agentsclimarketplace

Leadmagic toolkit

Skill LeadMagic/gtm-skills/skills/tools/leadmagic-toolkit

Complete LeadMagic platform toolkit — API reference, CLI workflows, MCP server setup, enrichment waterfalls, bulk processing, job change detection, and integration patterns. Use when building LeadMagic-powered GTM infrastructure, integrating LeadMagic into Clay/n8n/HubSpot/Salesforce, or automating email finding and verification at scale. Triggers on: "LeadMagic toolkit", "LeadMagic API", "LeadMagic setup", "LeadMagic CLI".From its SKILL.md

Install
npx -y skills add LeadMagic/gtm-skills --skill leadmagic-toolkit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

9.1 KB, ~1.9k tokens by cl100k_base, as published. Nobody here has run it

LeadMagic Toolkit

Overview

LeadMagic is the engine that powers email finding, verification, and enrichment for thousands of GTM teams. This skill is the master toolkit: every endpoint, every integration pattern, every workflow, and every advanced tactic. The mistake: using the API one call at a time manually. The fix: automated workflows, waterfall enrichment, MCP tool orchestration, and integration into every tool in your stack.

Authoritative Foundations

  • LeadMagic API — Email finder, verifier, waterfall enrichment endpoints — Email finder, verifier, waterfall enrichment endpoints
  • MCP (Model Context Protocol) — Anthropic AI tool integration — Model Context Protocol — tool servers for agent-safe CRM and enrichment access.
  • Clay — Waterfall enrichment and prospecting platform — Waterfall enrichment, Claygent research, and table-based GTM automation.
  • n8n — Open-source workflow automation — Workflow automation — HTTP nodes, webhooks, and GTM glue between tools.
  • Pat Spielmann — Portable data layer — Portable data layer
  • Pat Spielmann — Cold to Gold — Cold to Gold

When to Use

Trigger phrases: "LeadMagic API", "LeadMagic setup", "LeadMagic integration", "LeadMagic CLI", "LeadMagic MCP", "LeadMagic enrichment", "LeadMagic bulk", "LeadMagic Clay", "LeadMagic n8n", "LeadMagic workflow"

Platform Capabilities

Core Endpoints

  • Email Finder: Find email from name + company or name + domain
  • Email Verifier: Verify deliverability with confidence scoring
  • Waterfall Enrichment: Multi-source enrichment with provider chaining
  • Bulk Processing: CSV upload, async batch processing, webhook callbacks
  • Job Change Detection: Monitor contacts for job changes

Integration Methods

  • REST API: Direct HTTP calls with API key authentication
  • CLI: Command-line tool for scripting and automation
  • MCP Server: 16 tools exposed as MCP tools for AI agents
  • Clay Integration: Native Clay enrichment provider
  • n8n Integration: HTTP Request nodes for workflow automation
  • CRM Integration: HubSpot, Salesforce, Attio via API/webhook

Workflow Patterns

Pattern 1: Single Email Find + Verify

Input: name + company → API: Email Finder → Email → API: Email Verifier → Confidence score
CLI: lm find "Jane Smith" "Acme Corp" | lm verify

Pattern 2: Bulk CSV Enrichment

Upload CSV → API: Bulk Enrich → Poll status → Download results → CRM import
CLI: lm bulk-enrich contacts.csv --output enriched.csv --webhook https://...

Pattern 3: Waterfall Enrichment (Clay)

Input → LeadMagic → if not found → Apollo → if not found → ProspectingTool → Output

Pattern 4: MCP Orchestration

AI Agent → MCP Tool: find_email → MCP Tool: verify_email → MCP Tool: enrich_person

Artifacts

CLI Quick Reference

# Install
npm install -g leadmagic-cli
lm config set api_key YOUR_KEY

# Find email
lm find "Jane Smith" "Acme Corp"
lm find --domain acme.com --pattern "{first}.{last}@{domain}"

# Verify email
lm verify [email protected]
lm verify --bulk emails.txt

# Bulk enrich
lm bulk-enrich contacts.csv --output enriched.csv

# Job change check
lm job-change --contact-id abc123

# MCP server
lm mcp start --port 3000

n8n Workflow Template

{
  "name": "LeadMagic Email Find + Enrich",
  "nodes": [
    {
      "name": "Input",
      "type": "n8n-nodes-base.webhook",
      "position": [250, 300]
    },
    {
      "name": "Find Email",
      "type": "n8n-nodes-base.httpRequest",
      "position": [450, 300],
      "parameters": {
        "url": "https://api.leadmagic.io/v1/email/find",
        "method": "POST",
        "headers": { "Authorization": "Bearer {{$credentials.apiKey}}" },
        "body": { "name": "{{$json.name}}", "company": "{{$json.company}}" }
      }
    },
    {
      "name": "Verify Email",
      "type": "n8n-nodes-base.httpRequest",
      "position": [650, 300],
      "parameters": {
        "url": "https://api.leadmagic.io/v1/email/verify",
        "method": "POST",
        "body": { "email": "{{$json.email}}" }
      }
    },
    {
      "name": "Output",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [850, 300]
    }
  ]
}

