CtrlK
BlogDocsLog inGet started
Tessl Logo

cost-anomaly-detection

Use when proactively scanning for cost anomalies, unusual spending, unexpected charges, or irregular patterns — during weekly reviews, after incidents, or when something looks off

63

1.25x
Quality

44%

Does it follow best practices?

Impact

100%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/cost-analyst/skills/cost-anomaly-detection/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

Cloud Cost Anomaly Analysis — Engineering Infrastructure Account

Math-in-code compliance

Criteria
Without context
With context

Mean calculated in code

100%

100%

Std dev in code

100%

100%

2-sigma threshold applied

100%

100%

Percentage change in code

100%

100%

Z-score computed in code

100%

100%

Permitted stdlib only

100%

100%

Data bound to variables

100%

100%

Rate-of-change in code

100%

100%

Anomaly count from code

100%

100%

Script executed or shown

100%

100%

100%

56%

Multi-Service Cost Anomaly Review — Q1 Infrastructure Audit

Complete report format compliance

Criteria
Without context
With context

Executive Summary fields

33%

100%

Anomaly type taxonomy

90%

100%

Severity classification present

87%

100%

Detailed anomaly entry format

20%

100%

Anomaly Dashboard — category table

0%

100%

Anomaly Dashboard — dimension table

0%

100%

False Positive Assessment

0%

100%

Baseline Comparison statistical analysis

70%

100%

Action Plan three-part structure

50%

100%

Deviation in std devs stated

100%

100%

100%

4%

Urgent Cost Review — Suspicious Spending Patterns Detected

Security and waste indicator detection

Criteria
Without context
With context

Security indicators identified

100%

100%

Waste patterns identified

100%

100%

50% account threshold applied

60%

100%

Security section separate

100%

100%

Waste section separate

100%

100%

Unusual region flagged

100%

100%

Security action recommended

100%

100%

Waste savings quantified in code

100%

100%

Misconfiguration pattern checked

100%

100%

High severity for security

100%

100%

Repository
Cloudzero/cloudzero-claude-marketplace
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.