agentforce-observe

Analyze Agentforce session traces to diagnose routing failures and action errors.

Updated Jun 17, 2026
One-click install
npx skills add https://github.com/angryracoon/ARIEF-VISEO-DEV-ORG --skill agentforce-observe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentforce-observe
Source: https://github.com/angryracoon/ARIEF-VISEO-DEV-ORG/tree/main/.agents/skills/agentforce-observe
Command: npx skills add https://github.com/angryracoon/ARIEF-VISEO-DEV-ORG --skill agentforce-observe

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you diagnose why an Agentforce agent behaved incorrectly by analyzing production session traces, preview traces, routing decisions, action usage, and instruction adherence. It turns scattered telemetry into clear root causes for regressions, performance issues, and knowledge gaps.

Core Features & Use Cases

  • Production observability: Review STDM session data, conversation turns, tool calls, and quality signals from live orgs.
  • Local reproduction: Recreate suspected failures in preview sessions and inspect trace files for routing or grounding problems.
  • Root-cause analysis: Detect subagent misroutes, missing actions, wrong bindings, dead hubs, abandoned sessions, and LOW instruction adherence.
  • Fix guidance: Map symptoms back to the agent configuration and recommend targeted edits to the authoring bundle.
  • Use case: An AI product analyst can use this Skill to understand why an agent failed in production, confirm the issue in preview, and prepare the next fix.

Quick Start

Ask the skill to analyze an Agentforce agent’s recent session traces and summarize the main failures, root causes, and recommended fixes.

Frequently Asked Questions about agentforce-observe

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze Agentforce session traces to find routing failures?

Analyzing Agentforce session traces requires reviewing STDM Data Cloud production data and local preview files to identify subagent misroutes, action errors, and instruction adherence issues, turning scattered telemetry into clear root causes for agent regressions.

Why does my Agentforce agent return the wrong action or fail to ground responses?

Agentforce grounding and action failures often stem from dead hubs, wrong bindings, or missing actions. Root-cause analysis of conversation turns and tool calls maps these symptoms back to the agent configuration for targeted edits to the authoring bundle.

How can I reproduce Agentforce production issues in a local preview environment?

Reproduce Agentforce production issues locally by recreating suspected failures in preview sessions and inspecting local .agent retrieval trace files to detect routing decisions and grounding problems before applying fixes.

Do I need STDM Data Cloud access to debug Agentforce observability issues?

Yes, STDM Data Cloud access is required for production observability. You also need to deploy an Apex helper and perform local .agent retrieval to generate reproducible diagnostics and fix guidance for agent regressions.

What is the best way to diagnose low instruction adherence in an Agentforce agent?

Diagnosing low instruction adherence in Agentforce requires analyzing session traces for quality signals and conversation turns. This root-cause analysis detects abandoned sessions and maps symptoms back to the agent configuration for targeted fixes.

Agentforce routing analysis not working for subagent misroutes, what are the limitations?

Routing analysis limitations include dependencies on STDM Data Cloud access, Apex helper deployment, and local .agent retrieval. Without these prerequisites, generating reproducible diagnostics for subagent misroutes and dead hubs is not possible.