agentleFS
johnisanerdjohnisanerd/alphaosint-prospector/skills/find-decision-makers/SKILL.md

find-decision-makers

Skill0 starsChanged 12 days agoMITView on GitHub

Find named decision-makers and verified work emails at the top-scored accounts, using Alpha OSINT Prospector. Pulls contacts already present in enrichment data for free, looks up business leads and verifies emails through the website contact Actor, and searches LinkedIn for the ICP's target titles. Use when the user says who do I contact, find the VP of Sales at these companies, get me emails, or find contacts for my top leads.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No personal email addresses, no phone lookups, no guessing an address from a name pattern.

    line 30

≈ “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

Find decision-makers and emails

Shared rules: ../prospect/references/conventions.md. Named people are personal data. Only run this for accounts the user intends to contact.

Steps

  1. list_leads(limit=10). Pick accounts scoring 40 or more unless the user names others.
  2. find_emails(top=5, leads_per_domain=3, verify=true).
    • Needs a known website. Accounts without one come back in skipped_no_website; run enrich-and-score on them first.
    • Needs $0.50 of session budget left even though real cost is about 5 cents per company. If budget_exceeded mentions "at least $0.50", that is why.
    • The crawl is capped at 15 pages and depth 1 per site by the server. Do not ask for more; contact pages are near the home page and this Actor bills per page.
    • On the Apify free plan the lead and verification add-ons cost $0.10 each instead of half a cent. If get_config or the user says free plan, set leads_per_domain=0 and only collect the company inbox.
  3. find_contacts(top=5). Free contacts from enrichment first, then LinkedIn search for the first two target titles. People whose current employer does not match are rejected; report rejected_wrong_employer as a number, not names.
  4. The email Actor filters by department, not by title, so it also returns neighbours of the buyer (account managers, enablement). Present people whose title matches the ICP's target titles first and label the rest as "same department, not a target title". The export marks this in title_match.
  5. For each account, get_lead and present: name, title, LinkedIn URL, email, verification.

Reading verification

  • ok: verified deliverable.
  • catch_all: the domain accepts everything, so the address cannot be confirmed. Not charged. Label as unverified.
  • unknown or empty: not confirmed. Label as unverified.
  • invalid or disposable: do not show as a usable email.

Addresses found on the site that belong to another domain (form vendors, trackers, agencies) are dropped and counted in off_domain_dropped.

Boundaries

No personal email addresses, no phone lookups, no guessing an address from a name pattern. If nothing verified was found, say so and give the company inbox.

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.