Use this skill when users want to execute this workflow when a user wants to test how a different LLM model would handle existing Agentforce agent conversations. Trigger when users mention agentforce, offline, experimentation.
Install
npx skills add forcedotcom/sf-skills --skill agentforce-offline-experimentation-runnpx skills add forcedotcom/sf-skills --skill agentforce-offline-experimentation-run -a claude-code -gnpx skills add forcedotcom/sf-skills --skill agentforce-offline-experimentation-run -a codex -ggemini skills install https://github.com/forcedotcom/sf-skills.git --path skills/agentforce-offline-experimentation-rungh skill install forcedotcom/sf-skills agentforce-offline-experimentation-rungit clone --depth 1 https://github.com/forcedotcom/sf-skills /tmp/forcedotcom__sf-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/forcedotcom__sf-skills/skills/agentforce-offline-experimentation-run ~/.claude/skills/agentforce-offline-experimentation-run # Claude Code
cp -R /tmp/forcedotcom__sf-skills/skills/agentforce-offline-experimentation-run ~/.agents/skills/agentforce-offline-experimentation-run # Codex, Cursor, Gemini CLI, Copilot, OpenCode