data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

Quality

59%

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 ./skills/data-engineer/SKILL.md

Quality

Content

35%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 functions as an exhaustive role/catalog definition rather than actionable guidance: it lists many tools Claude already knows, provides only abstract workflow steps, and inlines everything with no progressive disclosure. The main improvements are trimming redundant catalog sections and adding concrete, executable patterns.

Suggestions

Cut the redundant Capabilities/Knowledge Base/Behavioral Traits catalogs that restate technologies Claude already knows; keep only non-obvious guidance, decision rules, and standards specific to your stack.

Replace abstract Instructions/Response Approach steps with concrete, executable patterns (e.g., example dbt project structure, Airflow DAG skeleton, a Great Expectations validation suite snippet, CDC config).

Add explicit validation checkpoints and error-recovery loops in the pipeline workflow (e.g., validate schema -> run quality checks -> only then write to production sink -> alert on failure), since this skill covers batch and production writes.

Move the long cloud-platform capability lists into reference files (e.g., references/aws-stack.md) referenced one level deep from SKILL.md, so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The 215-line body is a padded catalog restating technologies Claude already knows (Snowflake, BigQuery, Kafka, Spark, etc.) across redundant sections (Capabilities, Knowledge Base, Behavioral Traits) that add little beyond the description.	2 / 5
Actionability	Guidance is high-level and abstract ('Define sources, SLAs, and data contracts', 'Analyze data requirements for scale, latency, and consistency needs') with no concrete code, commands, templates, or specific executable procedures.	2 / 5
Workflow Clarity	A rough sequence exists (Instructions 1-4 and Response Approach 1-8), and the Safety section notes to 'Validate data before writing to production sinks', but explicit validation checkpoints and error-recovery feedback loops are otherwise absent for batch/production operations.	3 / 5
Progressive Disclosure	Section headers provide some structure, but the entire capability catalog (cloud stacks, tool lists) is inlined in one file with no bundle references, so content that could live in separate files is all inline.	3 / 5
	Total	10 / 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.

The description is well-constructed: third-person voice, concrete actions, named tools, and an explicit 'Use PROACTIVELY for ...' trigger clause answering both what and when. It is slightly tool-list-heavy and could add a few more natural synonyms, but is strong overall.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Build scalable data pipelines, modern data warehouses, and real-time streaming architectures') and specific tools ('Implements Apache Spark, dbt, Airflow'), but coverage leans on tool names rather than fully enumerated concrete actions, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (build pipelines, warehouses, streaming architectures; implement Spark/dbt/Airflow) and 'when' ('Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('data pipeline design', 'analytics infrastructure', 'modern data stack', 'data warehouses', 'real-time streaming') with good coverage, though a few common synonyms/extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear data-engineering niche with distinct triggers, but carries minor overlap risk with adjacent analytics/ML-engineering skills.	4 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/data-engineer/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.