CtrlK
BlogDocsLog inGet started
Tessl Logo

airflow-plugins

Builds Airflow 3.1+ plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI. Use when building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface - creating an Airflow plugin, adding a custom UI page or nav entry, building FastAPI-backed endpoints inside Airflow, serving static assets from a plugin, embedding a React app, adding middleware to the API server, creating custom operator extra links, or calling the Airflow REST API from inside a plugin; also when AirflowPlugin, fastapi_apps, external_views, react_apps, or plugin registration come up.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code, clear step sequencing, and useful verification checkpoints, but it is a dense single-file skill whose critical rules are repeated for reinforcement and whose detailed API/token catalogs would benefit from being split into separate reference files for better progressive disclosure.

Suggestions

Move the Step 5 'Common API endpoint patterns' catalog and the Step 4 JWT token-management code into a bundled reference file (e.g. references/api-patterns.md) and link to it from SKILL.md, keeping the main body as an overview that earns the relative-path and asyncio.to_thread rules once.

Consolidate the repeated relative-path and asyncio.to_thread guidance into a single canonical statement (callout or checklist) rather than restating it in Step 3 and the Common pitfalls table, to tighten token efficiency.

Add an explicit validate→fix→retry loop for the direct-database-access pattern (e.g., verify query results / session handling before returning) since it is flagged as risky to Airflow's metadb.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes competence (it does not explain what FastAPI or Airflow is), but it restates critical rules — relative paths and asyncio.to_thread — across the CRITICAL callout, the pre-flight checklist, Step 3, and the pitfalls table, and includes explanatory prose around JWT caching that could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready Python (FastAPI routes, JWT token management, SDK-call wrapping, DB access) alongside concrete commands such as 'astro dev restart' and 'astro dev logs --api-server', matching the executable-code anchor.

3 / 3

Workflow Clarity

The seven steps are clearly sequenced, fronted by an explicit 'Before writing any code, verify' checklist, with error-recovery feedback via per-component log inspection and a final 'Verify the plugin loaded: open Admin > Plugins' checkpoint.

3 / 3

Progressive Disclosure

Sections, tables, and subsections are well organized, but the skill is a monolithic ~587-line SKILL.md with detailed catalogs (JWT token management, the Step 5 endpoint-pattern catalog, direct DB access) kept inline rather than split into bundled reference files, and no references/, scripts/, or assets/ bundle exists to offload detail.

2 / 3

Total

10

/

12

Passed

Description

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.

The description is specific, trigger-rich, and clearly answers both what it does and when to use it within a well-scoped Airflow 3.1+ plugin niche. It uses appropriate third-person voice with no fluff or over-claims.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It explicitly states what it does ('Builds Airflow 3.1+ plugins that embed...') and when to use it ('Use when building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface...'), satisfying both the what and the when with explicit triggers.

3 / 3

Trigger Term Quality

It covers natural phrasings users would say ('creating an Airflow plugin', 'custom UI page or nav entry', 'React app', 'middleware to the API server', 'operator extra links', 'calling the Airflow REST API') plus technical triggers (AirflowPlugin, fastapi_apps, external_views, react_apps), giving good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (Airflow 3.1+ plugins specifically) with distinctive triggers like AirflowPlugin, fastapi_apps, external_views, and react_apps, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (592 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

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.