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.
84
81%
Does it follow best practices?
Impact
86%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates its niche as a fast in-memory DataFrame library positioned between pandas and distributed computing tools. It excels at trigger terms and completeness with explicit 'use when' guidance and boundary conditions. The main weakness is that it describes characteristics and properties rather than listing specific concrete actions the skill enables.
Suggestions
Add specific concrete actions like 'filter, join, aggregate, pivot, and transform DataFrames' to improve specificity beyond just describing library characteristics.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (DataFrame library, in-memory data processing) and mentions some capabilities (lazy evaluation, parallel execution, Apache Arrow backend, ETL pipelines), but doesn't list specific concrete actions like 'filter rows', 'join tables', 'aggregate columns'. The description is more about characteristics than actions. | 2 / 3 |
Completeness | Clearly answers both 'what' (fast 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', with explicit boundary guidance for when NOT to use it). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'pandas is too slow', 'DataFrame', 'ETL pipelines', 'faster pandas replacement', 'in-memory', 'Apache Arrow', 'dask', 'vaex', and dataset size ranges (1-100GB). These cover many natural ways a user might describe their need. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved niche: positioned specifically as a Polars-like tool between pandas (slower) and dask/vaex (larger-than-RAM). The size range (1-100GB), the 'faster pandas replacement' framing, and explicit boundary conditions make it highly distinguishable from other data processing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured Polars skill with excellent actionability and progressive disclosure. Its main weakness is verbosity—there's redundancy between Quick Start and Common Operations sections, and some explanatory prose that Claude doesn't need. The workflow clarity could be improved with an end-to-end ETL pipeline example showing validation steps.
Suggestions
Remove the duplicate select/filter/with_columns examples from Quick Start since they're covered more thoroughly in Common Operations, or consolidate into a single section.
Trim explanatory prose like 'Expressions are the fundamental building blocks of Polars operations' and 'Benefits of lazy evaluation' bullet list—Claude knows these concepts.
Add an end-to-end ETL pipeline workflow example with explicit validation checkpoints (e.g., schema validation after read, row count checks after joins/filters).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations Claude already knows (e.g., 'Expressions are the fundamental building blocks...', 'Benefits of lazy evaluation' list, explaining what Parquet/CSV/JSON are). The pandas migration table is useful but the surrounding prose could be tighter. Several sections repeat concepts (e.g., select/filter shown in Quick Start and again in Common Operations). | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout. Every operation is demonstrated with concrete Python code, specific method calls, and realistic examples. The pandas migration table with side-by-side comparisons is particularly actionable. | 3 / 3 |
Workflow Clarity | The skill covers individual operations well but lacks clear multi-step workflow sequences for common tasks like ETL pipelines. The best practices section lists tips but doesn't sequence them into a workflow. For a library focused on data pipelines, there's no end-to-end pipeline example with validation checkpoints (e.g., checking schema after read, validating row counts after joins). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The main file provides a clear overview with working examples for each topic, then consistently points to one-level-deep reference files (core_concepts.md, operations.md, pandas_migration.md, io_guide.md, transformations.md, best_practices.md). The Resources section provides a clear directory of all references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.