Skip to content

moonlight-lupin/agent-skills / research/people-enrichment

people-enrichment

Verified

Use when the user has a list of names or companies and wants their job, employer, work history, LinkedIn URLs or company profiles looked up, or wants to find people or companies matching criteria — trigger on phrases like "enrich these contacts", "find their LinkedIn", "look up these people", "who works at X", "find directors at Y", "enrich these companies", or "get firmographics for". Enrich and search People Data Labs (PDL) Person and Company data, writing results to .xlsx. Five operations: enrich named PEOPLE into a profile, employment history and LinkedIn URL; IDENTIFY an ambiguous person as several scored candidates; SEARCH people by criteria (company, title, location); enrich COMPANIES into firmographics (industry, size, employees, HQ, founded, LinkedIn); and SEARCH companies by criteria. Do not scrape LinkedIn directly — this uses a licensed data aggregator (PDL) instead, for legal and reliability reasons.

FileKindSize
README.mdmarkdown2.0 KB
SKILL.mdskill md10.9 KB
references/sample_companies.csvother67 B
references/sample_input.csvother117 B
requirements.txtmanifest93 B
scripts/email_list.pyscript10.0 KB
scripts/enrich.pyscript26.9 KB
tests/__init__.pyscript0 B
tests/test_email_list.pyscript4.1 KB
tests/test_enrich.pyscript24.6 KB

scripts/email_list.py

View on GitHub
#!/usr/bin/env python3
"""
email_list.py - enrich a list of email addresses: triage first, one lookup per company, people last.

  triage  Sort the addresses for free (no network) into webmail, shared mailbox (info@, sales@ ...),
          personal work address, invalid and excluded. Writes:
            email_triage.csv  one row per unique address with its triage class
            companies.csv     ONE row per unique company domain (website column) -> company-enrich
            people.csv        personal work addresses only (email column)     -> person-enrich
          and prints the lookup counts so the cost can be agreed before anything is sent.
  merge   Join the enrich.py outputs back onto the triage rows -> one .xlsx (or .csv) with an
          outcome per address: person, company only, webmail, shared mailbox, not found, excluded.

Webmail addresses are never looked up (no company data, and they are private). Shared mailboxes
get the company lookup only. This script makes no network calls; the lookups are the existing
enrich.py commands:

  python email_list.py triage --input emails.csv --out-dir work [--exclude-domain example.org]
  python enrich.py company-enrich --input work/companies.csv --output work/companies.xlsx
  python enrich.py person-enrich  --input work/people.csv    --output work/people.xlsx   # optional
  python email_list.py merge --dir work --output enriched_list.xlsx
"""

import argparse
import csv
import sys
from pathlib import Path

WEBMAIL = {
    "gmail.com", "googlemail.com", "yahoo.com", "yahoo.co.jp", "yahoo.com.sg", "yahoo.co.uk",
    "hotmail.com", "outlook.com", "live.com", "live.jp", "msn.com", "icloud.com", "me.com",
    "aol.com", "protonmail.com", "proton.me", "gmx.com", "gmx.de", "mail.com", "qq.com", "163.com",
    "126.com", "nifty.com", "docomo.ne.jp", "ezweb.ne.jp", "softbank.ne.jp", "web.de", "yandex.ru",
}
ROLE_LOCALPARTS = {
    "info", "ir", "investor", "investors", "investorrelations", "investor.relations", "enquiries",
    "enquiry", "inquiries", "inquiry", "contact", "contactus", "admin", "hello", "office", "sales",
    "support", "help", "hr", "careers", "jobs", "recruitment", "marketing", "media", "press", "pr",
    "team", "mail", "general", "reception", "accounts", "finance", "billing", "compliance", "legal",
    "noreply", "no-reply", "webmaster", "service", "customerservice", "ops", "operations",
}
TRIAGE = "email_triage.csv"
COLS = ["email", "outcome", "company", "domain", "industry", "size", "country", "full_name",
        "title", "linkedin_url", "check"]


def classify(addr, exclude=()):
    """(class, domain) for one address. Classes: invalid, excluded, webmail, shared mailbox, personal."""
    a = str(addr or "").strip().lower()
    if a.count("@") != 1 or not a.split("@")[0] or "." not in a.split("@")[1]:
        return "invalid", ""
    local, dom = a.split("@")
    if any(dom == d or dom.endswith("." + d) for d in exclude):
        return "excluded", dom
    if dom in WEBMAIL:
        return "webmail", dom
    if local in ROLE_LOCALPARTS or local.replace("_", ".") in ROLE_LOCALPARTS:
        return "shared mailbox", dom
    return "personal", dom


