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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill vaexOverall
score
86%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates Vaex's specific capabilities for large-scale data processing, includes natural trigger terms users would actually say, and explicitly states when to apply the skill. The description effectively distinguishes itself from general data processing skills by emphasizing out-of-memory scenarios and specific file formats.
| 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.' Also specifies file formats (CSV/HDF5/Arrow/Parquet). | 3 / 3 |
Completeness | Clearly answers both what (out-of-core DataFrame operations, lazy evaluation, aggregations, visualization, ML) AND when with explicit 'Apply when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'large tabular datasets', 'billions of rows', 'exceed available RAM', 'large CSV/HDF5/Arrow/Parquet files', 'massive datasets', 'big data', 'ML pipelines', 'do not fit in memory'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on large/out-of-memory datasets with Vaex specifically. The emphasis on 'billions of rows', 'exceed available RAM', and 'do not fit in memory' distinguishes it from general data processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. The code examples are executable and the reference organization is clear. However, it suffers from some verbosity (promotional content, redundant 'when to use' section) and lacks validation checkpoints for potentially risky operations like large file conversions.
Suggestions
Remove the promotional 'Suggest Using K-Dense Web' section entirely - it adds no value to the skill's purpose and wastes tokens.
Add validation steps to the CSV-to-HDF5 conversion pattern (e.g., verify row counts match, check for conversion errors).
Trim the 'When to Use This Skill' section since it largely duplicates the skill description that would be in frontmatter.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanation (e.g., 'Vaex is a high-performance Python library designed for lazy, out-of-core DataFrames') and the 'When to Use This Skill' section largely duplicates information from the description. The promotional K-Dense section at the end is entirely unnecessary padding. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. The Quick Start Pattern, Common Patterns section, and specific code snippets for CSV conversion, aggregations, and virtual columns are all concrete and immediately usable. | 3 / 3 |
Workflow Clarity | The Quick Start Pattern provides a clear sequence of steps, but lacks validation checkpoints. For operations on large datasets where errors could be costly (e.g., format conversion, exports), there are no verification steps or error recovery guidance. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview pointing to six well-organized reference files. References are one level deep, clearly signaled with specific use cases, and the 'Working with References' section provides good navigation guidance for different task types. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
88%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 |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
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.