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

38%

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/antigravity-bundle-data-engineering/skills/data-engineer/SKILL.md

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

Quality

Content

10%Scale 1-5

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

This skill reads as a comprehensive resume or capability catalog rather than actionable instructions for Claude. It extensively lists technologies and concepts Claude already knows without providing any executable code, concrete examples, or specific implementation guidance. The content is severely bloated (~300+ lines) while delivering almost no actionable value that Claude couldn't derive from its training data.

Suggestions

Replace the massive 'Capabilities' technology listings with 2-3 concrete, executable code examples for the most common tasks (e.g., a Spark pipeline, a dbt model, an Airflow DAG).

Add specific validation and verification steps to the workflow, such as data quality checks with Great Expectations code snippets and pipeline health monitoring commands.

Remove 'Behavioral Traits', 'Knowledge Base', and 'Example Interactions' sections entirely — these describe Claude's persona rather than providing actionable instructions.

Split detailed cloud-specific guidance (AWS/Azure/GCP stacks) into separate reference files and keep only a concise overview with links in the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of technologies Claude already knows about. The 'Capabilities' section is a massive enumeration of tools and services (200+ lines) that reads like a resume rather than actionable instructions. 'Behavioral Traits', 'Knowledge Base', and 'Example Interactions' sections add significant padding with no instructional value.	1 / 5
Actionability	Contains zero executable code, no concrete commands, no specific examples with inputs/outputs, and no copy-paste ready snippets. The entire skill is abstract descriptions and technology listings. The 'Instructions' section is four vague bullet points with no concrete guidance on how to actually implement anything.	1 / 5
Workflow Clarity	The 'Instructions' and 'Response Approach' sections provide rough sequences but are extremely high-level with no specific steps, no validation checkpoints, and no error recovery. For a skill involving data pipelines (which are multi-step, potentially destructive batch operations), the absence of any concrete validation steps is a significant gap.	2 / 5
Progressive Disclosure	All content is inlined in a single monolithic file with no references to supporting files. The massive technology listings across 12+ subsections should be split into separate reference files. There are no bundle files to support the content, and no navigation structure to help find relevant sections.	2 / 5
	Total	6 / 20 Passed

Description

66%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 effectively communicates the data engineering domain with specific technologies and architecture patterns, making it reasonably distinctive. However, it lacks a 'Use when...' clause which limits Claude's ability to know exactly when to select this skill, and could benefit from additional trigger terms covering common synonyms like ETL/ELT.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks about ETL/ELT pipelines, data warehouse design, streaming data, workflow orchestration, or mentions tools like Spark, dbt, or Airflow.'

Include additional natural trigger terms such as 'ETL', 'ELT', 'Kafka', 'data lake', 'batch processing', 'DAG', and 'data transformation' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific actions and technologies (data pipelines, data warehouses, streaming architectures, Spark, dbt, Airflow, cloud-native platforms), though it could be more granular about what specific operations are performed with each tool.	4 / 5
Completeness	Has a clear 'what' (build pipelines, warehouses, streaming architectures using specific tools) but completely lacks a 'when' clause. There is no explicit guidance on when Claude should select this skill.	3 / 5
Trigger Term Quality	Includes good natural keywords like 'data pipelines', 'data warehouses', 'streaming', 'Spark', 'dbt', 'Airflow', and 'cloud-native'. Missing some common variations like 'ETL', 'ELT', 'Kafka', 'data lake', 'batch processing', or 'DAG'.	4 / 5
Distinctiveness Conflict Risk	The combination of data engineering-specific tools (Spark, dbt, Airflow) and architecture types (pipelines, warehouses, streaming) creates a fairly distinct niche, though there could be minor overlap with general cloud infrastructure or database skills.	4 / 5
	Total	15 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/antigravity-bundle-data-engineering/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.