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.

56

Quality

65%

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 ./skills/airflow-dag-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 well-organized and token-lean but nearly empty of actionable content: instructions are abstract directives with no code, commands, or concrete patterns, and the one reference that would carry the real detail points to a file that does not exist in the bundle. As written, the skill delegates everything to a missing playbook while offering only high-level guidance in its place.

Suggestions

Add the actual bundle file (e.g., references/implementation-playbook.md) with the promised patterns, checklists, and templates, and fix the path in the body so the reference resolves — currently the skill's core content is a dangling pointer.

Include at least one copy-paste-ready DAG skeleton in SKILL.md (schedule, retries, idempotent task pattern, an example operator or sensor) so the primary instructions are executable without the external file.

Make the workflow concrete: replace abstract directives like 'Implement DAGs with observability and alerting hooks' with specific steps and an explicit staging-validation checkpoint plus an error-recovery loop (what to check, what to do on failure).

DimensionReasoningScore

Conciseness

The body is short, assumes Airflow knowledge, and never explains concepts Claude already knows, so it is broadly efficient. It is not a 5 because of redundancy and boilerplate: the "resources/implementation-playbook.md" pointer appears twice ("Refer to" in Instructions and again in Resources), and the generic "Limitations" disclaimers ("Do not treat the output as a substitute for...", "Stop and ask for clarification...") add tokens without actionable value.

4 / 5

Actionability

The Instructions are high-level hints with no executable detail: "Design idempotent tasks with clear ownership and retries", "Implement DAGs with observability and alerting hooks", "Validate in staging and document operational runbooks" — no code, commands, DAG example, operator names, or configuration snippets anywhere. This matches the anchor of minimal concrete guidance missing the specific steps to execute; it is above 1 only because the steps do name real Airflow concepts.

2 / 5

Workflow Clarity

The four numbered steps give a recognizable sequence (identify → design → implement → validate/deploy) and step 4 includes a validation mention ("Validate in staging"), which avoids the missing-validation cap for batch operations. It is not a 4-5 because the checkpoints are implicit and there is no feedback loop (what to check, what to do when staging validation fails, how to verify idempotency before backfill), and each step is too abstract to execute unambiguously.

3 / 5

Progressive Disclosure

The only reference, "resources/implementation-playbook.md", is repeated twice yet no such file exists anywhere in the bundle (no references/, scripts/, assets/, or resources/ directory is present), so the single one-level reference is broken and the skill's substance is a dangling pointer. Section structure itself is present and the body is not monolithic, keeping this above 1, but the broken plus duplicated reference leaves navigation ineffective.

2 / 5

Total

11

/

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.

A strong description: third-person voice, concise, and it explicitly states both what the skill does and when to use it with natural trigger phrases. The main gaps are missing common synonyms (ETL, cron, task scheduling) and trigger terms broad enough to invite minor overlap with generic pipeline/orchestration skills.

DimensionReasoningScore

Specificity

"Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment" names the domain plus several concrete capability areas (operators, sensors, testing, deployment), matching the anchor for several specific actions with minor gaps. It is not a 5 because the actions are framed as topical coverage ("best practices for X") rather than fully distinct concrete actions, and "best practices" is mildly buzzwordy; it is above 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

The description explicitly answers both: 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. It is not a 4 because the "when" clause is already fully explicit rather than weakly specified.

5 / 5

Trigger Term Quality

"creating data pipelines, orchestrating workflows, or scheduling batch jobs" are natural phrases users would say when needing this skill, giving good keyword coverage. Not a 5 because common synonyms and variations are missing (e.g., "ETL", "cron", "task scheduling", "pipeline dependencies"); clearly above 3 since multiple relevant natural terms are present.

4 / 5

Distinctiveness Conflict Risk

"Apache Airflow DAGs" carves out a clear niche with distinct triggers, so it is mostly distinguishable. Not a 5 because "creating data pipelines, orchestrating workflows, or scheduling batch jobs" could also trigger generic ETL/data-engineering or other orchestrator skills (Prefect, cron-based tooling); not a 3 because the Airflow/DAG specificity is strong.

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
sickn33/agentic-awesome-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.