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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

86%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.

A well-structured body with executable, copy-paste-ready code patterns and a clean reference table backed by real bundle files. The main improvement areas are trimming minor redundant prose and adding an explicit error-recovery feedback loop to the workflow.

Suggestions

Trim the opening sentence ('Expert pandas developer specializing in…') since it duplicates the frontmatter description, and fold Output Templates into the Constraints section to remove overlap.

Add an explicit feedback loop to the Core Workflow validation step, e.g. 'If asserts fail: diagnose via the failing check, fix the transform, and re-run validation before optimizing.'

Consider noting file-format triggers (CSV/Parquet/Excel I/O) in the description or a reference to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Conciseness	Mostly lean with code patterns that earn their place, but the opening line ('Expert pandas developer specializing in…') restates the description and the Output Templates section partially restates the Constraints — minor trimmable padding rather than the every-token-counts ideal of a 5.	4 / 5
Actionability	Eight copy-paste-ready, executable pandas patterns (groupby agg, merge with validate, ffill+interpolate, resample, pivot_table, memory downcasting) cover the common cases, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	A clear 5-step sequence (Assess → Design → Implement → Validate → Optimize) with an explicit validation checkpoint (asserts on shape/nulls/columns), but it lacks the error-recovery feedback loop that distinguishes the 5 anchor; the destructive/batch cap of 3 does not apply because validation is present.	4 / 5
Progressive Disclosure	Reference Guide table signals five one-level-deep references with a 'Load When' column, all verified present in ./references/, with quick patterns kept inline — clean navigation matching the 5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

92%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 highly specific, third-person description that clearly states what the skill does and when to invoke it, with concrete trigger phrases and a well-scoped pandas niche. The only gap is the absence of file-format synonyms that would push trigger-term quality to the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, performance optimization' — giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	Explicitly answers both — 'Performs pandas DataFrame operations…' (what) and 'Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis' (when) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms (groupby, pivot, merge, forward-fill, resampling) but stops short of the 5 anchor: file-format synonyms (CSV/Parquet/Excel) and 'data wrangling' (present only in metadata triggers) are absent.	4 / 5
Distinctiveness Conflict Risk	Clear pandas niche with distinctive triggers (groupby, pivot, resample, forward-fill) and minimal conflict risk; not the broad-overlap case of a 4.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jeffallan/claude-skills
Path: skills/pandas-pro/SKILL.md
Commit: 882ef55

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.