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

49%

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/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 well-structured and specific across architecture, ingestion, orchestration, transformation, quality, storage, and monitoring, but it inlines everything in one file, uses a non-executable code example, and lacks validation feedback loops in its main workflow. Scores are uniformly middling because these gaps cap each dimension.

Suggestions

Split tool-specific deep dives (dbt modeling, Great Expectations suites, Delta/Iceberg operations) into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Replace the example's fictional imports with real, runnable code (e.g. actual pyspark/spark-delta or dbt calls) or explicitly justify the illustrative pseudocode so the example is executable.

Add explicit validation checkpoints to the Instructions workflow (e.g. after ingestion: 'Validate schema and run DQ suite; on failure, route to DLQ and retry' before proceeding to transformation) to lift workflow clarity above the batch-operation cap.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet lists that avoid re-explaining concepts Claude knows, but it is lengthy and the example code imports fictional packages. It is not 4 because the volume and non-runnable example could be trimmed further.	3 / 5
Actionability	Bullets give specific, concrete guidance (exactly-once consumers, manual offset commits, dbt staging/marts, Delta merge modes), but the sole code example uses non-existent modules like 'from batch_ingestion import BatchDataIngester', making it pseudocode rather than executable. Not 4 because the runnable example is not copy-paste ready.	3 / 5
Workflow Clarity	The Instructions section sequences seven numbered steps and a Success Criteria checklist exists, but this is a batch-operation skill whose main workflow lacks explicit validate→fix→retry checkpoints between steps; per rubric guidance that caps workflow clarity at 3. Not 4 because feedback loops are absent from the primary flow.	3 / 5
Progressive Disclosure	Sections are well-headed, but no bundle files (references/, scripts/, assets/) exist and large tool-specific detail (dbt, Great Expectations, Delta, Iceberg) is inlined in one file; the under-50-lines simple-skill exception does not apply here. Not 4 because content that belongs in separate reference files is not split out.	3 / 5
	Total	12 / 20 Passed

Description

48%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 declares a clear domain niche but is persona-flavored rather than action-oriented, and it omits any 'use when' trigger guidance. It is distinct enough but would benefit from concrete verbs and explicit trigger phrases.

Suggestions

Replace the persona phrasing with concrete actions, e.g. 'Design and implement batch and streaming data pipelines — ETL/ELT, ingestion, orchestration, and storage with dbt, Airflow, Delta Lake, and Iceberg.'

Add an explicit trigger clause: 'Use when designing, building, debugging, or optimizing data pipelines, or when the user mentions ETL, ELT, Airflow, dbt, Kafka, Delta Lake, or Iceberg.'

Include common synonyms/file-tech keywords (ETL, ELT, data engineering, .sql, .py DAGs) to raise trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('data pipeline architecture', 'batch and streaming data processing') but lists no concrete actions — 'specializing in scalable, reliable, and cost-effective data pipelines' uses adjectives, not verbs. It does not reach 3 because there are no 1-2 concrete actions named.	2 / 5
Completeness	It states a clear 'what' (data pipeline architecture expert for batch/streaming) but provides no 'use when' trigger clause; per rubric guidance a missing explicit trigger caps completeness at 3. Not 4 because 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	'data pipeline' and 'batch and streaming data processing' are relevant natural terms, but common variations/synonyms users say (ETL, ELT, data engineering, Kafka/Airflow/dbt) are absent. Not 4 because keyword coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	'Data pipeline architecture' is a clear, specific niche with minimal conflict risk, though it could overlap with broader data-engineering skills. Not 5 because the generic 'expert specializing in' framing does not give sharply distinct triggers.	4 / 5
	Total	12 / 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/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.