python-polars
Enforces Polars over Pandas for functional pipe-style data manipulation (like dplyr in R). Use when writing Python data processing code, data transformation pipelines, ETL workflows, or analytical queries—e.g., "process this CSV", "aggregate sales data", "filter and transform DataFrame", "group by and calculate metrics".
89
86%
Does it follow best practices?
Impact
92%
7.07xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly communicates its purpose (enforcing Polars over Pandas), provides rich context about the programming paradigm (functional pipe-style like dplyr), and includes comprehensive trigger terms with concrete user request examples. The description uses proper third-person voice and balances technical specificity with natural language triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'functional pipe-style data manipulation', 'data processing code', 'data transformation pipelines', 'ETL workflows', 'analytical queries', with specific examples like 'aggregate sales data', 'filter and transform DataFrame', 'group by and calculate metrics'. | 3 / 3 |
Completeness | Clearly answers both what ('Enforces Polars over Pandas for functional pipe-style data manipulation') and when ('Use when writing Python data processing code, data transformation pipelines, ETL workflows, or analytical queries') with explicit trigger examples. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'process this CSV', 'aggregate sales data', 'filter and transform DataFrame', 'group by and calculate metrics', 'ETL workflows', 'data processing', 'analytical queries'. These are phrases users naturally use when requesting data work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by specifying Polars over Pandas, functional pipe-style (like dplyr), and Python context. The specific library preference and paradigm creates a clear niche that wouldn't conflict with general Python or data skills. | 3 / 3 |
Total | 12 / 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 skill provides strong actionable guidance with excellent code examples and a well-organized structure with appropriate progressive disclosure. However, it's somewhat verbose with unnecessary persuasion language ('Authority', 'Social Proof', 'Commitment') that Claude doesn't need, and lacks validation/verification steps for data pipeline workflows.
Suggestions
Remove the 'Authority/Commitment/Social Proof' framing and reduce repetitive 'pandas is bad' messaging - Claude doesn't need persuasion, just instructions
Add validation checkpoints to the workflow, such as checking row counts after filters or verifying schema after transformations
Consider adding a brief error handling pattern for common pipeline failures (e.g., missing columns, type mismatches)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity like the 'Authority/Commitment/Social Proof' framing and repeated emphasis on 'pandas is bad'. The comparison tables are useful but the philosophical explanations could be trimmed since Claude understands functional programming concepts. | 2 / 3 |
Actionability | Provides fully executable code examples with clear pipe-style patterns, a comprehensive quick reference table mapping pandas to Polars operations, and concrete expression patterns that are copy-paste ready. | 3 / 3 |
Workflow Clarity | The main pipeline example shows clear sequencing with numbered comments, but lacks validation checkpoints. For data manipulation workflows, there's no guidance on verifying intermediate results or handling errors in the pipeline. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, a concise overview, and appropriately deferred detailed content to reference files (migration-patterns.md, anti-patterns.md, etc.) with clear descriptions of when to load each. | 3 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jjjermiah/dotagents
- Commit
b74de5e
- 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.