Agentforce Observability helps you watch how your AI agents behave in the real world. You can pull session traces from Data Cloud to see what went wrong. Then you can replay those conversations in a safe preview to find the exact issue. Finally you can edit the agent file and publish the fix. This skill is built for anyone who runs Agentforce agents and wants to keep them working well.
You do not need to be a developer to use it. The tool guides you step by step through observing, reproducing, and improving your agents. It works with your existing Salesforce org and agent files. You will get clear data on failures, regressions, and performance so you can act fast.
Global
mkdir -p ~/.claude/skills/observing-agentforceProject
mkdir -p .claude/skills/observing-agentforceSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Skill Creatoranthropics/skills
Create, test, and improve AI agent skills with easy step-by-step guidance
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly
Openclaw Secure Linux Cloudxixu-me/skills
Secure self-hosting of OpenClaw with private control and SSH tunneling