pandas-pro
Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation, missing value handling, groupby operations, or performance optimization.
Overall
score
61%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
72%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 description has excellent trigger term coverage and distinctiveness for pandas-related work, making it easy for Claude to identify when to use it. However, it lacks an explicit 'what this does' statement and relies entirely on 'Use when/Invoke for' clauses, which makes it incomplete. The actions mentioned are category-level rather than concrete specific operations.
Suggestions
Add an explicit capability statement before the trigger guidance, e.g., 'Performs data manipulation, transformation, and analysis using pandas DataFrames.'
Make actions more concrete by specifying operations like 'reshape data with pivot tables, join datasets on keys, resample time series data, fill or drop missing values'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (pandas DataFrames) and lists several actions (data cleaning, aggregation, merging, time series analysis, missing value handling, groupby operations), but these are category-level terms rather than concrete specific actions like 'fill missing values with interpolation' or 'merge datasets on common keys'. | 2 / 3 |
Completeness | The description starts with 'Use when...' which addresses the 'when' question, but the 'what does this do' is only implied through the trigger contexts. There's no explicit statement of capabilities like 'Performs data manipulation and analysis using pandas' before the trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'pandas', 'DataFrames', 'data cleaning', 'aggregation', 'merging', 'time series', 'missing value', 'groupby', 'performance optimization'. These cover common variations of how users discuss data manipulation tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly targets pandas/DataFrame work with specific technical terms (groupby, time series, DataFrame) that distinguish it from general data skills or other programming skills. The pandas-specific terminology creates a clear niche. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has good structural organization and progressive disclosure with clear references to detailed topic files. However, it critically lacks executable code examples, making it more of an abstract guideline document than an actionable skill. The MUST DO/MUST NOT DO lists are helpful constraints but would benefit from concrete code demonstrating the patterns.
Suggestions
Add executable code examples for key operations (e.g., vectorized filtering, proper .loc[] usage, method chaining pattern) in a Quick Start section
Replace abstract guidance like 'use vectorized operations instead of loops' with before/after code showing the anti-pattern and correct pattern
Add specific validation commands to the workflow (e.g., `df.info()`, `df.isna().sum()`, `df.dtypes`) rather than just 'validate results'
Remove or condense the 'Role Definition' section as it explains Claude's persona rather than providing actionable guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content like the 'Role Definition' section that explains what Claude should already understand, and the 'Knowledge Reference' section is a list of keywords rather than actionable content. | 2 / 3 |
Actionability | The skill lacks any concrete, executable code examples. It provides abstract guidance like 'use vectorized operations' and 'use method chaining' without showing actual pandas code that Claude could copy and execute. | 1 / 3 |
Workflow Clarity | The 5-step core workflow provides a reasonable sequence, but lacks specific validation checkpoints or feedback loops. Steps like 'Validate results' are vague without concrete commands or checks to perform. | 2 / 3 |
Progressive Disclosure | The skill has a clear structure with a reference table pointing to topic-specific files (one level deep), well-organized sections, and appropriate separation of concerns between overview and detailed references. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
Total | 12 / 16 Passed | |
- 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.