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

80%

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.

Well-structured, actionable content that uses progressive disclosure effectively with verified reference files. The main weakness is the absence of validation/verification checkpoints in batch and export workflows, which caps workflow clarity.

Suggestions

Add explicit verification checkpoints to the export and batch workflows (e.g., after df.export_hdf5, check df.nbytes/row count of the re-opened file; after delay=True + vaex.execute, confirm results are materialized).

Trim the marketing-style Overview sentence ('process over a billion rows per second, enabling interactive data exploration...') and consolidate version notes into a dedicated compatibility/deprecated section to reduce padding.

Provide a short error-recovery note for the large-CSV-to-HDF5 pattern (e.g., what to do if conversion is interrupted or the file is larger than disk).

Dimension	Reasoning	Score
Conciseness	Efficient overall — annotated Quick Start, tight Common Patterns, and useful non-fluff guidance — with only minor trimmable bits such as the marketing-style 'process over a billion rows per second' line and version notes that pad the Overview.	4 / 5
Actionability	Quick Start and Common Patterns provide concrete, copy-paste-ready Python covering common cases (CSV→HDF5 conversion, delay=True batching, virtual columns), with only minor gaps where some capability sections are descriptive lists rather than executable guidance.	4 / 5
Workflow Clarity	The 7-step Quick Start is a clear sequence, but batch/export operations like df.export_hdf5, large-CSV conversion, and delay=True execution have no validation or verification checkpoints or error-recovery loops, so the batch-operation cap of 3 applies.	3 / 5
Progressive Disclosure	Clean overview body with six capability sections each explicitly pointing to one real references/ file (all six files present), plus a 'Working with References' routing guide and a Resources list — well-signaled, one-level-deep navigation matching anchor 5.	5 / 5
	Total	16 / 20 Passed

Description

88%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.

A strong, third-person description that states concrete capabilities and provides an explicit 'Apply when...' trigger clause with file-format keywords. Trigger-term naturalness and synonym breadth are the main areas keeping it from a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across the library's surface — 'out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning' plus 'work with large CSV/HDF5/Arrow/Parquet files ... fast statistics ... visualizations ... ML pipelines' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (out-of-core processing/analysis of RAM-exceeding tabular data, aggregations, viz, ML) and 'when' via the concrete trigger clause 'Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics ..., create visualizations of big data, or build ML pipelines that do not fit in memory'.	5 / 5
Trigger Term Quality	Good natural-term coverage including format synonyms ('large CSV/HDF5/Arrow/Parquet files', 'billions of rows', 'big data'), but leans technical ('out-of-core', 'lazy evaluation') and is short on plain synonym variations, so it is not quite the comprehensive coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche — RAM-exceeding out-of-core tabular analytics with file-format triggers — distinct from general in-RAM DataFrame skills, with only minor overlap risk on the broad 'large tabular datasets' framing.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/vaex/SKILL.md
Commit: b2a92ba

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.