CtrlK
BlogDocsLog inGet started
Tessl Logo

airflow-dag-patterns

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

76

1.09x
Quality

72%

Does it follow best practices?

Impact

92%

1.09x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/airflow-dag-patterns/SKILL.md

The canonical home for this skill is airflow-dag-patterns in rmyndharis/antigravity-skills

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 brief and well-sectioned, but it defers all substantive guidance to `resources/implementation-playbook.md`, which is missing from the bundle, leaving the skill with abstract directions and no executable content. Adding a minimal working DAG example and fixing or removing the dangling reference would substantially improve it.

Suggestions

Add minimal executable guidance inline (e.g., a short DAG definition snippet showing retries, idempotency, and scheduling) so the skill is usable without the missing playbook, addressing the low actionability score.

Fix the dangling reference: either include `resources/implementation-playbook.md` in the bundle or remove the pointer, and state it once instead of duplicating it in both Instructions and Resources.

Replace the single 'Validate in staging' step with explicit validation checkpoints and feedback loops (e.g., run `airflow dags test <dag_id>` after implementation, fix and re-run on failure) to lift workflow clarity for this batch-operation context.

DimensionReasoningScore

Conciseness

The body is lean with clear sections and no explanation of concepts Claude already knows, matching 'efficient; minor instances that could be trimmed'. Not a 5 because the identical reference to `resources/implementation-playbook.md` is stated twice (Instructions and Resources) with near-identical phrasing; not a 3 because there is no substantive verbosity beyond that duplication.

4 / 5

Actionability

Instructions are high-level hints only — "Identify data sources, schedules, and dependencies", "Design idempotent tasks with clear ownership and retries", "Implement DAGs with observability and alerting hooks" — with no code, commands, examples, or concrete patterns, matching 'minimal concrete guidance; missing the specific steps to execute'. Not a 3 because there is no executable or pseudocode-level guidance at all: all substance is deferred to `resources/implementation-playbook.md`, which does not exist in the bundle; not a 1 because a rough high-level process is at least outlined.

2 / 5

Workflow Clarity

Four numbered steps give a coherent identify → design → implement → validate sequence with a staging-validation step and a Safety section, but checkpoints are implicit with no feedback loops or verification commands, matching 'steps listed but validation gaps; checkpoints missing or implicit'. As a batch-operation workflow it also cannot exceed 3 without explicit validation/verification steps, and it lacks them; not a 2 because the sequence itself is well-ordered and coherent.

3 / 5

Progressive Disclosure

Sections (Use when, Do not use, Instructions, Safety, Resources) are well organized and the reference is one level deep, but the single referenced path `resources/implementation-playbook.md` does not exist in the bundle and is duplicated across two sections, so the disclosure structure does not actually deliver detail. This sits between 'references present but not clearly signaled' and 'references mostly clear; minor organization gaps'; not a 4 because a dangling, duplicated reference is more than a minor organization gap.

3 / 5

Total

12

/

20

Passed

Description

83%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 strong: it explicitly states what the skill does and when to use it, with natural trigger terms and a distinct Airflow-specific niche. Minor improvements possible by adding synonym coverage (ETL, data engineering) and pipeline-failure phrasing.

DimensionReasoningScore

Specificity

"Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment" names the domain and lists several concrete facets (operators, sensors, testing, deployment), matching the 'several specific actions; minor gaps' anchor. It is not a 5 because the action coverage is narrower (essentially one build action with practice areas) and not a 3 because more than 1-2 concrete items are enumerated.

4 / 5

Completeness

It clearly answers what ("Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment") and when ("Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs") with concrete trigger phrases, matching the top anchor. A 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"creating data pipelines, orchestrating workflows, or scheduling batch jobs" plus "Apache Airflow" and "DAGs" give good natural keyword coverage users would actually say. Not a 5 because common variations like ETL, data engineering, or pipeline failure/debugging phrasings are missing; not a 3 because multiple natural terms beyond just the domain name are present.

4 / 5

Distinctiveness Conflict Risk

Apache Airflow DAGs is a clear niche with explicit tool naming, keeping conflict risk low. Not a 5 because generic triggers like "orchestrating workflows" or "data pipelines" could overlap with other orchestration tools (Prefect, Luigi, cron); not a 3 because the explicit Airflow/DAG naming makes it mostly distinct.

4 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.