Agentforce D360 Analyze

When you need to reconstruct what happened in an Agentforce session, this pulls the complete audit trail from Data Cloud's standardized data model: every step, message, LLM generation, and gateway call, assembled into a timestamped hierarchy. It handles session discovery if you only remember "yesterday afternoon" or "the one that escalated," then runs a three-stage pipeline that takes roughly 10 to 30 seconds for a typical conversation. The honest limitation is right in the docs: Data Cloud shows you what ran, not what was eligible to run, so if you're debugging why a topic didn't fire or an action wasn't offered, you'll still need the runtime planner telemetry that lives outside this surface.

skills.sh installs: 5.4K
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add forcedotcom/sf-skills --skill agentforce-d360-analyze --agent claude-code

Installs into .claude/skills of the current project.

Files

agentforce-d360-analyze — Data Cloud 360° session view

Hierarchical session reconstruction from Data Cloud STDM + GenAI DMOs for one Agentforce session. Three stages — fetch → assemble → render. Typical wall-clock: ~10–30s for a ~15-turn session.

The pipeline is DC-only: it reads runtime audit rows that Data Cloud has materialized. It is not a runtime-availability tool — see "DC-only blind spot" below for what this skill cannot answer.

If the user hasn't given enough to proceed

When invoked with no session id AND no discovery criteria, print this block verbatim — do not paraphrase, do not pre-run any script. Trigger condition: the input is empty OR contains no session-id shape (neither a UUID nor a 0Mw… messaging id) AND no discovery expression (no time phrase / --agent / --channel / --outcome / --grep / verbs like "find" / "list").

SKILL.md on GitHub