Salesforce Setup logo

Salesforce Setup

Organization
LeadMagic
salesforce-setup

Set up Salesforce for B2B SaaS GTM — object model, opportunity pipelines, lead management, reports and dashboards, automation (Flows), and enrichment integration. Use when configuring Salesforce for sales or revops. Triggers on: "Salesforce setup", "configure Salesforce", "Salesforce CRM", "Salesforce pipeline", "Salesforce automation", or any Salesforce configuration request.

Overview

PublisherLeadMagic
Repositorygtm-skills
Skill namesalesforce-setup
Stars
72
Forks
18
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by LeadMagic on GitHub. Read the source before you install it.

Installation

Install the Salesforce Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LeadMagic/gtm-skills/tree/main/skills/automation/salesforce-setup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LeadMagic/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/automation/salesforce-setup .claude/skills/salesforce-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Salesforce Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Salesforce Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Salesforce Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Salesforce Setup

Overview

Salesforce is the enterprise CRM standard. It's infinitely customizable and infinitely misconfigurable. This skill covers GTM-specific Salesforce setup: object model for B2B SaaS, opportunity pipelines, lead management, Flows automation, reporting, and enrichment integration. Designed for teams that have outgrown HubSpot or require enterprise-grade customization.

Authoritative Foundations

  • Salesforce Architecture — Lead/Account/Contact/Opportunity — Opportunity stages, forecasting categories, and RevOps object hygiene.
  • Marc Benioff — Trust selling, land-and-expand, customer success in CRM
  • Force.com Platform — Flows, validation, reporting

When to Use

  • "Set up Salesforce for our sales team"
  • "Configure Salesforce opportunity pipeline"
  • "Set up Salesforce Flows automation"
  • "Build Salesforce reports and dashboards"
  • "Migrate from HubSpot to Salesforce"

Step-by-Step Process

Load crm-toolkit first — crm-selection, contacts-vs-leads (Lead vs Contact decision), salesforce-blueprint, and implementation-partners (Salesforce almost always needs SI help).

Phase 1: Object Model

Standard B2B SaaS object hierarchy: Lead → Account → Contact → Opportunity.

Contacts vs leads: Use the Lead object when SDRs qualify inbound before opportunities exist. Convert Lead → Account + Contact + (optional) Opportunity. Skip Leads only for low-volume founder-led motions — see crm-toolkit contacts-vs-leads reference. Do not mirror HubSpot lifecycle as custom Lead fields without a conversion path.

Enterprise motion: Load crm-toolkit → benioff-enterprise-playbook — land-and-expand opp structure, CS fields, trust/commitment logging on Opportunity.

Custom objects for SaaS-specific needs: Subscription (track recurring revenue), Customer Success Plan (health score, QBRs), Integration (partner tracking).

Key custom fields on Opportunity: MEDDICC dimensions (Economic Buyer, Decision Criteria, Champion, etc.), ICP fit score, enrichment status, lead source detail, competitors in deal.

Phase 2: Opportunity Pipeline

Sales process: Define path per record type. Standard: Prospecting → Qualification → Discovery → Demo → Proposal → Negotiation → Closed Won/Lost.

Stage requirements: Required fields per stage. Qualification: MEDDIC dimensions populated. Proposal: Amount, Close Date, Competitors. Negotiation: Decision Process documented.

Validation rules: Close Date cannot be in the past. Amount > $0. Next Step required when stage changes. Stage cannot skip forward.

Phase 3: Lead Management

Lead conversion: Lead → Account + Contact + Opportunity. Required mapping: company name → Account Name, email → Contact Email. Auto-assignment rules based on territory, deal size, or round-robin.

Web-to-Lead: Form submission creates Lead. Auto-enrich via Flow before assignment. Score leads based on ICP fit + engagement.

Phase 4: Flows Automation

Replace Process Builder and Workflow Rules with Flows (Salesforce's modern automation tool). Key Flows:

  • Auto-create task when opportunity stage changes
  • Alert manager when deal stalls >14 days
  • Create renewal opportunity 90 days before contract end
  • Enrich contact on create via external service webhook

Phase 5: Reports and Dashboards

Sales dashboards: Pipeline by stage, rep activity, forecast vs quota, win rate by source, deal velocity.

Revenue dashboards: MRR/ARR trending, churn analysis, expansion revenue, cohort retention.

Data quality dashboards: Missing required fields, stale opportunities, duplicate detection, enrichment gaps.

Phase 6: Enrichment Integration

One-direction push: External enrichment (Clay, LeadMagic) → Salesforce. Never Salesforce → enrichment platform.

Flow-triggered enrichment: Contact created → Flow calls external webhook → enrichment data writes back to Contact/Account fields.

Scheduled enrichment: Weekly batch job re-verifies emails >90 days old, refreshes firmographic data on key accounts.

Output Format

Salesforce configuration document with: object model diagram, opportunity pipeline map with validation rules, lead management flow, Flows automation catalog, dashboard specs, and enrichment integration architecture.

Quality Check

  • Object model: Lead → Account → Contact → Opportunity hierarchy configured
  • Opportunity stages defined with required fields and validation rules
  • Lead scoring and assignment rules active
  • Key Flows automating repetitive tasks
  • Dashboards for sales, revenue, and data quality
  • Enrichment: one-direction push, never two-way sync

Common Pitfalls

  1. Over-customization before process. Custom objects and fields without a defined process create complexity without value. Design the process, then configure Salesforce to support it.

  2. No validation rules. Close dates in the past, $0 opportunities, blank required fields. Validation rules enforce data quality.

  3. Process Builder instead of Flows. Process Builder is deprecated. Migrate everything to Flows.

  4. Lead assignment without enrichment. Routing an unenriched lead means reps waste time researching. Enrich on lead create, then assign.

  5. Report sprawl. 50 reports nobody reads. Build 5-7 dashboards that answer the most important questions. Archive the rest.

Execution Artifacts

  • references/framework-notes.md — named frameworks, citation anchors, and operating assumptions
  • templates/output-template.md — copy-paste deliverable structure for the user
  • scripts/check-output.py — local checklist validator for required sections This skill includes lightweight artifacts the agent can load on demand: Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.

Related Skills

  • crm-toolkit: Selection, contacts-vs-leads, salesforce-blueprint, benioff-enterprise-playbook, partners
  • crm-integration: CRM configuration principles
  • pipeline-management: Deal stage design
  • hubspot-setup: HubSpot alternative (no Lead object)
  • attio-setup: Attio alternative (status + lists)
  • hiring-agencies: SI / RevOps agency pilot

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Salesforce Setup AI skill do?

Set up Salesforce for B2B SaaS GTM — object model, opportunity pipelines, lead management, reports and dashboards, automation (Flows), and enrichment integration. Use when configuring Salesforce for sales or revops. Triggers on: "Salesforce setup", "configure Salesforce", "Salesforce CRM", "Salesforce pipeline", "Salesforce automation", or any Salesforce configuration request.

Why use Salesforce Setup on TypingMind?

Because you install it once and use it with any model. Salesforce Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Salesforce Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeadMagic/gtm-skills/tree/main/skills/automation/salesforce-setup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Salesforce Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Salesforce Setup?

As many as you like. As long as a model supports skills, you can use Salesforce Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Salesforce Setup AI skill free?

Yes. It is published on GitHub by LeadMagic under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