LeadMagic platform help — Email Finder (97% accuracy), Email Validation (catch-all detection), Mobile Finder, Profile Search, Personal Email Finder, Company Search (firmographics), Technographics, Company Funding, Employee Finder, Role Finder, Job Change Detector, Jobs Finder, Google/Meta/B2B Ads Search, V3 search endpoints, REST API (20+ endpoints), MCP Server (Claude/Cursor/Windsurf), CLI. Use when LeadMagic email lookups returning no results, API calls failing or returning incomplete data, not sure which endpoint to use, MCP server not connecting, credits running out too fast, or wondering how LeadMagic compares to Apollo or Clay. Do NOT use for enrichment strategy across tools (use /sales-enrich), prospect list strategy across tools (use /sales-prospect-list), intent signal strategy across tools (use /sales-intent), or competitive intelligence strategy across tools (use /sales-compete).
Instrucciones de origen · Vista previa de solo lectura
name
sales-leadmagic
description
LeadMagic platform help — Email Finder (97% accuracy), Email Validation (catch-all detection), Mobile Finder, Profile Search, Personal Email Finder, Company Search (firmographics), Technographics, Company Funding, Employee Finder, Role Finder, Job Change Detector, Jobs Finder, Google/Meta/B2B Ads Search, V3 search endpoints, REST API (20+ endpoints), MCP Server (Claude/Cursor/Windsurf), CLI. Use when LeadMagic email lookups returning no results, API calls failing or returning incomplete data, not sure which endpoint to use, MCP server not connecting, credits running out too fast, or wondering how LeadMagic compares to Apollo or Clay. Do NOT use for enrichment strategy across tools (use /sales-enrich), prospect list strategy across tools (use /sales-prospect-list), intent signal strategy across tools (use /sales-intent), or competitive intelligence strategy across tools (use /sales-compete).
Help the user with LeadMagic platform questions — from email/mobile finding and company enrichment through ads intelligence, job tracking, API integration, and MCP server setup for AI agents.
Step 1 — Gather context
If references/learnings.md exists, read it first for accumulated knowledge.
Ask the user:
What area of LeadMagic do you need help with?
A) Email Finder — finding verified work emails from name + company
B) Email Validation — verifying emails, catch-all detection, deliverability scoring
C) Mobile Finder — finding direct dial phone numbers
D) Profile Search — enriching contacts from LinkedIn/B2B profile URLs
E) Company Intelligence — company search, funding, technographics, competitors
F) Employee/Role Finder — discovering employees or specific roles at companies
G) Job Change Detector — tracking contacts changing jobs
H) Ads Intelligence — Google, Meta, B2B ad research
I) API Integration — REST API setup, authentication, endpoints
J) MCP Server — setting up LeadMagic tools in Claude, Cursor, Windsurf, VS Code
K) CLI — command-line usage
L) Credits & Billing — credit costs, plan optimization
M) Something else — describe it
What's your role?
A) Sales rep / AE / BDR
B) RevOps / GTM Ops / GTM Engineer
C) Developer / Engineer
D) Marketing / Growth
E) Founder / solo seller
F) Agency
G) Other
What are you trying to accomplish? (describe your specific goal or question)
If the user's request already provides most of this context, skip directly to the relevant step. Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask only the most critical 1-2 clarifying questions at the end — don't gate your response behind gathering complete context.
Step 2 — Route or answer directly
If the request maps to a specialized skill, route:
Otherwise, answer directly using the platform reference below.
Step 3 — LeadMagic platform reference
Read references/platform-guide.md for the full platform reference — core concepts, the module/
capability breakdown, credit system and pricing, data model, and integration recipes. Read
references/leadmagic-api-reference.md for the raw API surface (endpoints, auth, request/response).
Answer the user's question using only the relevant section — don't dump the full reference.
Step 4 — Actionable guidance
When answering, always:
Include credit costs — every endpoint has different credit costs. Help users budget (e.g., "Finding emails for 1,000 leads = ~1,000 credits via Email Finder").
Emphasize free failed lookups — users only pay when data is found. This changes the ROI calculation vs flat-rate providers.
Recommend the right endpoint — Email Finder vs Profile to Email vs Personal Email Finder serve different use cases. Guide users to the cheapest path.
Consider MCP for AI workflows — if the user works in Claude, Cursor, or Windsurf, the MCP server gives them the full toolset (all 20+ endpoints) without writing code.
Suggest Clay integration — for waterfall enrichment, LeadMagic is one of Clay's 150+ providers. Users can combine LeadMagic with other providers for max coverage.
Gotchas
Best-effort from research — review these, especially items about plan-gated features and integration gotchas that may be outdated.
