Agentforce Test

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.

skills.sh installs: 5.8K
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

ADLC Test

Automated testing for Agentforce agents with smoke tests, batch execution, and iterative fix loops.

Overview

This skill provides comprehensive testing capabilities for Agentforce agents, including automated utterance derivation from agent subagents, preview-based smoke testing, trace analysis, an iterative fix loop for identified issues, and security testing (OWASP LLM Top 10). It bridges the gap between initial development and production deployment.

Security testing is part of the ADLC, not a separate skill. Functional correctness (right topic, right action) and security posture (resists attacks) are two dimensions of the same test suite. Treat adversarial coverage as part of the test flow and the Agent Spec — when you plan tests for an agent, plan its security tests too. Security test-case generation is gated on explicit user confirmation (see Mode C).