Tessl • The package manager for agent skills

SkillPublic

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

83%

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

65%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 bundle with excellent progressive disclosure and mostly executable guidance, but weakened by triple redundancy in how references are listed, a couple of inaccurate API calls, and a lack of validation checkpoints in batch-oriented workflows.

Suggestions

Consolidate the three separate reference listings (Core Capabilities bullet lists, 'Working with References', and 'Resources') into a single map of task type to reference file to remove systematic redundancy.

Add validation checkpoints to the Quick Start and CSV-conversion patterns, e.g. verify df.shape/columns after opening a large file and confirm the exported HDF5 file loads back correctly before moving on.

Fix inaccurate API usage: replace 'vaex.execute([mean_x, std_y, sum_z])' with 'df.execute(delayed=[mean_x, std_y, sum_z])' and verify 'df.stat()' exists or substitute the correct profiling call.

Dimension	Reasoning	Score
Conciseness	The six reference files are enumerated three separate times (Core Capabilities bullet lists, 'Working with References', and 'Resources'), and 'When to Use This Skill' repeats the frontmatter description. Content is mostly efficient — no padding with concepts Claude already knows — but the systematic redundancy should be consolidated.	3 / 5
Actionability	The Quick Start Pattern and Common Patterns are near copy-paste-ready executable code, but 'vaex.execute([mean_x, std_y, sum_z])' is not the real API (should be df.execute(delayed=[...])) and 'df.stat()' in Best Practices is not a documented Vaex method, leaving minor gaps in executability.	4 / 5
Workflow Clarity	The Quick Start Pattern provides a clear numbered 7-step sequence, but there are no validation checkpoints (e.g., verifying loaded shape or confirming export success), and large-data conversion/export is a batch operation — the rubric's batch-operations cap therefore holds workflow clarity at 3.	3 / 5
Progressive Disclosure	The body is a concise overview with six one-level-deep, well-signaled reference files (all verified to exist), each mapped to a task type in 'Working with References', making navigation easy and the content split appropriate.	5 / 5
	Total	15 / 20 Passed

Description

96%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 description: explicit what and when clauses, concrete capability lists, natural trigger phrasing with format names, and a clearly framed out-of-memory niche. The only weak point is mild overlap on generic large-file triggers with adjacent big-data libraries.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets' — plus named formats (CSV/HDF5/Arrow/Parquet), giving comprehensive coverage of the skill's capabilities rather than a partial list.	5 / 5
Completeness	It explicitly answers both what ('Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations...') and when ('Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasings are well covered with synonyms ('large tabular datasets', 'massive datasets', 'big data', 'do not fit in memory') alongside concrete file formats ('CSV/HDF5/Arrow/Parquet'), matching the comprehensive-with-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	The 'exceed available RAM' / out-of-core framing carves a mostly distinct niche, but generic triggers like 'work with large CSV... files' carry minor overlap risk with closely related DataFrame skills (pandas/Dask/polars).	4 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/data-engineering/vaex/SKILL.md
Revision: 6a85742

Reviewed: 22 days ago

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.

vaex

Table of Contents

Is this your skill?