whylabs-monitor

SkillMonitoring & ops

WhyLabs integration skill for ML observability, profile logging, and anomaly detection.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the whylabs-monitor skill

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/specializations/data-science-ml/skills/whylabs-monitor/SKILL.md and read by ahel’s review.

Overview

WhyLabs integration skill for ML observability, data profile logging, and anomaly detection in production ML systems.

Capabilities

  • Data profile generation (whylogs)
  • Profile upload to WhyLabs platform
  • Anomaly detection and alerts
  • Segment analysis for data subsets
  • Performance monitoring dashboards
  • Integration with ML pipelines
  • Historical profile comparison
  • Custom constraint validation

Target Processes

  • Model Performance Monitoring and Drift Detection
  • ML System Observability and Incident Response

Tools and Libraries

  • whylogs
  • WhyLabs Platform
  • pandas

Input Schema

{
  "type": "object",
  "required": ["action"],
  "properties": {
    "action": {
      "type": "string",
      "enum": ["profile", "upload", "compare", "validate", "alert-config"],
      "description": "WhyLabs action to perform"
    },
    "profileConfig": {
      "type": "object",
      "properties": {
        "dataPath": { "type": "string" },
        "datasetId": { "type": "string" },
        "segments": { "type": "array", "items": { "type": "string" } },
        "timestamp": { "type": "string" }
      }
    },
    "uploadConfig": {
      "type": "object",
      "properties": {
        "orgId": { "type": "string" },
        "modelId": { "type": "string" },
        "profilePath": { "type": "string" }
      }
    },
    "compareConfig": {
      "type": "object",
      "properties": {
        "baselineProfile": { "type": "string" },
        "targetProfile": { "type": "string" },
        "metrics": { "type": "array", "items": { "type": "string" } }
      }
    },
    "validationConfig": {
      "type": "object",
      "properties": {
        "constraints": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "column": { "type": "string" },
              "constraint": { "type": "string" },
              "value": { "type": "number" }
            }
          }
        }
      }
    }
  }
}

Output Schema

{
  "type": "object",
  "required": ["status", "action"],
  "properties": {
    "status": {
      "type": "string",
      "enum": ["success", "error", "warning"]
    },
    "action": {
      "type": "string"
    },
    "profilePath": {
      "type": "string"
    },
    "uploadId": {
      "type": "string"
    },
    "dashboardUrl": {
      "type": "string"
    },
    "comparison": {
      "type": "object",
      "properties": {
        "driftScore": { "type": "number" },
        "driftedFeatures": { "type": "array", "items": { "type": "string" } },
        "alerts": { "type": "array" }
      }
    },
    "validation": {
      "type": "object",
      "properties": {
        "passed": { "type": "boolean" },
        "failures": { "type": "array" }
      }
    }
  }
}

Usage Example

{
  kind: 'skill',
  title: 'Profile and upload production data',
  skill: {
    name: 'whylabs-monitor',
    context: {
      action: 'profile',
      profileConfig: {
        dataPath: 'data/production_batch.parquet',
        datasetId: 'fraud-detection',
        segments: ['region', 'customer_type'],
        timestamp: '2024-01-15T00:00:00Z'
      },
      uploadConfig: {
        orgId: 'org-123',
        modelId: 'model-fraud-v2'
      }
    }
  }
}

Signals

GitHub stars
2k
Forks
112
Last commit
Sep 2026
Advanced
Item type
skill
Key
whylabs-monitor
Source
github.com/a5c-ai/babysitter