agentleFS
CodeAlive-AICodeAlive-AI/ceo-ai-os/skills/lead-enrichment/SKILL.md

lead-enrichment

Skill9 starsChanged 6 months agoMITView on GitHub

Enrich leads with email, phone, company data using Hunter, Sixtyfour, and Fiber. Use when you have a name/company and need full contact profile. For just email, see find-email-by-name. For building prospect lists from scratch, see sales-prospecting.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before helping, check MEMORY.md for current ICP and outbound targets.

    line 9
  2. Distinctive:

    Only if score < 70 or you need high confidence before outreach.

    line 33
  3. Distinctive:

    If LinkedIn URL known:

    line 45
  4. Distinctive:

    Ask the user what level they need if unclear.

    line 73
  5. Distinctive:

    Always verify email before cold outreach

    line 79

“Common” is measured: kept by at least 6 in 10 of the 11 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

[YOUR_PRODUCT] Context

Before helping, check MEMORY.md for current ICP and outbound targets. Output in Russian (names, emails, titles in original). For chat platforms: compact profile card, not raw JSON.

Lead Enrichment

Enrich a lead from partial info (name + company) into a full contact profile with email, phone, LinkedIn, and company data.

Workflow

Step 1: Find Email (Hunter)

orth run hunter /v2/email-finder -q domain=COMPANY_DOMAIN -q first_name=FIRST -q last_name=LAST

IMPORTANT: Use separate -q flags. Never join with &.

Step 2: Verify Email (Hunter)

orth run hunter /v2/email-verifier -q email=found@email.com

Only if score < 70 or you need high confidence before outreach.

Step 3: Full Profile (Sixtyfour)

orth run sixtyfour /enrich-lead -d '{"lead_info": {"first_name": "FIRST", "last_name": "LAST", "company": "COMPANY"}, "struct": {"email": "Work email", "phone": "Phone number", "title": "Job title"}}'

Returns AI-researched profile with email, phone, title.

Step 4: LinkedIn Data (Fiber)

If LinkedIn URL known:

orth run fiber /v1/linkedin-live-fetch/profile/single -d '{"identifier": "https://linkedin.com/in/USERNAME"}'

Step 5: Company Context (Hunter)

orth run hunter /v2/companies/find -q domain=COMPANY_DOMAIN

Output Format

**[Full Name]** — [Title] @ [Company]
Email: [email] ([verified/unverified], score [X]%)
Phone: [phone or "not found"]
LinkedIn: [url]
Company: [size] employees, [industry], [location]

Quick Mode vs Full Mode

  • Quick (1 call, cheap): Just Step 1 — email only
  • Standard (2-3 calls): Steps 1 + 3 — email + profile
  • Full (4-5 calls): All steps — complete dossier

Ask the user what level they need if unclear.

Tips

  • LinkedIn URL dramatically improves match rates
  • Sixtyfour is AI-powered — slower but finds more data
  • Always verify email before cold outreach
  • Cache results — don't re-enrich the same lead

Related Skills

  • pipeline-manager — stores enrichment results in pipeline.json
  • signal-scanner — triggers enrichment for newly detected signals
  • find-email-by-name — just email lookup (cheaper, faster)
  • person-lookup — background research on a person
  • sales-prospecting — find new leads matching ICP
  • cold-email — write outreach after enrichment
  • outreach-sender — send and track outreach

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.