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

77%

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/polars/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A code-heavy, highly actionable Polars reference whose examples are its main strength. It loses points for marketing-flavored padding, reference-style rather than validated workflow framing, and progressive-disclosure references that are signaled but missing from the bundle.

Suggestions

Trim the Overview and lazy-vs-eager exposition to assume Claude's familiarity with DataFrame concepts, and deduplicate the repeated select/filter examples to tighten conciseness.

Create the referenced bundle files (core_concepts.md, operations.md, io_guide.md, transformations.md, pandas_migration.md, best_practices.md) or remove the 'load references/...' pointers, since progressive disclosure only works when the deferred content is actually present.

Move the detailed per-operation API coverage that overlaps with the missing references out of SKILL.md so the main file is a true overview rather than an inline mirror of the reference docs.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight code examples, but the Overview ('lightning-fast', 'high-performance data manipulation capabilities') and the lazy/eager exposition restate library concepts Claude already knows, and several select/filter snippets are repeated across sections, so it is mostly efficient with padding to trim.	2 / 3
Actionability	Nearly every section is built from complete, copy-paste-ready Polars snippets (select, filter, with_columns, group_by, joins, I/O) with real column names, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The Best Practices section gives a numbered sequence, but the skill is reference-style API documentation rather than a multi-step process, and there are no validation/feedback checkpoints — acceptable for a library skill but it sits at the 'steps listed, checkpoints implicit' anchor.	2 / 3
Progressive Disclosure	References are clearly signaled one level deep ('load references/core_concepts.md') and listed in a Resources section, but the referenced files do not exist in the bundle and the body itself duplicates much of that deferred content inline, so structure is present but not cleanly split.	2 / 3
	Total	9 / 12 Passed

Description

90%

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, third-person description with an explicit 'Use when' trigger and good natural keywords. Its only gap is feature-oriented phrasing rather than enumerated concrete actions, which keeps specificity at the middle anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Fast in-memory DataFrame library') and use-cases ('ETL pipelines, faster pandas replacement') but lists features (lazy evaluation, parallel execution, Apache Arrow backend) rather than concrete user actions like filter/join/aggregate, so it stops short of the 'multiple specific concrete actions' anchor.	2 / 3
Completeness	Explicitly answers both what ('Fast in-memory DataFrame library for datasets that fit in RAM') and when ('Use when pandas is too slow but data still fits in memory'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Includes natural trigger terms a user would actually say — 'pandas is too slow', 'DataFrame', 'ETL pipelines', '1-100GB datasets' — plus comparison terms 'dask' and 'vaex' that aid routing, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche (in-RAM, pandas-replacement) and actively redirects larger-than-RAM workloads to 'dask or vaex', making conflict with sibling skills unlikely.	3 / 3
	Total	11 / 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: 6 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: about 1 hour 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.