Sf Ai Agentforce Testing

What it does

The Sf Ai Agentforce Testing skill facilitates formal testing of AI agents, focusing on multi-turn conversation validation, CLI Testing Center specifications, topic/action coverage analysis, and structured test-fix loops after publication. It supports both API-based (Agent Runtime API) and Salesforce's built-in Testing Center workflows to ensure agent quality and reliability. This skill is designed for debugging and quality assurance within AI agent development.

When to use it

• Validating multi-turn conversation flows and context preservation.
• Executing test specifications generated in YAML format using the CLI Testing Center.
• Performing regression testing or expanding coverage after an agent has been published/activated.
• Running API tests for complex scenarios involving topic routing, action invocation, guardrails, or escalation.
• Implementing a structured test-fix loop to address issues identified post-publish.

Key capabilities

• Multi-turn Agent Runtime API testing.
• CLI Testing Center workflow support.
• Topic/action coverage analysis.
• Test specification generation and execution.
• Support for smoke tests, regression testing, and bug reproduction.
• Pre-approved scripts located at ~/.claude/skills/sf-ai-agentforce-testing/hooks/scripts/.

Example prompts

• "Run a multi-turn API test to validate context preservation in the agent."
• "Execute the test specification for topic routing using the CLI Testing Center."
• "Perform a regression test after the recent agent update, focusing on action invocation."
• "Reproduce bug report #1234 using the Agentforce testing framework."

Tips & gotchas

• Testing should always occur after an agent has been deployed/published/activated.
• For conversation continuity, prioritize multi-turn API testing (Track A).
• Avoid using raw curl for OAuth token validation; utilize the provided credential tooling within the Agent Runtime API flow.