data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.

Quality

48%

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-engineer/SKILL.md

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

Quality

Content

31%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 large capability/tool catalog that enumerates technologies Claude already knows, offering little executable guidance and no validation checkpoints in its workflows. It is also monolithic with no progressive disclosure or external reference files despite its length.

Suggestions

Trim the technology enumeration and replace it with concise, decision-oriented guidance Claude doesn't already know (trade-offs, when to pick Iceberg vs Delta vs Hudi, sizing/partitioning rules of thumb) to improve conciseness and actionability.

Add concrete, executable artifacts (a dbt project scaffold, an Airflow DAG template, a Spark/Great Expectations validation snippet) so guidance is copy-paste ready rather than descriptive.

Add validation checkpoints to the pipeline workflow (e.g., 'Run Great Expectations suite before writing to production; only proceed on pass') and move the capability/tool catalog into reference files (e.g., references/stacks.md, references/cloud-services.md) with one-level-deep links from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~190-line body is a long enumerative catalog of tools and technologies Claude already knows (Spark, Kafka, Snowflake, BigQuery, Iceberg, etc.), padded across many capability subsections; it noticeably over-lists concepts Claude already knows rather than adding guidance Claude doesn't, fitting the 'noticeably verbose' anchor and falling below the 'mostly efficient' 3.	2 / 5
Actionability	Provides only high-level directives ('Define sources, SLAs, and data contracts', 'Choose architecture, storage, and orchestration tools') with no code, commands, templates, or concrete executable steps; it describes rather than instructs, matching the 'minimal concrete guidance' 2 anchor and not reaching 3 where incomplete-but-present executable guidance would appear.	2 / 5
Workflow Clarity	Both the Instructions (4 steps) and Response Approach (8 steps) sections give a present sequence, but there are no validation checkpoints; since the skill involves batch operations and writes to production sinks, the rubric's destructive/batch validation rule caps workflow_clarity at 3 even though steps are listed.	3 / 5
Progressive Disclosure	All content is inlined monolithically in SKILL.md with no bundle files (references/, scripts/, assets/ all absent), and the long capability/tool catalog clearly belongs in separate reference files; minimal offloading structure with references buried (none signaled), matching the 'content that belongs in separate files is inlined' anchor.	2 / 5
	Total	9 / 20 Passed

Description

66%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 clearly states what the skill does and names specific technologies, but lacks an explicit 'Use when...' trigger clause, capping completeness at 3. It is specific and reasonably distinctive but reads more as a capability list than activation guidance.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases users would say (e.g., 'Use when designing ETL/ELT pipelines, building data warehouses or lakehouses, or working with Spark, dbt, or Airflow').

Include common synonyms users say ('ETL', 'ELT', 'data engineering', 'data orchestration') to broaden natural trigger coverage.

Tighten the verbs beyond generic 'Build'/'Implements' to concrete actions (e.g., 'designs', 'implements', 'orchestrates', 'optimizes') for stronger specificity.

Dimension	Reasoning	Score
Specificity	Names concrete domains ('scalable data pipelines, modern data warehouses, real-time streaming architectures') and specific tools (Apache Spark, dbt, Airflow, cloud-native platforms), covering several actions with only minor gaps; not a 5 because the verbs are generic ('Build', 'Implements') over broad domains rather than a fully enumerated action set.	4 / 5
Completeness	Has a clear 'what' (build pipelines, warehouses, streaming architectures) but no explicit 'when'/'Use when' trigger clause, so per the rubric guideline a missing explicit trigger caps completeness at 3; clearly above the 2 anchor because the 'what' is concrete, not below at 4 because 'when' is absent.	3 / 5
Trigger Term Quality	Includes natural user-facing terms ('data pipelines', 'data warehouses', 'streaming', 'Spark', 'dbt', 'Airflow') that users would plausibly say, but omits common variations/synonyms like 'ETL', 'ELT', 'data engineering', and any file extensions; falls short of comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The data-engineering niche with named tools is mostly distinct from unrelated skills, though 'data pipelines'/'data platforms' is broad enough to risk minor overlap with analytics or ML-pipeline skills; not 5 because the boundary is not crisply drawn against adjacent data skills.	4 / 5
	Total	15 / 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-engineer/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.