CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apache-airflow-orchestration

Complete guide for Apache Airflow orchestration including DAGs, operators, sensors, XComs, task dependencies, dynamic workflows, and production deployment

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/luxor-data-engineering/skills/apache-airflow-orchestration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

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

The body is a monolithic, tutorial-style dump of the Airflow documentation: highly concrete code but verbose with material Claude already knows, no bundled reference files, and a broken EXAMPLES.md pointer. It works as an API cheat sheet but fails as a well-structured skill with progressive disclosure.

Suggestions

Cut the 'Core Concepts' tutorial material (what Airflow/DAGs/operators/executors are, cron syntax tables) that Claude already knows, and keep only Airflow-specific gotchas and patterns.

Create the referenced EXAMPLES.md (or remove the reference) and split operator/sensor API detail into references/ files so SKILL.md is a lean overview with one-level-deep pointers.

Inconsistent import paths ('airflow.sdk' vs 'airflow.operators.python', 'airflow.datasets.Dataset' vs 'airflow.sdk Asset', deprecated 'apply_defaults') mix Airflow 2 and 3 idioms — pick one version and state it upfront, moving legacy patterns to a 'deprecated' section.

DimensionReasoningScore

Conciseness

At ~1,660 lines the body extensively re-teaches concepts Claude already knows — 'What is Apache Airflow?', definitions of DAGs/operators/sensors, executor type descriptions, cron preset tables, and basic dependency syntax lifted from the Airflow tutorial. It is noticeably verbose with several padded sections (anchor 2), though not wholly padding since deferrable sensors and asset aliases are genuinely non-obvious.

2 / 5

Actionability

Most sections provide concrete, copy-paste-ready code (full DAG definitions with imports, ExternalTaskSensor configs, retry settings, pytest tests). Minor gaps: several snippets reference undefined variables (task1/op1), use placeholder '...' in a DAG call, and rely on undefined helpers like save_to_s3/execute_sql — 'mostly executable with minor gaps' (anchor 4).

4 / 5

Workflow Clarity

The content is organized by topic rather than as a sequenced process — there is no ordered build → test → deploy workflow with checkpoints. The Testing DAGs section does provide concrete pytest validation, placing it above anchor 2, but validation is not integrated into any workflow sequence, so it fits anchor 3.

3 / 5

Progressive Disclosure

Section headers are consistent and the body points to an EXAMPLES.md file for extended examples, but no bundle files exist (references/, scripts/, assets/ are absent), so that pointer is dangling, and large blocks of operator/sensor API reference material that belong in separate files are inlined in SKILL.md. This matches anchor 3: some structure, references present but not clearly signaled, content that should be separate is inline.

3 / 5

Total

12

/

20

Passed

Description

65%Weight 40%Scale 1-5

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 distinctive and uses good natural trigger terms, but it reads as a topic inventory rather than a capability statement and omits any 'Use when' trigger guidance, which caps its completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building, scheduling, or debugging Airflow DAGs and data pipelines.'

Convert topic nouns into concrete actions, e.g. 'Builds and schedules DAGs, wires task dependencies and sensors, passes data via XComs, and deploys to production executors.'

Add natural synonyms users say, such as 'data pipelines', 'ETL', and 'workflow scheduling'.

DimensionReasoningScore

Specificity

The description enumerates specific topics ('DAGs, operators, sensors, XComs, task dependencies, dynamic workflows, and production deployment') but uses no action verbs — 'Complete guide ... including' is a topic list rather than a statement of capabilities, and 'Complete guide' is a mild over-claim. It sits between anchors 3 and 4; the total absence of concrete actions keeps it at 3 rather than 4.

3 / 5

Completeness

The 'what' is present (an orchestration guide covering the listed topics) but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance anywhere in the description. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

'Apache Airflow', 'DAGs', 'operators', 'sensors', 'XComs', and 'task dependencies' are natural terms users say when they need this skill. A few common variations are missing ('data pipelines', 'ETL', 'workflow scheduling'), so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

'Apache Airflow orchestration' names a clear niche with distinct technical triggers (DAGs, XComs, sensors); only a near-duplicate Airflow skill would conflict, matching the anchor-5 example of a clear niche with minimal conflict risk.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1667 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

manutej/luxor-claude-marketplace

Path

plugins/luxor-data-engineering/skills/apache-airflow-orchestration/SKILL.md

Revision

1861cc9

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill