model-drift-detector

Model Drift Detector - Auto-activating skill for ML Deployment. Triggers on: model drift detector, model drift detector Part of the ML Deployment skill category.

1.02x

Quality

Does it follow best practices?

Impact

99%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/model-drift-detector/SKILL.md

Evaluation results

97%

Detecting Performance Degradation in a Production Credit Scoring Model

Statistical drift detection implementation

Criteria

Without context

With context

Statistical test usage

100%

Feature-level drift

100%

Prediction drift detection

100%

Structured JSON report

100%

Threshold-based decision

100%

Production-ready error handling

62%

Requirements file

100%

Runnable demo block

100%

Step-by-step structure

100%

Standard library choices

100%

Report completeness

100%

Without context: $0.4590 · 1m 57s · 25 turns · 26 in / 6,518 out tokens

With context: $0.7340 · 2m 38s · 35 turns · 293 in / 9,243 out tokens

100%

Building a Continuous Model Monitoring Pipeline for a Recommendation Engine

MLOps monitoring pipeline integration

Criteria

Without context

With context

CLI argument parsing

100%

JSONL monitoring log

100%

Non-zero exit on drift

100%

Prediction column drift

100%

Feature drift detection

100%

Statistical method used

100%

Timestamp in log entry

100%

Drift flag in log

100%

Requirements file

100%

README scheduling guidance

100%

Production-ready error handling

50%

100%

Configurable threshold

100%

Without context: $0.4690 · 2m 2s · 26 turns · 26 in / 6,980 out tokens

With context: $0.9249 · 3m 13s · 46 turns · 44 in / 11,668 out tokens

100%

Optimizing Drift Detection Configuration for a Healthcare Risk Model

Production drift configuration and validation

Criteria

Without context

With context

YAML config file

100%

Per-feature method config

100%

Per-feature threshold config

100%

Config validation at startup

100%

Statistical drift test

100%

validation_report.json produced

100%

Per-feature drift results

100%

Overall drift assessment

100%

Config-driven thresholds

100%

Requirements file

100%

Production code quality

100%

Without context: $0.3668 · 1m 40s · 22 turns · 22 in / 5,740 out tokens

With context: $0.7829 · 3m 5s · 35 turns · 348 in / 11,720 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 0ad6004

Evaluated: 14 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Detecting Performance Degradation in a Production Credit Scoring Model Building a Continuous Model Monitoring Pipeline for a Recommendation Engine Optimizing Drift Detection Configuration for a Healthcare Risk Model

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.