polars

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Quality

78%

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 ./bundled/skills/polars/SKILL.md

Quality

Content

86%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 a well-organized, executable reference with strong progressive disclosure pointing to real, one-level-deep reference files. It is lean and actionable, with only minor over-explanation in a few section introductions and no need for validation checkpoints given its non-destructive reference nature.

Suggestions

Trim a few explanatory intros (e.g., the 'Expressions are the fundamental building blocks...' paragraph) to pure pointers since Claude already understands these concepts.

Consider adding a brief note on validating output schema/types after complex joins or pivots to give the reference a light verification checkpoint without imposing a heavy workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code examples and tables with very little padding of concepts Claude already knows, but a few section intros ('Expressions are the fundamental building blocks of Polars operations...') are slightly over-explanatory, matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Provides extensive copy-paste-ready, executable code covering the common cases (DataFrame creation, filter, with_columns, group_by, joins, concat, pivot, window functions, I/O), matching the 'fully executable; specific examples cover common cases' anchor.	5 / 5
Workflow Clarity	This is a reference/lookup skill rather than a destructive multi-step process, so the validation-cap does not apply; per-operation guidance is unambiguous and the Best Practices section offers a clear sequenced performance list, though it lacks explicit validation checkpoints.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references ('For detailed concepts, load references/core_concepts.md') and all six referenced files exist and match the Resources listing, fitting the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	18 / 20 Passed

Description

71%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 well-constructed with a clear what-and-when structure, concrete capability claims, and explicit boundary guidance against larger-than-RAM tools. It would benefit from a few more natural file-format triggers (.csv, parquet, tabular data) to round out keyword coverage.

Suggestions

Add common file-format and synonym triggers (e.g., '.csv', 'parquet', 'tabular data', 'DataFrames') so users searching by format or term land on this skill.

Confirm the '1-100GB datasets' sizing claim is accurate and current, since outdated size guidance could mislead triggering.

Dimension	Reasoning	Score
Specificity	Names the domain ('Fast in-memory DataFrame library') and several concrete capabilities ('Lazy evaluation, parallel execution, Apache Arrow backend', 'ETL pipelines, faster pandas replacement') with only minor coverage gaps, matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both 'what' (in-memory DataFrame library with lazy evaluation, parallel execution, Arrow backend) and 'when' ('Use when pandas is too slow but data still fits in memory', 'Best for 1-100GB datasets, ETL pipelines', 'For larger-than-RAM data use dask or vaex') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('Use when pandas is too slow', 'ETL pipelines', 'faster pandas replacement', '1-100GB datasets') but is missing some common synonyms and file extensions like .csv, parquet, or 'tabular data', fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche via the RAM-fitting constraint and pandas-too-slow trigger, plus an explicit boundary ('For larger-than-RAM data use dask or vaex'), giving it distinct triggers and minimal conflict risk.	5 / 5
	Total	18 / 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/polars/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.