CtrlK
BlogDocsLog inGet started
Tessl Logo

statistical-distribution-and-outlier-analysis

执行数值型数据的分布分析与异常值检测,支持通过正则表达式从文本中提取误差项并生成高分辨率的箱线图与直方图报告。

57

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-da-excel-workflow/capability/excel-data-visualization/histogram-visualization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The content is a self-contained, executable Python workflow with clear step sequencing and efficient code, but it lacks an overview section, external reference structure, and explicit validation checkpoints for its batch column-processing. It would score higher with a brief overview and verify-then-proceed steps.

Suggestions

Add explicit validation checkpoints (e.g., confirm the Excel file loaded and has numeric columns before plotting; assert extracted_errors is non-empty before histogram generation) to lift workflow_clarity above 3.

Add a short '## Overview' section summarizing the six-step pipeline and expected input format so the body is not a monolithic wall of code.

Parameterize the fragile assumptions ('input_data.xlsx' path and 'df.columns[0]' as the error-term column) with explicit configuration or detection guidance.

DimensionReasoningScore

Conciseness

The body is mostly lean code blocks with brief step headers and only minimal, useful inline comments, matching 'efficient; minor instances of over-explanation'; not a 5 because some comments restate the obvious (e.g., '设置中文字体,兼容不同环境').

4 / 5

Actionability

Provides fully executable, copy-paste-ready Python across all six steps covering the common cases; not a 5 because of minor gaps such as the hardcoded 'input_data.xlsx' path and the assumed 'df.columns[0]' target column for regex extraction.

4 / 5

Workflow Clarity

Six steps are clearly sequenced (load → box plots → IQR outlier detection → regex extraction → histogram → export) but validation checkpoints are only implicit (is_numeric_dtype skips, 'if extracted_errors'), and this batch operation over all columns lacks explicit verify-then-proceed steps, capping the score at 3.

3 / 5

Progressive Disclosure

Content is organized into six labeled step sections but is a monolithic inline code wall with no overview/summary section and no external references (the bundle directories are empty); this matches 'some structure but could be better organized', and the under-50-line exception does not apply.

3 / 5

Total

14

/

20

Passed

Description

66%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.

The description clearly states concrete capabilities using third-person voice and natural domain keywords, but it omits any explicit 'when to use' trigger guidance, which caps completeness at 3. It is a solid, specific description that would benefit from an added 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when analyzing numerical data distributions, detecting outliers, or extracting error terms from text') to raise completeness and trigger_term_quality.

Drop the filler phrase '高分辨率的' from the description to improve conciseness and specificity.

Include common synonyms or file extensions (e.g., .xlsx, 离群值, 误差分析) to broaden natural trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — '分布分析与异常值检测', '通过正则表达式从文本中提取误差项', '生成...箱线图与直方图报告' — which matches the 'several specific actions; minor gaps' anchor; not a 5 because '高分辨率' is filler and coverage is not fully comprehensive.

4 / 5

Completeness

The 'what' is clearly stated (distribution analysis, outlier detection, regex error extraction, report generation) but there is no 'Use when...' or equivalent trigger clause, so per the judging guidelines completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains natural domain terms a user would say (分布分析, 异常值检测, 箱线图, 直方图, 正则表达式, 误差项) giving good keyword coverage; not a 5 because it lacks synonyms/file-extension variants and there is no explicit trigger phrasing.

4 / 5

Distinctiveness Conflict Risk

The niche (numerical distribution analysis + outlier detection + regex error-term extraction + box plot/histogram reports) is mostly distinct with only minor overlap risk against general data-analysis skills; not a 5 because triggers are not explicitly stated.

4 / 5

Total

15

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenSenseNova/SenseNova-Skills
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.