Mobile Finder costs 5x more than Email Finder. At 5 credits per valid mobile number, mobile enrichment burns credits fast. Budget separately — 1,000 mobile lookups = 5,000 credits (assuming 100% hit rate; less in practice since failed lookups are free).
Email to Profile is the most expensive endpoint at 10 credits. Reverse lookups (email → B2B profile) are costly. If you already have LinkedIn URLs, use Profile Search (1 credit) instead.
Basic plan credits don't roll over. Only Essential ($99/mo) and above get rollover (up to 2 months while subscribed). If you're on Basic and don't use all 2,000 credits, they expire at month end.
Field naming is inconsistent — mix of snake_case and camelCase. Different endpoints return fields in different conventions. When parsing responses programmatically, don't assume consistent naming. Check the OpenAPI spec or test each endpoint.
Rate limits are documented and tiered. Most endpoints allow 300 requests/minute (~5 req/sec burst), but Profile Search and Company Search are capped at 100 req/min (~2 req/sec). Responses carry RateLimit-Limit/RateLimit-Remaining/RateLimit-Reset plus X-Credits-Remaining/X-Credits-Cost headers — read these to self-throttle instead of guessing. Custom limits available on Enterprise.
Self-improving: If you discover something not covered here, append it to references/learnings.md with today's date.
Step 5 — Related skills
/sales-enrich — Enrichment strategy across all tools (for choosing providers, comparing approaches)
/sales-prospect-list — Building targeted prospect lists (for list strategy beyond LeadMagic)
/sales-intent — Buying signals and account prioritization (for signal strategy using Job Change Detector)
/sales-compete — Competitive intelligence (for competitive strategy using ads intelligence)
/sales-integration — Connecting tools with webhooks, Zapier, APIs
/sales-clay — Clay platform help (LeadMagic is a native Clay provider for waterfall enrichment)
/sales-do — Not sure which skill to use? The router matches any sales objective to the right skill. Install: npx skills add sales-skills/sales --skill sales-do
Examples
Example 1: Finding work emails for a prospect list
User says: "I have 2,000 leads with names and company domains. How do I find their work emails with LeadMagic?"
Skill does: Recommends Email Finder endpoint (POST /v1/people/email-finder), shows curl example with first_name + last_name + company_name, calculates credit budget (~2,000 credits max, likely less since failed lookups are free), and suggests the Essential plan ($99/mo, 5,000 credits) for headroom.
Result: API integration guide with credit budget and plan recommendation.
Example 2: Setting up MCP server for Claude Code
User says: "I want to use LeadMagic tools directly in Claude Code for prospect research."
Skill does: Walks through MCP server setup — install via npx leadmagic-mcp, configure API key, shows example usage of find_email and search_company tools within Claude. Notes the full toolset (20+ endpoints) is available.
Result: Working MCP setup with usage examples.
Example 3: LeadMagic vs Apollo for enrichment
User says: "Should I use LeadMagic or Apollo for email finding? We do about 5,000 lookups a month."
Skill does: Compares LeadMagic's pay-per-result model (5,000 lookups @ ~$0.01 = ~$50-100/mo on Essential) vs Apollo's subscription model ($49/user/mo with credit limits). Notes LeadMagic's advantage in pay-only-for-found and API-first approach. Recommends LeadMagic for API/automation workflows, Apollo for teams wanting prospecting + outbound in one tool.
Result: Clear comparison with cost analysis and recommendation.
Troubleshooting
Email Finder returning null for many lookups
Symptom: Email Finder returns null (not_found) for 40%+ of lookups.
Cause: Input data quality issues — misspelled names, wrong company domains, people no longer at that company.
Solution: Validate company domains first with Company Search. Use LinkedIn URLs with Profile to Email for higher hit rates. For stale lists, run Job Change Detector first to identify who's moved. Combine with other providers (via Clay waterfall) for maximum coverage.
Credits running out faster than expected
Symptom: Credit balance depleting before the billing cycle ends.
Cause: High-cost endpoints (Mobile Finder at 5 credits, Email to Profile at 10 credits) or ad search returning many results (1 credit per ad).
Solution: Audit endpoint usage in your dashboard. Favor low-cost endpoints (Email Finder at 1 credit, Employee Finder at 0.05 credits) where possible. Upgrade to Essential+ for credit rollover. Use Email Validation (0.25 credits) to pre-filter before running expensive lookups.
MCP server not connecting
Symptom: LeadMagic tools not appearing in Claude Code or Cursor after MCP setup.
Cause: API key not set in environment, or MCP config syntax error.
Solution: Verify LEADMAGIC_API_KEY is set in your environment or MCP config. Test the API key with curl https://api.leadmagic.io/v1/credits -H "X-API-Key: your_key" — should return your balance. Check MCP config JSON syntax. Restart your editor after config changes.
