Skip to content
TrustedSkillsbeta
Back to all skills

Sf Ai Agentforce Testing

Listed
jaganpro·vlatest·testing·MIT

Helps with AI, testing as part of testing, debugging, and quality assurance workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add jaganpro/sf-skills --skill sf-ai-agentforce-testing -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

jaganpro

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: api.salesforce.com, developer.salesforce.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    api.salesforce.comundeclaredsoap.sforce.comnamespace identifierdeveloper.salesforce.comundeclared

    What it found (3 of 5)

    • skills/sf-ai-agentforce-testing/hooks/scripts/agent_api_client.py:240contacts api.salesforce.com
      f"https://api.salesforce.com/einstein/ai-agent/v1"
    • skills/sf-ai-agentforce-testing/hooks/scripts/agent_api_client.py:283contacts api.salesforce.com
      f"https://api.salesforce.com/einstein/ai-agent/v1"
    • skills/sf-ai-agentforce-testing/hooks/scripts/agent_api_client.py:328contacts api.salesforce.com
      API_BASE = "https://api.salesforce.com/einstein/ai-agent/v1"

  • No credential access: failed

    Touches credential material in 8 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found (3 of 8)

    • skills/sf-ai-agentforce-testing/assets/test-plan-template.yaml:30environment file outside the project
      # Convention: ~/.sfagent/{org_alias}/{eca_name}/credentials.env
    • skills/sf-ai-agentforce-testing/assets/test-plan-template.yaml:31environment file outside the project
      path: "~/.sfagent/{org_alias}/{eca_name}/credentials.env"
    • skills/sf-ai-agentforce-testing/hooks/scripts/credential_manager.py:40environment file outside the project
      source ~/.sfagent/{org}/{eca}/credentials.env

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned jaganpro/sf-skills at 53c9956c42.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
53c9956c42
Manifest
skills/sf-ai-agentforce-testing/SKILL.md
Scanned
58 files, 17,273 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

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.