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

82%

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

65%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 examples and excellent progressive disclosure via real reference files, but it is held back by redundant capability restatements and the absence of validation checkpoints in its workflows. Tightening the overlapping overview sections and adding a verify step to the conversion pattern would raise the weaker dimensions.

Suggestions

Consolidate the Overview, When to Use, and Core Capabilities sections into a single concise overview to remove repeated capability descriptions and improve conciseness.

Add an explicit validation/checkpoint step to the CSV-to-HDF5 conversion pattern (e.g., reopen and sanity-check the exported file) to strengthen workflow clarity for a batch conversion operation.

In the delay/batching Common Pattern, confirm the exact vaex API for executing deferred results and annotate it so the example is unambiguously executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean code blocks, but capability information is restated across the Overview, When to Use, and Core Capabilities sections (and again in Best Practices), which could be tightened into a single overview.	3 / 5
Actionability	Provides copy-paste-ready, executable code in the Quick Start Pattern and three Common Patterns (loading, filtering, aggregation, virtual columns, visualization, export, delay batching), with only minor API-specification gaps.	4 / 5
Workflow Clarity	The Quick Start Pattern is a clear numbered sequence (steps 1–7) but includes no validation or verification checkpoints, and the CSV→HDF5 conversion pattern proceeds without confirming the output is valid.	3 / 5
Progressive Disclosure	Clear overview with six well-signaled, one-level-deep references (references/core_dataframes.md, data_processing.md, performance.md, visualization.md, machine_learning.md, io_operations.md), all verified to exist, with a Resources section listing each for easy navigation.	5 / 5
	Total	15 / 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 strong across all dimensions: it states concrete capabilities, provides natural trigger terms with file extensions, explicitly covers both 'what' and 'when', and carves out a distinct out-of-core/big-data niche. It uses imperative rather than first/second-person voice, matching the good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets' — giving comprehensive coverage of the library's capabilities.	5 / 5
Completeness	Explicitly answers both what ('processing and analyzing large tabular datasets... out-of-core DataFrame operations, lazy evaluation...') and when ('Apply when users need to work with large CSV/HDF5/Arrow/Parquet files... or build ML pipelines that do not fit in memory') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural terms users would say ('large tabular datasets', 'billions of rows', 'fast statistics', 'ML pipelines') plus concrete file extensions 'CSV/HDF5/Arrow/Parquet files', including synonyms and format names.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — out-of-core processing of datasets exceeding RAM at billion-row scale — with triggers unlikely to fire for ordinary in-memory pandas/data work, minimizing conflict 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: 543b17f

Reviewed: 5 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.