forcedotcom avatar

Observing Agentforce

This is the monitoring and debugging counterpart to agent development. It queries Salesforce Data Cloud's Session Trace Data Model to pull real production conversation logs, then lets you reproduce issues locally with `sf agent preview` and fix them by editing the .agent file directly. The workflow is observe, reproduce, improve. If your org doesn't have STDM enabled, it falls back to running test suites and analyzing local traces instead. The skill resolves agent names against the org metadata, handles the double-nesting bug in `sf project retrieve`, and walks you through the three-phase loop. Use this when production agents are misbehaving and you need actual session data to figure out why, not when you're writing new agents from scratch.

skills.sh installs
3.6K
GitHub stars
1.2K
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

This is the monitoring and debugging counterpart to agent development. It queries Salesforce Data Cloud's Session Trace Data Model to pull real production conversation logs, then lets you reproduce issues locally with `sf agent preview` and fix them by editing the .agent file directly. The workflow is observe, reproduce, improve. If your org doesn't have STDM enabled, it falls back to running test suites and analyzing local traces instead. The skill resolves agent names against the org metadata, handles the double-nesting bug in `sf project retrieve`, and walks you through the three-phase loop. Use this when production agents are misbehaving and you need actual session data to figure out why, not when you're writing new agents from scratch.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/forcedotcom/sf-skills
Categories
Testing & QA, Git & Pull Requests, AI & Agent Building, Debugging, Cloud & Infrastructure
First seen
Jun 3, 2026

More from forcedotcom/sf-skills

All 158
1wondelai avatarworking-with-legacy-codewondelai/skillsSafely change and test untested codebases using Feathers' "Working Effectively with Legacy Code". Use when the user mentions "legacy code", "no tests", "unteste3.6Kskills.sh installs
2giuseppe-trisciuoglio avatarwiremock-standalone-dockergiuseppe-trisciuoglio/developer-kitProvides patterns and configurations for running WireMock as a standalone Docker container. Generates mock HTTP endpoints, creates stub mappings for testing, va3.5Kskills.sh installs
3giuseppe-trisciuoglio avataraws-cdkgiuseppe-trisciuoglio/developer-kitProvides AWS CDK TypeScript patterns for defining, validating, and deploying AWS infrastructure as code. Use when creating CDK apps, stacks, and reusable constr3.5Kskills.sh installs
4pytorch avatarpr-reviewpytorch/pytorchReview PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, o3.3Kskills.sh installs
5web-infra-dev avatarios-device-automationweb-infra-dev/midscene-skillsVision-driven iOS device automation using Midscene CLI. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visi3.2Kskills.sh installs
6mksglu avatarcontext-modemksglu/context-modeUse context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process3Kskills.sh installs