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 strong progressive disclosure and largely executable examples, but it falls short on workflow clarity because batch/export operations include no validation or verification steps. Minor conciseness improvements are available.

Suggestions

Add explicit validation/verification checkpoints to batch and export workflows (e.g., after export_hdf5, reopen the file to confirm integrity; after delay=True aggregations, check that results resolved before using them) and a fix-and-retry loop, which would lift workflow_clarity above 3.

Trim the Overview's marketing language ('over a billion rows per second, enabling interactive data exploration') since it duplicates the description, and tighten the Best Practices list by merging near-duplicate items.

Replace the simplified df.plot1d/df.plot calls in the Quick Start with complete, runnable signatures (or note they are illustrative) so the actionability examples are fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with focused code examples and bullet-pointed capability sections, but the Overview repeats the description and includes minor marketing-style padding ('process over a billion rows per second, enabling interactive data exploration').	4 / 5
Actionability	The Quick Start Pattern and three Common Patterns provide mostly executable, copy-paste-ready Python code covering common cases, with only minor simplifications in the plotting calls.	4 / 5
Workflow Clarity	The Quick Start is a clear 7-step sequence, but batch and export operations (delay=True aggregations, CSV->HDF5 conversion, export_hdf5) lack any validation/verification checkpoints or error-recovery feedback loops, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	A clear overview points to six one-level-deep reference files, all of which exist and are substantive, with explicit per-section routing ('Reference references/X.md'), a 'Working with References' task-routing map, and a Resources list.	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 distinguishes the skill via the out-of-core/RAM-exceeding framing. It explicitly answers both 'what' and 'when' with concrete trigger phrases and file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets') with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers what ('processing and analyzing large tabular datasets that exceed available RAM' with enumerated capabilities) and when ('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').	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms ('large tabular datasets', 'big data', 'massive datasets') and explicit file extensions ('CSV/HDF5/Arrow/Parquet'), plus the RAM-exceeding framing users would naturally invoke.	5 / 5
Distinctiveness Conflict Risk	Clear niche (out-of-core, RAM-exceeding big data via Vaex) with distinct triggers that separate it from generic pandas/dataframe skills; third-person voice used throughout with no conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/vaex/SKILL.md
Commit: d5ae560

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.