CtrlK
BlogDocsLog inGet started
Tessl Logo

data-engineering-data-pipeline

You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.

44

Quality

45%

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/data-engineering-data-pipeline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The content is a well-organized, dense catalog of data-pipeline patterns that mostly respects the token budget, but it falls short on executability (invented module imports, descriptive rather than instructional guidance) and lacks validation checkpoints in its batch/destructive workflow. Splitting per-tool detail into referenced files would improve progressive disclosure.

Suggestions

Make the code example executable by using real libraries or clearly marking the imports as illustrative placeholders with concrete substitutes.

Add explicit validation gates between pipeline stages (e.g., validate schema and quality before writing to Delta/Iceberg; re-run on failure) to support feedback loops.

Move per-tool reference detail (dbt, Delta Lake, Iceberg, Airflow/Prefect) into separate one-level-deep reference files and link to them from the overview.

DimensionReasoningScore

Conciseness

The body is mostly terse bullets that assume Claude's knowledge with no concept-explaining fluff, but it repeats the frontmatter description verbatim, includes generic use/don't-use sections, and aspirational "Output Deliverables"/"Success Criteria" checklists that could be trimmed.

2 / 3

Actionability

It names specific tools and includes a code example, but the example imports invented modules (batch_ingestion, storage.delta_lake_manager) that are not executable, and most sections describe patterns rather than giving copy-paste commands or config.

2 / 3

Workflow Clarity

The seven numbered "Architecture Design" through "Monitoring" sections give a clear sequence, but for batch/destructive pipeline operations there are no explicit validation checkpoints or validate-fix-retry feedback loops, capping workflow_clarity at 2.

2 / 3

Progressive Disclosure

No bundle files exist, so everything is inline; the ~200-line body is organized with headers but is effectively monolithic, with per-tool detail (dbt, Delta, Iceberg, Airflow) that could be split into one-level-deep reference files.

2 / 3

Total

8

/

12

Passed

Description

40%

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 identifies a coherent domain but reads as a single descriptive sentence with no concrete actions or explicit use-trigger, and it uses second-person voice which the rubric penalizes. It is functional but below the strong examples that pair specific actions with a "Use when..." clause.

Suggestions

Rewrite in third person and lead with concrete actions, e.g. "Designs and implements ETL/ELT, Lambda, Kappa, and Lakehouse pipelines...".

Add an explicit trigger clause: "Use when working on data pipelines, ETL/ELT, batch or streaming ingestion, or tools like Airflow, dbt, Delta Lake, or Iceberg."

Include natural user-facing terms (ETL, data engineering, data ingestion, dbt, Airflow) to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain and modes ("data pipeline architecture expert", "batch and streaming data processing") but lists no concrete actions, and the second-person opener "You are a data pipeline architecture expert" is penalized per the voice guideline, reducing specificity by 1.

1 / 3

Completeness

It states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

"data pipeline" is a natural user term, but coverage is thin — common variations like ETL, data engineering, Airflow, dbt, or data ingestion are absent, and "scalable, reliable, and cost-effective" is adjective fluff.

2 / 3

Distinctiveness Conflict Risk

"data pipeline architecture" is a recognizable niche, but the generic quality adjectives and absence of distinct explicit triggers leave it overlapping with general data-engineering/ETL skills.

2 / 3

Total

7

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-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.