agentsclimarketplace
Sign in

Kpi anomaly triage

Skill sisodiabhumca/agent-skills/skills/kpi-anomaly-triage

Vendor-neutral skill to analyze KPI time-series data, detect anomalies, and generate a triage summary with likely drivers.From its SKILL.md

Install
npx -y skills add sisodiabhumca/agent-skills --skill kpi-anomaly-triage

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

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.1 KB, 260 tokens by cl100k_base, as published. Nobody here has run it

When to invoke

  • When monitoring weekly/daily KPI dashboards for sudden changes.
  • When preparing an investigation checklist for metric movements.

Inputs needed

  • --input: Path to a CSV file with columns date (YYYY-MM-DD) and value.
  • Optional --window: Rolling window size in days (default 14).
  • Optional --z: Z-score threshold (default 3.0).
  • Optional --out: Path to write a JSON report.

Workflow

  1. Parse dates and values; sort by date.
  2. Compute rolling mean and standard deviation.
  3. Flag points with [ z = \frac{x - \mu}{\sigma} ] above threshold.
  4. Summarize recent anomalies and basic context (last 7 days trend).

Output format

JSON with:

  • anomalies: list of {date, value, z, mean, std}.
  • recent_summary: last value, 7d min/max, direction.

Guardrails

  • If standard deviation is zero, do not divide by zero; skip anomaly scoring.
  • Purely statistical heuristic; not a root cause analysis.

Reference code

  • kpi_anomaly_triage.py

What ships with it: 2 files

3.1 KB alongside SKILL.md, 1 of them executable

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.