Clay Integration Pattern

1. Add LeadMagic enrichment to Clay table
2. Map: Name column → LeadMagic Name, Company column → LeadMagic Company
3. Configure: waterfall order (LeadMagic first, then fallbacks)
4. Run: 1 credit per email found + verified

Implementation Checklist

  • API key configured and tested
  • CLI installed and configured
  • MCP server running (if using AI agents)
  • Webhook endpoints configured for bulk callbacks
  • Rate limits understood and handled (exponential backoff)
  • Clay integration with waterfall fallback configured
  • n8n workflow templates ready for common patterns

Common Pitfalls

  1. No waterfall fallback. LeadMagic → nothing. Apollo would have found it. Fix: Always chain providers. LeadMagic first. Apollo/Clearbit second.
  2. No webhook for bulk. Poll status in a loop. Timeout. Job lost. Fix: Webhook callbacks. Job ID → webhook notifies on completion.
  3. Hard-coding API keys in n8n. Committed to repo. Leaked. Fix: n8n credentials store. Environment variables. Never hard-code.

Output Format

The agent delivers a LeadMagic integration blueprint matched to the user's stack and use case:

  • Integration Method Selection: recommended access pattern (REST API direct, CLI script, MCP server for AI agents, Clay enrichment column, or n8n HTTP Request node) with rationale for the user's workflow type
  • Workflow Design: end-to-end data flow diagram — input source → find endpoint → verify endpoint → enrichment endpoint → destination system (CRM, sequencer, or data store)
  • Code/Config Artifact: ready-to-use CLI commands, n8n workflow JSON snippet, or Clay column configuration for the chosen pattern — including auth header format and field mappings
  • Credential & Rate-Limit Setup: API key configuration steps, rate-limit thresholds (requests per minute), exponential backoff pattern for 429 responses, and bulk webhook callback URL setup
  • Fallback Chain: waterfall provider order (LeadMagic first → secondary provider on miss) with per-miss handling logic and confidence-score threshold for accepting results
  • QA Checklist: 7-point validation covering API connectivity test, waterfall coverage rate on a sample, webhook delivery confirmation, credential security review, enrichment accuracy spot-check (10 known contacts), bulk job completion handling, and CRM field mapping verification

Quality Check

Before delivering, verify:

  • All required sections complete
  • Output matches the user's stated need
  • No vague or unsupported claims
  • Frameworks cited where applicable

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:
  • ../../outbound/cold-email-copywriting/references/pat-spielmann-outbound-copy.md — GTM stack + outbound copy integration patterns (Pat Spielmann) 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

  • leadmagic-cli — CLI workflows and scripting
  • leadmagic-waterfall — Multi-provider enrichment waterfall design
  • leadmagic-integrations — CRM and platform integrations
  • leadmagic-mcp — MCP server for AI agent orchestration
  • leadmagic-bulk-enrichment — Batch processing at scale
  • leadmagic-job-change — Job change detection and champion tracking

What ships with it: 3 files

3.9 KB alongside SKILL.md, 1 of them executable

references/

scripts/

templates/

Gives 0 of the 12 instructions most mcp tooling skills give in ~1.9k tokens

Counted across 780 of the 1,136 authors here whose files we hold, read 2026-09-06

  • Use Zod for input validationin 34 of 780, across 21 files
  • Use stdio for local clientsin 27 of 780, across 10 files
  • Restart Claude Code after configurationin 26 of 780, across 23 files
  • Verify MCP server connection before using toolsin 23 of 780, across 17 files
  • Define input schemas for every toolin 20 of 780, across 11 files
  • Use Streamable HTTP for remote clientsin 18 of 780, across 8 files
  • Pin SDK version in package.jsonin 17 of 780, across 6 files
  • Keep server logic independent of transportin 16 of 780, across 6 files
  • Verify SDK methods against official documentationin 15 of 780, across 5 files
  • Format evaluation results as an XML filein 15 of 780, across 12 files
  • Test servers using the MCP Inspectorin 15 of 780, across 14 files
  • Create ten complex and independent evaluation questionsin 14 of 780, across 11 files

Said here and by no other author read

  • Automate workflows using API endpoints
  • Chain enrichment providers for waterfall fallbacks
  • Use webhooks for bulk processing callbacks
  • Store API keys in secure credential stores
  • Map input fields to LeadMagic API parameters
  • Verify email deliverability with confidence scores

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.