the-anomaly-alert
Installation
SKILL.md
The Anomaly Alert
Take a metric's recent history and flag which points are genuinely outside its normal range, using a stated method the user can check, not an impression of "that looks off."
Input integrity. Run the checks in
references/data-input-integrity.mdbefore computing anything, and report what they found. Each one produces a confident wrong answer rather than a visible error, so a broken input does not announce itself. A partial final period is the most common cause of a false anomaly. Never flag an incomplete bucket as a drop. Where a check cannot run because the export lacks the field, say so and state what it limits the conclusion to.
How to run
Ask the user for these inputs. If any are missing, ask before flagging anything.
- The metric and its history: the metric name and a series of values with their time periods (at least 8 periods; fewer than that is not enough to establish a normal range).
- Period granularity: daily, weekly, or monthly, since the definition of "normal fluctuation" differs by granularity.
- Direction that matters: does the user care about drops, spikes, or both (a spike in signups is good news; a spike in churn is not).