Lead Enrichment — Multi-Source Data Completion
Enrich CRM contact records by filling missing fields from multiple sources. Works with DuckDB workspace entries or standalone JSON data.
Sources (Priority Order)
- LinkedIn (via linkedin-scraper skill) — name, title, company, education, connections
- Web Search (via web_search tool) — email patterns, company info, social profiles
- Company Website (via web_fetch) — team pages, about pages, contact info
- Email Pattern Discovery — derive email from name + company domain
Enrichment Pipeline
Step 1: Assess What's Missing
-- Query the target object to find gaps
SELECT "Name", "Email", "LinkedIn URL", "Company", "Title", "Location"
FROM v_leads
WHERE "Email" IS NULL OR "LinkedIn URL" IS NULL OR "Title" IS NULL;
Step 2: Prioritize by Value
- High priority: Missing email (needed for outreach)
- Medium priority: Missing title/company (needed for personalization)
- Low priority: Missing education, connections count, about text
Step 3: Enrich Per Record
For each record with gaps:
If LinkedIn URL is known but other fields missing:
- Use linkedin-scraper to visit profile
- Extract: title, company, location, education, about
- Update DuckDB record
If LinkedIn URL is missing:
- Search LinkedIn:
{name} {company} or {name} {title}
- Verify match (name + company alignment)
- Store LinkedIn URL, then scrape full profile
If Email is missing:
- Find company domain (web search or LinkedIn company page)
- Try common patterns:
first@domain.com
first.last@domain.com
flast@domain.com
firstl@domain.com
- Optionally verify with web search:
"email" "{name}" site:{domain}
- Check company team/about page for email format clues
If Company info is missing:
- Web search:
"{name}" "{title}" or check LinkedIn
- Fetch company website for: industry, size, description, funding
Step 4: Update Records
-- Update via DuckDB pivot view
UPDATE v_leads SET
"Email" = ?,
"LinkedIn URL" = ?,
"Title" = ?,
"Company" = ?,
"Location" = ?
WHERE id = ?;
Bulk Enrichment Mode
For enriching many records at once:
- Query all incomplete records from DuckDB
- Group by company (scrape company once, apply to all employees)
- Process in batches of 10-20 records
- Report progress after each batch:
Enrichment Progress: 45/120 leads (38%)
├── Emails found: 32/45 (71%)
├── LinkedIn matched: 41/45 (91%)
├── Titles updated: 38/45 (84%)
└── ETA: ~15 min remaining
- Save checkpoint after each batch (in case of interruption)
Enrichment Quality Rules
- Confidence scoring: Mark each enriched field with confidence (high/medium/low)
- High: Direct match from LinkedIn profile or company website
- Medium: Inferred from patterns (email format) or partial match
- Low: Best guess from web search results
- Never overwrite existing data unless explicitly asked
- Flag conflicts: If enriched data contradicts existing data, flag for review
- Dedup check: Before inserting LinkedIn URL, check it's not already assigned to another contact
Email Pattern Discovery
Common corporate email formats by frequency:
first.last@domain.com (most common, ~45%)
first@domain.com (~20%)
flast@domain.com (~15%)
firstl@domain.com (~10%)
first_last@domain.com (~5%)
last.first@domain.com (~3%)
first.l@domain.com (~2%)
Strategy:
- If you know one person's email at the company, derive the pattern
- Search web for
"@{domain}" email format
- Check company team page source code for mailto: links
- Use the most common pattern as fallback
Output
After enrichment, provide a summary:
Enrichment Complete: 120 leads processed
├── Emails: 94 found (78%), 26 still missing
├── LinkedIn: 108 matched (90%), 12 not found
├── Titles: 115 updated (96%)
├── Companies: 118 confirmed (98%)
├── Locations: 89 found (74%)
└── Avg confidence: High (82%), Medium (14%), Low (4%)
Top gaps remaining:
- 26 leads missing email (mostly small/stealth companies)
- 12 leads missing LinkedIn (common names, ambiguous matches)
DuckDB Field Mapping
Standard field names for Ironclaw CRM objects:
| Enrichment Data |
DuckDB Field |
Type |
| Full name |
Name |
text |
| Email address |
Email |
email |
| LinkedIn URL |
LinkedIn URL |
url |
| Job title |
Title |
text |
| Company name |
Company |
text / relation |
| Location |
Location |
text |
| Education |
Education |
text |
| Phone |
Phone |
phone |
| Company size |
Company Size |
text |
| Industry |
Industry |
text |
| Enrichment date |
Enriched At |
date |
| Confidence |
Enrichment Confidence |
enum (high/medium/low) |
