vaex

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Quality

86%

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

Quality

Content

72%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 with executable code and clean one-level-deep references, but it repeats the reference-file listing three times and lacks validation checkpoints in its batch/export workflows. Tightening redundancy and adding verification steps would lift the weaker dimensions.

Suggestions

Consolidate the reference-file listing into one section (e.g. keep only the Resources list or the Working with References map) to remove the triplicate enumeration and tighten conciseness.

Add an explicit validation step to the Quick Start and batch patterns, e.g. verify row count or dtypes after loading (`len(df)`, `df.column_names`) and confirm export output before relying on it.

Trim the redundant 'billion rows' phrasing in the Overview and drop bullets in Core Capabilities that merely restate the reference file's scope, linking directly instead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with good inline code, but the six reference files are listed three times (Core Capabilities bullets, Working with References, and Resources) and the Overview repeats 'billion rows', which could be tightened.	3 / 5
Actionability	Provides copy-paste-ready executable code in the Quick Start and three Common Patterns covering loading, virtual columns, aggregations, and export across the common cases.	5 / 5
Workflow Clarity	The Quick Start gives a clear 7-step sequence, but there are no validation/verification checkpoints for batch (delay=True) and export operations, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to six real, one-level-deep reference files with task-to-file navigation; bulk detail is appropriately split out and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

100%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 specific, comprehensive, and clearly answers both what the skill does and when to use it, with strong natural trigger terms and a distinctive big-data niche. No meaningful gaps or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (out-of-core DataFrame operations, lazy evaluation, fast aggregations, visualization, ML on large datasets) plus specific file formats, giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly states both what the skill does and when to apply it via a concrete 'Apply when users need to...' trigger clause with multiple listed scenarios.	5 / 5
Trigger Term Quality	Covers natural user phrases ('large tabular datasets', 'exceed available RAM', 'billions of rows', 'do not fit in memory') and explicit file extensions/formats (CSV/HDF5/Arrow/Parquet), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The out-of-core / exceeds-RAM / billions-of-rows niche is clearly distinct from in-memory pandas/polars skills, giving a clear trigger with minimal overlap risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/vaex/SKILL.md
Commit: 3a6c3a9

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.