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.
npx -y skills add forcedotcom/sf-skills --skill agentforce-d360-analyze --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills