pandas-pro
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 a strong skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms that users would naturally use, explicit 'Use when' and 'Invoke for' clauses, and a clear niche focused on pandas DataFrame operations that distinguishes it from other data-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, and performance optimization of large datasets. | 3 / 3 |
Completeness | Clearly answers both 'what' (pandas DataFrame operations for data analysis, manipulation, and transformation) and 'when' (explicit 'Use when' clause covering DataFrames, data cleaning, aggregation, merging, time series, plus an 'Invoke for' clause with detailed trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'pandas', 'DataFrame', 'data cleaning', 'aggregation', 'merging', 'time series', 'joining', 'pivoting', 'NaN values', 'forward-fill', 'groupby', 'type conversion'. These are terms a user working with pandas would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to pandas DataFrame operations specifically, with distinct triggers like 'pandas', 'DataFrame', 'groupby', 'forward-fill', 'resampling time series' that are unlikely to conflict with general data or spreadsheet skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with excellent executable code examples covering the key pandas operations described in the skill description. The workflow is well-sequenced with validation checkpoints. Main weaknesses are that the referenced bundle files don't exist (or weren't provided), and some inline content could be more concise or delegated to the reference files to better leverage progressive disclosure.
Suggestions
Provide the referenced bundle files (references/dataframe-operations.md, etc.) so the progressive disclosure structure actually functions, and move some of the longer inline code patterns into those files.
Trim the constraints section to only non-obvious items — Claude already knows not to use deprecated methods or convert to Python lists unnecessarily.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code examples, but includes some unnecessary framing ('Expert pandas developer specializing in...') and the output templates section is somewhat generic. The constraints section has items Claude already knows (e.g., don't use deprecated methods, don't iterate with iterrows), though presenting them as explicit constraints is reasonable. | 2 / 3 |
Actionability | Excellent executable code examples throughout — vectorized operations, groupby aggregation, merge with validation, missing value handling, time series resampling, pivot tables, and memory optimization are all copy-paste ready with clear before/after patterns. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced (assess → design → implement → validate → optimize) with explicit validation steps including assertion examples. The merge pattern includes indicator-based validation for unmatched rows, and the workflow includes feedback loops for data quality checking. | 3 / 3 |
Progressive Disclosure | The reference table pointing to topic-specific files (references/dataframe-operations.md, etc.) is well-structured with clear 'Load When' guidance, but no bundle files were provided, meaning these references don't actually resolve. The main file also includes substantial inline code patterns that could arguably live in the referenced files. | 2 / 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
- jeffallan/claude-skills
- Commit
e8be415
- 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.