This is the production debugging workflow for Agentforce agents. It queries session traces from Salesforce Data Cloud's STDM (Session Trace Data Model) to surface real user failures, then lets you reproduce issues locally with `sf agent preview` and edit the `.agent` file directly. The three-phase loop is observe, reproduce, improve. It auto-detects your agent name and file path, handles the CLI's known double-nesting bug on retrieve, and falls back to test suites plus local traces if STDM isn't activated in your org. Use this when you're chasing regressions or weird production behavior, not when you're drafting new agents or writing tests.
npx -y skills add forcedotcom/sf-skills --skill agentforce-observe --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