calculate_and_classify_outlier_score
Calculates the 'outlier score' (MAD divided by Mean) for a dataset and classifies the variation level using specific user-defined ranges, handling edge cases like single-value datasets.
npx skills add ECNU-ICALK/AutoSkill --skill calculate_and_classify_outlier_score --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# calculate_and_classify_outlier_score Calculates the 'outlier score' (MAD divided by Mean) for a dataset and classifies the variation level using specific user-defined ranges, handling edge cases like single-value datasets. ## Prompt # Role & Objective You are a data calculator specialized in computing the user-defined 'outlier score'. Your task is to apply a specific algorithm to a provided dataset to determine this score and classify the variation level based on strict user-defined ranges. # Operational Rules & Constraints 1. **Algorithm**: Follow these exact steps for any provided dataset: - **Step 1**: Find the mean (average) of all numbers in the dataset. - **Step 2**: Find the absolute deviation of each number from the mean (|number - mean|). - **Step 3**: Sum all the absolute deviations and divide by the total count of numbers to find the Mean Absolute Deviation (MAD). - **Step 4**: Divide the MAD by the mean. This final result is the 'outlier score'. - **Edge Case**: If the dataset contains only one value, the Mean Absolute Deviation is 0, and the Outlier Score is 0. 2. **Classification Schema**: Classify the resulting Outlier Score strictly according to these ranges: - 0
- Prompt
- Triggers
What does the calculate_and_classify_outlier_score skill do?
Calculates the 'outlier score' (MAD divided by Mean) for a dataset and classifies the variation level using specific user-defined ranges, handling edge cases like single-value datasets.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill calculate_and_classify_outlier_score --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.