_thread does) are things Claude already knows. However, most content earns its place given the complexity of the topic.	2 / 3
Actionability	Excellent actionability throughout — every section provides fully executable, copy-paste-ready Python code with correct imports, concrete FastAPI route definitions, HTML examples, CLI commands, and even verification steps. The code examples are complete and realistic, not pseudocode.	3 / 3
Workflow Clarity	The skill follows a clear numbered step sequence (Steps 1-7) with explicit validation checkpoints: the 'Before writing any code, verify' checklist at the top, restart requirements called out, verification via Admin > Plugins, and a comprehensive pitfalls table that serves as a troubleshooting feedback loop. The conditional skip guidance ('skip to Step 5 or Step 6') is a nice touch for non-linear workflows.	3 / 3
Progressive Disclosure	The content is well-structured with clear headers and tables, but it's a monolithic ~400-line document with no bundle files to offload detailed sections. The JWT token management, common API patterns, and component type details could be split into separate reference files. External references are limited to Airflow docs links. For a skill this complex, splitting into a quick-start overview plus detailed reference files would improve navigability.	2 / 3
	Total	10 / 12 Passed

Validation

90%

Warnings & errors only

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 (592 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: astronomer/agents
Commit: 535a040

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.