agentleFS
LeadMagicLeadMagic/leadmagic-claude-plugin/skills/contact-lookup/SKILL.md

contact-lookup

Skill1 starsChanged 9 days agoMITView on GitHub

Find, validate, or identify one B2B contact with LeadMagic MCP — work email, profile, or reverse email lookup. Use when the user has a person plus company, a profile URL, or an email and wants a work email, deliverability check, or who-is-this answer.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use when the user needs a work email for a specific person, wants to check an address, or wants the professional profile behind a URL or …

    line 9
  2. Distinctive:

    Start from the strongest identifier the user gave:

    line 12
  3. Distinctive:

    Do not re-find an email that already validates.

    line 19
  4. Very specific:

    Never validate an email a LeadMagic finder just returned: finder emails are already validated.

    line 20
  5. Very specific:

    Use email_to_b2b_profile only when the user actually needs the profile.

    line 21
  6. Distinctive:

    Prefer one composite over chaining many primitives, and don't repeat a lookup already made for the same inputs.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Contact lookup

Trigger

Use when the user needs a work email for a specific person, wants to check an address, or wants the professional profile behind a URL or email. For more than 5 people, use the bulk-enrichment or sheets skill — never loop these tools per row.

Workflow

  1. Start from the strongest identifier the user gave:
    • Existing email from elsewhere (CRM, list, sign-up) → validate_work_email. Its public status is exactly valid, invalid, or unknown; treat only valid as deliverable. unknown includes catch-all results and must never be reported as deliverable.
    • Full name + company/domain → find_work_email, or composite enrich_contact when they want the full picture
    • Profile URL (the full URL; the path ends in in/{slug}) → b2b_profile_to_work_email for the work email, search_profile for name, role, company, and work history
    • Email only, and they want the person behind it → email_to_b2b_profile (returns a profile URL), then search_profile if they want details
    • "Has this person moved on?" → detect_job_change with profile_url (most reliable) or work_email, plus the expected company when known
  2. Take the cheapest path that answers the question:
    • Do not re-find an email that already validates.
    • Never validate an email a LeadMagic finder just returned: finder emails are already validated. For any validation result, only the exact status valid is a success; invalid and unknown are not. Do not present catch-all/unknown results as deliverable.
    • Use email_to_b2b_profile only when the user actually needs the profile. It is pricier than the email tools, so check preview_cost first.
  3. Prefer one composite over chaining many primitives, and don't repeat a lookup already made for the same inputs.
  4. Personal email (find_personal_email) and mobile (find_mobile_number) are lawful B2B fallbacks. Use them only when the user explicitly asks for that channel.
  5. Report only fields the tools returned — never invent contacts, emails, or titles.

Output

  • The best contact field found and its validation status
  • The inputs used and the tools called
  • Not-found cases (usually free)
  • A concise next action

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.