Testing Agentforce
forcedotcom/afv-libraryTesting your AI agent is a key step before launching it to users. This skill helps you write and run structured tests for Agentforce agents. You can do quick smoke tests during development using sf agent preview. You can also build full regression suites for your team using sf agent test commands.
The skill supports two main testing modes. Mode A is for ad-hoc preview testing without deploying a test suite. It is best for quick checks and iterative fixes. Mode B uses persistent test suites deployed to your org. This is great for regression testing and CI/CD integration.
You can also test individual Flow or Apex actions directly via REST API. This makes it easy to debug isolated pieces of your agent. The skill helps you interpret results and find failures quickly.
Add Testing Agentforce skill to your workflow
Global
mkdir -p ~/.claude/skills/testing-agentforceProject
mkdir -p .claude/skills/testing-agentforceSource Repository
More Testing & QA Claude Code Skills
Grill Memattpocock/skills
Stress-test your plan with relentless questions until we both understand
Tddmattpocock/skills
Write one test at a time then code to make it pass
Test Driven Developmentobra/superpowers
Write a failing test first then code just enough to pass
Webapp Testinganthropics/skills
Test your local web apps quickly with Playwright automation and screenshots
Qamattpocock/skills
Turn bug reports into GitHub issues through natural conversation without technical fuss
Migrate To Shoehornmattpocock/skills
Replace unsafe as assertions with type-safe partial test data easily
Playwright Best Practicescurrents-dev/playwright-best-practices-skill
Master Playwright testing with best practices for reliable and fast tests
Google Agents Cli Evalgoogle/agents-cli
Run evaluations on your AI agent, find failures, and improve its quality step by step