lead-enrichment
Skill0 starsChanged 2 months agoMITView on GitHub
Find 5-10 key decision makers per company with verified emails using Parallel, Apollo, and MillionVerifier APIs
- Reads credentials
13 other projects use a version of this.
Adopted by
Most recently taken up by
- manypicom/sales-skillstheir own version, first seen Nov 15, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- runxhq/runxtheir own version, first seen Oct 13, 2026
- SELAT-AI/selat-skillstheir own version, first seen Oct 4, 2026
- omnimay/skillstheir own version, first seen Sep 18, 2026
- 0xMassi/webclaw-skilltheir own version, first seen Sep 14, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- runxhq/runx★ 97same name
- chadboyda/agent-gtm-skills★ 77same name
- kevinbadi/ai-os-skills★ 69same name
- CodeAlive-AI/ceo-ai-os★ 9same name
- superagnt/leverage★ 6same name
- 0xMassi/webclaw-skill★ 2same name
- omnimay/skills★ 2same name
- SELAT-AI/selat-skills★ 2same name
- manypicom/sales-skills★ 1same name
- SkillMedev/b2b-prospecting-engine★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 13 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Use this skill when: user asks to "enrich leads", "find decision makers", "get contacts for companies", "find emails", or any request to …
- Distinctive: line 30
Before running enrichment, verify these keys exist:
- Distinctive: line 39
Ask user which keys they have
- Distinctive: line 177
Verify all discovered emails before outreach.
- Distinctive: line 181
Verify each with MillionVerifier API
- Distinctive: line 218
Look for personal emails instead
- Very specific: line 288
If pga-2026/scripts/enrichment/ exists with:
- Distinctive: line 293
Run them in sequence:
- Distinctive: line 303
Use Parallel MCP tool directly for contact discovery
- Distinctive: line 304
Use Apollo API calls for missing emails
- Distinctive: line 305
Use MillionVerifier for verification
- Very specific: line 310
Create script directory: [campaign]/scripts/enrichment/
- Distinctive: line 311
Create 3 stage scripts based on templates
- Distinctive: line 312
Create progress tracking directory
- Distinctive: line 340
Before delivering enriched list:
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lead Enrichment
Use this skill when: user asks to "enrich leads", "find decision makers", "get contacts for companies", "find emails", or any request to turn a company list into actionable contacts.
Overview
This skill takes a list of companies and finds key decision makers with:
- Full name
- Job title
- Work email (verified)
- LinkedIn URL
Uses a 3-stage pipeline:
- Parallel API - Primary contact discovery
- Apollo API - Email enrichment fallback
- MillionVerifier - Email verification
Pre-flight Checks
Required API Keys
Before running enrichment, verify these keys exist:
| Key | Service | Get it at |
PARALLEL_API_KEY | Parallel (contact discovery) | platform.parallel.ai |
APOLLO_API_KEY | Apollo (email enrichment) | app.apollo.io |
MILLIONVERIFIER_API_KEY | MillionVerifier (verification) | app.millionverifier.com |
If keys are missing:
- Ask user which keys they have
- Guide them to sign up for missing services
- Explain what each service does and approximate cost
- Have them add keys to
.envfile
Required Input
- Company list: CSV or JSON with at minimum:
- Company name
- Website (for domain extraction)
- Optional: ICP segment, priority score, target titles
Stage 1: Contact Discovery (Parallel API)
Purpose
Find 5-10 decision makers per company from public sources.
Process
- For each company, call Parallel Task API with:
- Company name
- Website domain
- Target titles to find
- Extract from results:
- Person name
- Title
- Email (if public)
- LinkedIn URL
Target Titles (customize per ICP)
Executive level:
- Founder, CEO, President, Owner
- CTO, CIO, COO, CFO
VP level:
- VP Supply Chain, VP Procurement, VP Sourcing
- VP Operations, VP Product, VP Engineering
Director level:
- Director Supply Chain, Director Procurement
- Director Operations, Director Product
Manager level:
- Product Manager, Procurement Manager
- Merchandise Manager, Buyer
Parallel API Call
from parallel_web import Parallel
client = Parallel(api_key=os.getenv("PARALLEL_API_KEY"))
result = client.task.create(
prompt=f"""Find up to 5 key decision makers at {company_name}.
Website: {website}
For each person, extract:
- Full name
- Job title
- Work email (if available)
- LinkedIn URL
Target titles: {target_titles}
""",
processor="base" # or "core", "pro"
)Output
{
"company": "Example Corp",
"contacts": [
{
"name": "John Smith",
"title": "VP Supply Chain",
"email": "john.smith@example.com",
"linkedin": "linkedin.com/in/johnsmith"
}
]
}Stage 2: Email Enrichment (Apollo API)
Purpose
Find emails for contacts that Parallel didn't return emails for.
