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

83%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, highly actionable with executable code, and exemplifies one-level-deep progressive disclosure with real reference files. Its main weakness is the absence of explicit validation/checkpoint steps for risky batch and export operations on large datasets.

Suggestions

Add explicit validation checkpoints to the Quick Start and export workflows (e.g., verify row counts with `df.shape` before/after export, confirm HDF5 reload integrity) to satisfy the batch/destructive feedback-loop expectation.

Trim overlap between the description and the 'When to Use This Skill' bullet list to reduce redundant tokens.

Consolidate the duplicated reference listing in 'Core Capabilities' and the 'Resources' section, which describe the same six files twice.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-forward, but the 'When to Use' bullets overlap with the description and some prose reiterates capabilities Claude already knows about vaex; minor padding keeps it just below 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code throughout — Quick Start, CSV-to-HDF5 conversion, delay=True batching, virtual columns — covering the common cases with specific, runnable snippets.	5 / 5
Workflow Clarity	The Quick Start Pattern is a clear numbered 7-step sequence (open, explore, virtual columns, filter, stats, visualize, export), but it lacks explicit validation checkpoints for batch/destructive operations like export and groupby on massive data.	4 / 5
Progressive Disclosure	Clear overview with six well-signaled one-level-deep references (core_dataframes.md, data_processing.md, performance.md, visualization.md, machine_learning.md, io_operations.md) — all of which exist in the bundle — and a 'Working with References' navigation guide; content is appropriately split.	5 / 5
	Total	18 / 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.

The description is comprehensive, concrete, and clearly distinguishes vaex's out-of-core niche with strong what-and-when trigger guidance. It is slightly verbose and could trim some enumerated capabilities for tighter token efficiency.

Suggestions

Tighten the capability list — 'out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets' repeats 'large datasets'/'big data' redundancy that could be condensed.

Add a few colloquial trigger synonyms (e.g., 'datasets too big to fit in memory', 'massive CSV files') to broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization ... machine learning' — and concrete file formats (CSV/HDF5/Arrow/Parquet), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers 'what' ('processing and analyzing large tabular datasets ... out-of-core DataFrame operations, lazy evaluation ...') and 'when' with a concrete '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	Strong natural terms ('large tabular datasets', 'billions of rows', 'fast statistics', 'visualizations of big data', file extensions CSV/HDF5/Arrow/Parquet), but the phrasing leans somewhat technical and lacks a few colloquial synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — single-machine out-of-core analytics on datasets exceeding RAM via memory-mapped files — with distinct triggers (billions of rows, exceeds RAM, lazy evaluation) minimizing overlap with in-memory tools.	5 / 5
	Total	19 / 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: 1e5eeff

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.