CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/data-engineering/polars/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-structured with abundant executable examples and clean progressive disclosure to six real reference files. Its weaknesses are mild conceptual over-explanation and the absence of explicit validation checkpoints for ETL/batch workflows.

Suggestions

Trim conceptual prose in the Overview and Expressions/Lazy-vs-Eager sections (e.g., remove 'Expressions are the fundamental building blocks...') to assume Claude's existing knowledge and improve conciseness.

Add an explicit validation/verification checkpoint in the Best Practices or Data I/O sections for ETL/batch workflows (e.g., verify row counts or schema before/after collect) to strengthen workflow clarity.

Replace the '(...)' placeholder examples (e.g., lf.filter(...).select(...).collect()) with concrete, runnable snippets so every example is fully copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient and code-forward, but the Overview and the Expressions/Lazy-vs-Eager sections explain concepts Claude already knows (e.g., 'Expressions are the fundamental building blocks...'), which could be tightened.

3 / 5

Actionability

Quotes executable, copy-paste-ready examples for DataFrame creation, select, filter, with_columns, group_by, joins, concat, pivot, and I/O — specific examples cover the common cases.

5 / 5

Workflow Clarity

Content is topically organized (Quick Start → Core Concepts → Operations → Best Practices) with a logical learning progression, but there are no explicit validation/checkpoint steps, which matters for ETL/batch contexts.

3 / 5

Progressive Disclosure

Body is a clear overview with well-signaled, one-level-deep references to six existing files (e.g., 'load references/core_concepts.md') plus a Resources section listing all of them with descriptions — easy to navigate.

5 / 5

Total

16

/

20

Passed

Description

87%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 strong: it concisely states what the skill does, when to use it, and where its boundaries lie with concrete trigger phrases and negative guidance. Minor room for more action-oriented verbs and a few more natural trigger synonyms.

DimensionReasoningScore

Specificity

Quotes 'Lazy evaluation, parallel execution, Apache Arrow backend', 'ETL pipelines, faster pandas replacement' — lists several specific capabilities/actions with only minor gaps, fitting just above the midpoint anchor.

4 / 5

Completeness

Clearly answers 'what' ('Fast in-memory DataFrame library...') and 'when' ('Use when pandas is too slow...', 'Best for 1-100GB datasets'), plus explicit negative boundary guidance ('For larger-than-RAM data use dask or vaex').

5 / 5

Trigger Term Quality

Quotes 'pandas is too slow', 'faster pandas replacement', 'ETL pipelines', 'dask or vaex' — good coverage of natural user phrases and synonyms, though a few common variations are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (in-memory DataFrames, 1-100GB, pandas replacement) with an explicit boundary steering larger-than-RAM workloads to dask/vaex, minimizing conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.