sf-ai-agentforce-observability

Community

Scale Agentforce tracing: extract, analyze, and debug.

Authorronitnuguru
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Agentforce session tracing data is large and complex; this Skill enables scalable extraction and analysis from Salesforce Data Cloud to support debugging and performance insights.

Core Features & Use Cases

  • Extract STDM data (sessions, interactions, steps, messages) to Parquet for efficient storage and analysis.
  • Analyze traces with Polars to detect patterns, bottlenecks, and escalation paths across agents.
  • Use cases include debugging sessions, performance optimization, and compliance auditing for data-trace workflows.

Quick Start

Run the stdm-extract CLI to pull recent sessions and then analyze results with the STDMAnalyzer in Python.

Dependency Matrix

Required Modules

httpxpyarrowpyjwtcryptographypolarsrichclickpydantic

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sf-ai-agentforce-observability
Download link: https://github.com/ronitnuguru/Package-Visualizer/archive/main.zip#sf-ai-agentforce-observability

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.