CtrlK
BlogDocsLog inGet started
Tessl Logo

polars

High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.

64

Quality

76%

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 ./skills/polars/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 highly actionable with comprehensive executable code and well-signaled one-level-deep references to real bundle files. It is held back by some redundant explanatory prose, missing validation feedback loops for batch/ETL operations, and inline sections that duplicate their reference counterparts.

Suggestions

Trim the Overview paragraph and the 'Expressions are the fundamental building blocks...' explanation to remove concepts Claude already knows, tightening conciseness toward a 4-5.

Add an explicit validate→fix→retry checkpoint (e.g. 'verify schema with df.schema before writing' or 'confirm row counts after a migration') to the Best Practices or pandas-migration flow so batch operations have a feedback loop.

Reduce inline detail in Common Operations, Aggregations, and Transformations to quick examples and defer the bulk to their corresponding references, sharpening the progressive-disclosure split.

DimensionReasoningScore

Conciseness

Mostly efficient with dense code examples, but includes some unnecessary explanation Claude already knows — the Overview paragraph restates the description, and 'Expressions are the fundamental building blocks... They describe transformations on data and can be composed, reused, and optimized' explains a basic concept.

3 / 5

Actionability

Abundant copy-paste-ready, executable code covering creation, select, filter, with_columns, group_by, window functions, I/O, joins, concat, pivot, and pandas mappings — specific examples cover the common cases comprehensively.

5 / 5

Workflow Clarity

The numbered Best Practices list gives a rough sequence but lacks validation checkpoints, and for a skill covering ETL/batch and pandas-migration operations the absence of explicit verify-validate-retry feedback loops caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Each topic section ends with a clearly signaled one-level-deep reference (e.g. 'load `references/operations.md`') and a Resources section enumerates all six real reference files; however, several sections (Common Operations, Aggregations, Transformations) carry fairly detailed inline content that overlaps its dedicated reference file, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

83%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, specific description that clearly states both what the skill does and when to use it, with rich concrete capabilities and a distinct niche. The main gap is trigger phrasing tied to natural user utterances rather than feature lists.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'Python ETL, analytics, and pandas migration', 'expression-based data manipulation', 'lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution' — giving comprehensive coverage of what the library does.

5 / 5

Completeness

Explicit 'Use for...' clause provides equivalent trigger guidance (so not capped at 3), and the 'what' is clearly stated as a high-performance DataFrame library; the 'when' lists capabilities rather than concrete user-facing trigger phrases, keeping it just below a 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('DataFrame', 'pandas migration', 'ETL', 'analytics'), but missing common variations a user might say such as 'dataframes', 'data processing', or 'query optimization' as standalone trigger phrases.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Polars DataFrame library with pandas-migration framing, lazy execution, Arrow/GPU) with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.