This handles the full testing lifecycle for Agentforce agents, from quick smoke tests during development to batch regression suites for CI/CD. It auto-derives test cases from your agent definitions, runs them through preview or the Testing Center, then digs into trace files to diagnose failures like missed topic routing or ungrounded responses. The iterative fix loop is solid: it tells you exactly where to edit (which subagent description, which action guard) based on trace analysis. Always runs safety probes and gives you an explicit SAFE/UNSAFE/NEEDS_REVIEW verdict before you ship. Use Mode A for quick iteration, Mode B when you need persistent test suites.
npx -y skills add forcedotcom/sf-skills --skill agentforce-test --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
wshobson/agents
github/awesome-copilot