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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/general/vaex/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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 and action-oriented but has real quality gaps: referenced documentation files do not exist, some code examples use non-existent Vaex API calls, workflows lack validation checkpoints, and reference listings are repeated redundantly. It sits at the mid-level on every content dimension.

Suggestions

Ship the six referenced files in references/ (core_dataframes.md, data_processing.md, performance.md, visualization.md, machine_learning.md, io_operations.md) or remove the navigation pointing to them, since progressive disclosure is currently broken.

Verify code examples against the real Vaex API, replacing 'vaex.execute([mean_x, std_y, sum_z])' and 'df.stat()' with valid calls (e.g. df.execute() with delayed objects) so snippets are copy-paste executable.

De-duplicate the reference file listing (it appears in Core Capabilities, Working with References, and Resources) and drop the description-repeating 'When to Use' section to tighten token usage.

Add at least one validation/checkpoint step (e.g. 'df.preview()' or shape/row-count verification) to the Quick Start workflow so the multi-step sequence has an explicit verification point.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and code-focused without explaining concepts Claude already knows, but the six reference files are listed three times (Core Capabilities, Working with References, and Resources) and the 'When to Use' list rehashes the description. This is the 'mostly efficient but could be tightened' anchor, not the fully lean level.	2 / 3
Actionability	Concrete code blocks are present throughout (vaex.open, virtual columns, groupby/agg, export), but several calls appear non-executable, e.g. 'vaex.execute([mean_x, std_y, sum_z])' and 'df.stat()', which do not match the real Vaex API. That lands at 'some concrete guidance but incomplete / missing key details' rather than copy-paste ready.	2 / 3
Workflow Clarity	The Quick Start Pattern gives a clear seven-step sequence (open, explore, virtual columns, filter, compute, visualize, export), but there are no validation checkpoints or error-recovery feedback loops anywhere. Per the anchors this is 'steps listed but validation gaps; checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	On paper the body is well-organized with clearly signaled one-level-deep references ('references/core_dataframes.md', etc.), but the references/ directory and all six referenced files are absent from the bundle, so the navigation leads nowhere. Scored against the actual (empty) bundle structure, this is broken disclosure rather than the clean anchor-3 case.	2 / 3
	Total	8 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, trigger-rich, and clearly states both what Vaex does and when to use it, with an explicit 'Apply when' clause and a distinctive memory-exceeding niche. It is among the strongest examples in the rubric's good_overall_examples set.

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', plus 'work with large CSV/HDF5/Arrow/Parquet files' and 'build ML pipelines'. This matches the score-3 anchor of enumerating several distinct concrete actions rather than a single vague verb.	3 / 3
Completeness	It states both what the skill does ('processing and analyzing large tabular datasets... out-of-core DataFrame operations...') and when to apply it with an explicit 'Apply when users need to work with large CSV/HDF5/Arrow/Parquet files...' clause. This satisfies the explicit-trigger requirement that would otherwise cap completeness at 2.	3 / 3
Trigger Term Quality	Covers natural user-facing terms such as 'large CSV/HDF5/Arrow/Parquet files', 'fast statistics on massive datasets', 'visualizations of big data', 'ML pipelines', and 'do not fit in memory'. These are phrases a user would naturally say, matching the good-coverage anchor rather than the jargon-only or partial-coverage levels.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to datasets 'that exceed available RAM' / 'billions of rows' / 'do not fit in memory', which distinguishes it from generic pandas/tabular skills. The trigger conditions are unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/vaex/SKILL.md
Commit: df37802

Reviewed: 7 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.