1---2name: lead-enrichment-23description: Enrich contact and lead records with LinkedIn profiles, email addresses, company data, and education info. Use when asked to "enrich contacts", "fill in missing data", "find emails for leads", "complete lead profiles", "look up company info", or any bulk data completion task for CRM records.4metadata:5 source: https://skillmd.com/skills/modbender/lead-enrichment-26 openclaw:7 emoji: ✨8---910# Lead Enrichment — Multi-Source Data Completion1112Enrich CRM contact records by filling missing fields from multiple sources. Works with DuckDB workspace entries or standalone JSON data.1314## Sources (Priority Order)15161. **LinkedIn** (via linkedin-scraper skill) — name, title, company, education, connections172. **Web Search** (via web_search tool) — email patterns, company info, social profiles183. **Company Website** (via web_fetch) — team pages, about pages, contact info194. **Email Pattern Discovery** — derive email from name + company domain2021## Enrichment Pipeline2223### Step 1: Assess What's Missing24```sql25-- Query the target object to find gaps26SELECT "Name", "Email", "LinkedIn URL", "Company", "Title", "Location"27FROM v_leads28WHERE "Email" IS NULL OR "LinkedIn URL" IS NULL OR "Title" IS NULL;29```3031### Step 2: Prioritize by Value32- **High priority**: Missing email (needed for outreach)33- **Medium priority**: Missing title/company (needed for personalization)34- **Low priority**: Missing education, connections count, about text3536### Step 3: Enrich Per Record3738For each record with gaps:3940#### If LinkedIn URL is known but other fields missing:411. Use linkedin-scraper to visit profile422. Extract: title, company, location, education, about433. Update DuckDB record4445#### If LinkedIn URL is missing:461. Search LinkedIn: `{name} {company}` or `{name} {title}`472. Verify match (name + company alignment)483. Store LinkedIn URL, then scrape full profile4950#### If Email is missing:511. Find company domain (web search or LinkedIn company page)522. Try common patterns:53 - `first@domain.com`54 - `first.last@domain.com`55 - `flast@domain.com`56 - `firstl@domain.com`573. Optionally verify with web search: `"email" "{name}" site:{domain}`584. Check company team/about page for email format clues5960#### If Company info is missing:611. Web search: `"{name}" "{title}"` or check LinkedIn622. Fetch company website for: industry, size, description, funding6364### Step 4: Update Records65```sql66-- Update via DuckDB pivot view67UPDATE v_leads SET68 "Email" = ?,69 "LinkedIn URL" = ?,70 "Title" = ?,71 "Company" = ?,72 "Location" = ?73WHERE id = ?;74```7576## Bulk Enrichment Mode7778For enriching many records at once:79801. **Query all incomplete records** from DuckDB812. **Group by company** (scrape company once, apply to all employees)823. **Process in batches** of 10-20 records834. **Report progress** after each batch:84 ```85 Enrichment Progress: 45/120 leads (38%)86 ├── Emails found: 32/45 (71%)87 ├── LinkedIn matched: 41/45 (91%)88 ├── Titles updated: 38/45 (84%)89 └── ETA: ~15 min remaining90 ```915. **Save checkpoint** after each batch (in case of interruption)9293## Enrichment Quality Rules9495- **Confidence scoring**: Mark each enriched field with confidence (high/medium/low)96 - High: Direct match from LinkedIn profile or company website97 - Medium: Inferred from patterns (email format) or partial match98 - Low: Best guess from web search results99- **Never overwrite existing data** unless explicitly asked100- **Flag conflicts**: If enriched data contradicts existing data, flag for review101- **Dedup check**: Before inserting LinkedIn URL, check it's not already assigned to another contact102103## Email Pattern Discovery104105Common corporate email formats by frequency:1061. `first.last@domain.com` (most common, ~45%)1072. `first@domain.com` (~20%)1083. `flast@domain.com` (~15%)1094. `firstl@domain.com` (~10%)1105. `first_last@domain.com` (~5%)1116. `last.first@domain.com` (~3%)1127. `first.l@domain.com` (~2%)113114Strategy:1151. If you know one person's email at the company, derive the pattern1162. Search web for `"@{domain}" email format`1173. Check company team page source code for mailto: links1184. Use the most common pattern as fallback119120## Output121122After enrichment, provide a summary:123124```125Enrichment Complete: 120 leads processed126├── Emails: 94 found (78%), 26 still missing127├── LinkedIn: 108 matched (90%), 12 not found128├── Titles: 115 updated (96%)129├── Companies: 118 confirmed (98%)130├── Locations: 89 found (74%)131└── Avg confidence: High (82%), Medium (14%), Low (4%)132133Top gaps remaining:134- 26 leads missing email (mostly small/stealth companies)135- 12 leads missing LinkedIn (common names, ambiguous matches)136```137138## DuckDB Field Mapping139140Standard field names for Ironclaw CRM objects:141142| Enrichment Data | DuckDB Field | Type |143|----------------|--------------|------|144| Full name | Name | text |145| Email address | Email | email |146| LinkedIn URL | LinkedIn URL | url |147| Job title | Title | text |148| Company name | Company | text / relation |149| Location | Location | text |150| Education | Education | text |151| Phone | Phone | phone |152| Company size | Company Size | text |153| Industry | Industry | text |154| Enrichment date | Enriched At | date |155| Confidence | Enrichment Confidence | enum (high/medium/low) |