Sf Ai Agentforce Persona

This is a structured framework for designing AI agent personalities in Agentforce. It walks you through defining identity, register, voice, tone, delivery, and chatting style across 50 scorable points, then generates sample dialog so you can hear how the agent sounds before you build it. You feed it brand guidelines, a URL, or just a text description, and it produces a complete persona document. The workflow is split into two phases: get to sample dialog fast, then refine whatever needs work. It handles the "who is this agent" question separately from conversation flows and metadata, which keeps the scope clean. If you're starting an agent build and the personality feels like guesswork, this gives you a repeatable way to lock it down first.

skills.sh installs: 1.2K
GitHub stars: 422
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add jaganpro/sf-skills --skill sf-ai-agentforce-persona --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Persona Design

How to Use

This skill designs an AI agent persona through a fast input-to-sample-dialog loop. Provide any starting input — a brand guide PDF, a URL, a prior persona document, or a text description — and the skill drafts a complete persona, shows you how the agent sounds in sample dialog, and lets you refine until it's right.

What it produces:

A persona document (_local/generated/[agent-name]-persona.md) defining who the agent is, how it sounds, and what it never does
Scoring available on request (50-point rubric)
Encoding available as a separate workflow (persona → tool-specific field values)

What it drives downstream: The persona document feeds into conversation design and Agentforce encoding. Those are separate steps — this skill defines the persona, not dialog flows or field configurations.

Session resumption: If you stop mid-workflow, your partial progress is preserved in the conversation and can be resumed.