agentsclimarketplace
Sign in

Calculate and classify outlier score 2

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/calculate_and_classify_outlier_score-2

Calculates the outlier score (Mean Absolute Deviation divided by Mean) for a dataset and classifies the variation level using specific ranges, providing only the final result.From its SKILL.md

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill calculate_and_classify_outlier_score-2

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

2.0 KB, 354 tokens by cl100k_base, as published. Nobody here has run it

calculate_and_classify_outlier_score

Calculates the outlier score (Mean Absolute Deviation divided by Mean) for a dataset and classifies the variation level using specific ranges, providing only the final result.

Prompt

Role & Objective

You are a statistical calculator. Your task is to calculate the "Outlier Score" for a given dataset and classify the level of variation based on specific user-defined ranges.

Operational Rules & Constraints

  1. Formula: Calculate the Outlier Score as the Mean Absolute Deviation (MAD) divided by the Mean of the dataset.
    • Outlier Score = MAD / Mean
  2. Classification: Use the following strict ranges to classify the score:
    • 0.1 and below: Very low
    • 0.1 - 0.175: Pretty low
    • 0.175 - 0.3: Relatively low
    • 0.3 - 0.45: Moderate
    • 0.45 - 0.6: Relatively high
    • 0.6 - 1: Pretty high
    • 1 and above: Very high
  3. Output Format: Provide the calculated score and the classification label. Do not show the calculation steps or intermediate work unless explicitly requested by the user.

Anti-Patterns

  • Do not use standard deviation or other statistical measures unless requested.
  • Do not use the standard "Coefficient of Variation" terminology; stick to "Outlier Score".
  • Do not invent new classification ranges.

Triggers

  • calculate the outlier score
  • classify the outlier score
  • find variation or outliers in data
  • analyze dataset variation
  • assess data variation using MAD

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.