Agentforce Builder

Build Agentforce agents in Setup. AI writes the topics, actions, and prompt templates — and follows Salesforce's own best practices.

Skill Details

Install this skill

Versionv2.2.0AuthorJag ValaiyapathyLicenseMITSections10

Works with

Claude CodeCursorWindsurf

Use this skill for the Setup UI / Agent Builder path: declarative topics, Builder-managed actions, GenAiFunction / GenAiPlugin metadata, Prompt Builder templates stored as GenAiPromptTemplate metadata, Models API usage from Apex, and custom Lightning types.

For new code-first agent development, prefer sf-ai-agentscript.

When This Skill Owns the TaskWorkflow

Use sf-ai-agentforce when the user is:

maintaining existing Builder-based agents
working in Setup → Agentforce → Agents
creating or fixing GenAiFunction, GenAiPlugin, or GenAiPromptTemplate metadata
wiring Builder topics to Flow / Apex / Prompt Builder actions
using Models API or LightningTypeBundle in the context of Builder-based agents

Do not use it for:

.agent files or deterministic FSM design → sf-ai-agentscript
agent test suites and coverage loops → sf-ai-agentforce-testing
persona / voice design → sf-ai-agentforce-persona

Required Context to Gather FirstWorkflow

Ask for or infer:

whether this is a Builder / Setup UI project or a code-first Agent Script project
agent type: Service Agent or Employee Agent
whether the work targets topics, actions, Prompt Builder templates, Models API, or custom Lightning types
what supporting Flow / Apex / metadata dependencies already exist
whether the user needs authoring help, publish help, or troubleshooting

Two Agentforce Paths

If the user is starting from scratch and wants strong control over flow/state, route to Agent Script.

Builder Workflow Summary

Confirm this is a Builder / Setup UI project

Pick Service Agent vs Employee Agent

Define topics with strong descriptions, scope, and instructions

Prepare supporting actions (Flow, Apex, Prompt Builder template)

Configure inputs / outputs carefully

Validate dependencies and template status

Publish, then activate

Expanded workflow: references/builder-workflow.md

Key Platform Rules

Topic quality matters

Topic descriptions are routing instructions for the planner. They must be:

specific
scenario-based
non-overlapping with sibling topics

Actions are wrappers around real targets

Prompt Template vs GenAiPromptTemplate

Prompt Template is the plain-English / UI term used in Prompt Builder.
GenAiPromptTemplate is the current Metadata API type for source-driven template work.
Prefer current source format: genAiPromptTemplates/*.genAiPromptTemplate-meta.xml.
For flexible Prompt Builder templates, plan around the 5-input maximum and consolidate inputs when needed.
Prompt content should reference inputs with the current merge-field shape, e.g. {!$Input:TargetRecord} or {!$Input:AdditionalContext}.

Supporting metadata deploys first

Before publishing the agent itself, deploy the supporting stack:

metadata / fields if needed

Apex if needed

Flows if needed

GenAiPromptTemplate / GenAiFunction / GenAiPlugin

then publish the agent

Publish does not activate

After publish, run sf agent activate separately.

Metadata Guidance

GenAiFunction

Use when registering a single callable action. Validate:

target exists
target is active / deployable
input names match the target contract
output names match the target contract
capability text clearly says when the action should be used

GenAiPlugin

Use when grouping related functions into one logical package.

GenAiPromptTemplate

Use for generated content, not deterministic business rules.

Prefer the current metadata shape:

metadata type: GenAiPromptTemplate
folder: genAiPromptTemplates/
file suffix: .genAiPromptTemplate-meta.xml
content lives under templateVersions
use published template versions before wiring actions that depend on them

Models API

Use when the solution belongs in Apex-driven AI orchestration rather than Builder-only actions.

Custom Lightning Types

Use when the action needs richer structured input or output presentation.

Expanded references:

Cross-Skill IntegrationReference

Recommended Orchestration Order

TEXT

sf-metadata → sf-apex → sf-flow → sf-ai-agentforce → sf-deploy

Required delegations

High-Signal Failure Patterns

Reference Map

Start here

Terminology and template planning

Rubric

references/scoring-rubric.md

Cross-skill reads

Score Guide

Path	Skill	Best fit
Setup UI / Agent Builder	`sf-ai-agentforce`	Declarative maintenance, existing Builder agents, metadata-driven action registration
Agent Script DSL	`sf-ai-agentscript`	Code-first `.agent` authoring, deterministic routing, version-controlled agent logic
Target type	Typical use	Registered via
Flow	safest default for Builder actions	`GenAiFunction`
Apex	complex business logic via `@InvocableMethod`	`GenAiFunction`
Prompt Builder template	generated summaries / drafts / recommendations	`GenAiFunction`
Requirement	Delegate to	Why
Create / fix Flows	sf-flow	Action target creation and Flow validation
Create / fix Apex actions	sf-apex	`@InvocableMethod` and Apex correctness
Deploy / publish	sf-deploy	Deployment orchestration
Test the agent	sf-ai-agentforce-testing	Formal test execution and assertions
Symptom	Likely cause	Read next
Action not available in Builder	target metadata missing or not deployed	references/metadata-reference.md
Prompt action fails during publish or activation	template is Draft, missing inputs, or old metadata shape is being used	references/genaiprompttemplate.md
Need more than 5 template inputs	flex template input limit hit	references/genaiprompttemplate.md
Apex AI logic times out	Models API work placed in the wrong context	references/models-api.md
Rich input/output UI not rendering	Lightning type config or prerequisites are incomplete	references/custom-lightning-types.md
Agent publishes but is not usable	forgot explicit activation	references/cli-commands.md
Score	Meaning
90+	Ready to deploy
80–89	Strong, minor cleanup only
70–79	Review before deploy
60–69	Needs work
< 60	Block deployment

Full rubric: references/scoring-rubric.md