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.

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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/data-engineering-data-pipeline/SKILL.md

The canonical home for this skill is data-engineering-data-pipeline in rmyndharis/antigravity-skills

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 comprehensive, well-sectioned capability catalog with a validation-aware example, but it is verbose, ships a non-executable code example, and inlines ~200 lines of tool reference detail that belongs in separate files.

Suggestions

Replace the fictional imports in the example with a real, copy-paste-runnable snippet (e.g. actual pdfplumber-style or pyarrow/delta-spark calls) or explicitly label it as illustrative.

Split the per-tool detail (Airflow/Prefect, dbt, Great Expectations, Delta Lake, Iceberg) into reference files under references/ and keep SKILL.md a concise overview with one-level-deep links.

Add explicit validation checkpoints to the workflow (e.g. "Run data-quality suite; only proceed to storage write when >99% pass") and remove the verbatim repeat of the frontmatter description on line 11.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but ~200 lines of bullet catalogs, repeats the frontmatter description verbatim on line 11, and explains concepts Claude already knows (e.g. "ETL (transform before load)", "Time travel for historical queries"), so it could be tightened.	3 / 5
Actionability	A code example is present but uses fictional, non-executable imports ("from batch_ingestion import BatchDataIngester", "from storage.delta_lake_manager import DeltaLakeManager"), and the surrounding guidance is high-level bullets without concrete commands or config snippets.	3 / 5
Workflow Clarity	The seven instruction sections form a rough sequence (design → ingest → orchestrate → transform → quality → storage → monitor) and validation is mentioned (schema validation, dead-letter queue, Great Expectations), but checkpoints are implicit rather than explicit gates, so the batch-operation cap of 3 applies.	3 / 5
Progressive Disclosure	The skill is a single ~200-line monolithic file with clear section headers but no bundle/reference files; the tool-specific detail for Airflow/Prefect/dbt/Great Expectations/Delta/Iceberg is inlined and would be better split into separate reference documents.	3 / 5
	Total	12 / 20 Passed

Description

43%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 conveys a clear domain and scope but lacks action verbs and any explicit "Use when" trigger guidance, and it uses second-person voice. Trigger term coverage is reasonable but missing common synonyms.

Suggestions

Rewrite in third person with concrete action verbs, e.g. "Designs and implements scalable batch and streaming data pipelines (ETL/ELT, Lambda, Kappa, Lakehouse) with orchestration, storage, and data-quality controls."

Add an explicit trigger clause: "Use when designing data pipeline architecture, or when the user mentions ETL/ELT, batch/streaming ingestion, Airflow/Prefect, dbt, Delta Lake/Iceberg, or pipeline cost optimization."

Include natural synonyms and tooling names users actually say (ETL, ELT, data engineering, Airflow, dbt, Kafka) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("data pipeline architecture") but uses a role framing ("specializing in") rather than concrete actions like design, build, or orchestrate; content alone is a 2, reduced by 1 because it uses second-person voice ("You are a data pipeline architecture expert").	1 / 5
Completeness	A clear "what" is present (data pipeline architecture for batch/streaming), but there is no "Use when…" trigger clause, so completeness is capped at 3 per the missing-trigger guideline.	3 / 5
Trigger Term Quality	"data pipeline", "batch and streaming data processing" are natural domain terms, but common synonyms and tooling variations users say (ETL/ELT, data engineering, Airflow, dbt, Kafka) are absent.	3 / 5
Distinctiveness Conflict Risk	"data pipeline architecture" is a fairly distinct niche unlikely to fire for unrelated skills, with only minor overlap risk against broader data-engineering skills.	4 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/data-engineering-data-pipeline/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.