Process
- Filter contacts where email is null/empty
- For each contact, call Apollo People Match:
- First name
- Last name
- Company domain (extracted from website)
- Apollo returns:
- Work email
- LinkedIn URL (backup)
- Verified title
Apollo API Call
import requests
def apollo_enrich(first_name, last_name, domain):
url = "https://api.apollo.io/v1/people/match"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"X-Api-Key": os.getenv("APOLLO_API_KEY")
}
data = {
"first_name": first_name,
"last_name": last_name,
"domain": domain
}
response = requests.post(url, headers=headers, json=data)
return response.json()Rate Limits
- 0.5 sec between requests (be gentle)
- 60 sec wait on 429 errors
- Bulk endpoint available for up to 10 at once
Stage 3: Email Verification (MillionVerifier)
Purpose
Verify all discovered emails before outreach.
Process
- Collect all emails (from Parallel + Apollo)
- Verify each with MillionVerifier API
- Score quality: good, bad, risky, unknown
MillionVerifier API Call
import requests
def verify_email(email):
url = f"https://api.millionverifier.com/api/v3/?api={api_key}&email={email}"
response = requests.get(url)
return response.json()Response Fields
| Field | Values | Meaning |
quality | good, bad, risky, unknown | Overall quality |
result | ok, catch_all, unknown, invalid | Specific result |
resultcode | 1, 2, 3, 6 | Numeric code |
role | true/false | Is it a role address (info@, sales@) |
free | true/false | Is it a free email provider |
Quality Interpretation
| Quality | Action |
| good | Safe to send |
| risky | Send with caution, may bounce |
| bad | Do not send |
| unknown | Manual review |
Flag Role Addresses
Role addresses (info@, sales@, support@) have lower response rates. Flag them:
- Still usable but deprioritize
- Look for personal emails instead
- Note in output for campaign decisions
Progress Tracking
Resume Capability
Store progress in JSONL files for resumability:
leads/progress/
parallel.jsonl - Company + contacts + status
apollo.jsonl - Contact + email + status
millionverifier.jsonl - Email + quality + statusJSONL Format
{"company": "Example Corp", "status": "done", "contacts": [...]}
{"company": "Another Inc", "status": "done", "contacts": [...]}Resume Logic
Before processing:
- Load existing progress file
- Build set of already-processed items
- Skip items in the set
- Append new results to progress file
Output Format
Final CSV
company,segment,website,person1_name,person1_title,person1_email,person1_linkedin,person2_name,person2_title,person2_email,person2_linkedin,...Up to 5 contacts per company (person1 through person5).
Final JSON
{
"company": "Example Corp",
"segment": "Tier1_Gloves",
"website": "example.com",
"contacts": [
{
"name": "John Smith",
"title": "VP Supply Chain",
"email": "john.smith@example.com",
"email_quality": "good",
"linkedin": "linkedin.com/in/johnsmith"
}
]
}Execution Flow
Option A: Use Existing Scripts
If pga-2026/scripts/enrichment/ exists with:
enrich_contacts_parallel.pyenrich_emails_apollo.pyverify_emails_millionverifier.py
Run them in sequence:
uv run pga-2026/scripts/enrichment/enrich_contacts_parallel.py
uv run pga-2026/scripts/enrichment/enrich_emails_apollo.py
uv run pga-2026/scripts/enrichment/verify_emails_millionverifier.pyOption B: Manual Enrichment
For small lists (under 10 companies):
- Use Parallel MCP tool directly for contact discovery
- Use Apollo API calls for missing emails
- Use MillionVerifier for verification
Option C: Create New Scripts
For new campaigns without existing scripts:
- Create script directory:
[campaign]/scripts/enrichment/ - Create 3 stage scripts based on templates
- Create progress tracking directory
- Run pipeline
Error Handling
API Failures
| Error | Action |
| 401 Unauthorized | Check API key is valid |
| 429 Rate Limited | Wait 60 sec, retry |
| 500 Server Error | Wait, retry up to 3 times |
| Timeout | Retry with longer timeout |
Missing Data
| Issue | Fallback |
| No contacts found (Parallel) | Manual web search |
| No email found (Apollo) | Try LinkedIn outreach |
| Bad email (MillionVerifier) | Remove from list |
Quality Checklist
Before delivering enriched list:
- All companies processed (check progress files)
- Emails verified (good/risky/bad flagged)
- Role addresses flagged (info@, sales@)
- LinkedIn URLs present for contacts
- Output format matches user request (CSV or JSON)
- No duplicate contacts across companies
Cost Awareness
Approximate costs (check current pricing):
| Service | Cost |
| Parallel | ~$0.01-0.05 per task |
| Apollo | Credits-based, varies by plan |
| MillionVerifier | ~$0.0003 per email |
For 100 companies with 5 contacts each:
- Parallel: 100 tasks
- Apollo: ~200 email lookups (assuming 40% need enrichment)
- MillionVerifier: ~500 verifications
This skill is generic - works for any campaign, not just Performance Leather.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