def read_addresses(path):
    p = Path(path)
    text = p.read_text(encoding="utf-8-sig", errors="replace")
    if p.suffix.lower() == ".csv":
        rows = list(csv.DictReader(text.splitlines()))
        if rows:
            key = next((k for k in rows[0] if k and k.strip().lower() in
                        ("email", "email address", "e-mail", "work email")), None)
            if not key:
                sys.exit("No email column found (expected 'email').")
            return [r[key] for r in rows if r.get(key)]
    return [ln.strip() for ln in text.splitlines() if ln.strip()]


def _write_csv(path, header, rows):
    with open(path, "w", newline="", encoding="utf-8") as f:
        w = csv.writer(f)
        w.writerow(header)
        w.writerows(rows)


def triage(input_path, out_dir, exclude=()):
    out = Path(out_dir)
    out.mkdir(parents=True, exist_ok=True)
    seen, rows = set(), []
    for raw in read_addresses(input_path):
        a = raw.strip().lower()
        if a in seen:
            continue
        seen.add(a)
        cls, dom = classify(a, [d.lower() for d in exclude])
        rows.append((a, dom, cls))
    _write_csv(out / TRIAGE, ["email", "domain", "triage"], rows)
    domains = sorted({d for _, d, c in rows if c in ("personal", "shared mailbox")})
    people = [a for a, _, c in rows if c == "personal"]
    _write_csv(out / "companies.csv", ["website"], [[d] for d in domains])
    _write_csv(out / "people.csv", ["email"], [[e] for e in people])
    counts = {}
    for _, _, c in rows:
        counts[c] = counts.get(c, 0) + 1
    return {"addresses": len(rows), "counts": counts, "company_lookups": len(domains),
            "person_lookups": len(people)}


def _read_xlsx(path):
    """{Query: row-dict} from an enrich.py output sheet (first sheet, header row 1)."""
    if not path or not Path(path).exists():
        return {}
    from openpyxl import load_workbook
    wb = load_workbook(path, read_only=True)
    try:
        it = wb.worksheets[0].iter_rows(values_only=True)
        head = [str(h or "") for h in next(it)]
        out = {}
        for r in it:
            rec = dict(zip(head, r))
            q = str(rec.get("Query") or "").strip().lower()
            if q:
                out[q] = rec
    finally:
        wb.close()                                   # read-only mode keeps the file open on Windows
    return out


def merge(dir_, people_xlsx=None, companies_xlsx=None):
    d = Path(dir_)
    people = _read_xlsx(people_xlsx or d / "people.xlsx")
    companies = _read_xlsx(companies_xlsx or d / "companies.xlsx")
    rows = list(csv.DictReader((d / TRIAGE).read_text(encoding="utf-8").splitlines()))
    out = []
    for r in rows:
        rec = {k: "" for k in COLS}
        rec.update({"email": r["email"], "domain": r["domain"]})
        t = r["triage"]
        if t in ("webmail", "invalid", "excluded"):
            rec["outcome"] = {"webmail": "webmail - not looked up", "invalid": "invalid address",
                              "excluded": "excluded"}[t]
            out.append(rec)
            continue
        checks = []
        c = companies.get(r["domain"])
        if c and c.get("Status") in ("matched", "needs_review"):
            rec.update({"company": c.get("Company name") or "", "industry": c.get("Industry") or "",
                        "size": c.get("Size") or "", "country": c.get("Country") or ""})
            if c.get("Status") == "needs_review":
                checks.append("company match below the confidence floor - confirm")
        p = people.get(r["email"]) if t == "personal" else None
        if p and p.get("Status") in ("matched", "needs_review"):
            rec.update({"full_name": p.get("Full name") or "", "title": p.get("Current title") or "",
                        "linkedin_url": p.get("LinkedIn URL") or ""})
            if p.get("Status") == "needs_review":
                checks.append("person match below the confidence floor - confirm the name")
            pc = str(p.get("Current company") or "").strip().lower()
            if pc and rec["company"] and pc != rec["company"].strip().lower():
                checks.append("person's current company differs from the address's domain - may have moved")
        if rec["full_name"]:
            rec["outcome"] = "person"
        elif rec["company"]:
            rec["outcome"] = "company only" + (" (shared mailbox)" if t == "shared mailbox" else "")
        else:
            rec["outcome"] = "not found"
        rec["check"] = "; ".join(checks)
        out.append(rec)
    return out


def write(recs, output):
    outp = Path(output)
    if outp.suffix.lower() == ".xlsx":
        try:
            from openpyxl import Workbook
        except ImportError:
            outp = outp.with_suffix(".csv")
            print("openpyxl not installed - writing CSV instead.")
    if outp.suffix.lower() == ".xlsx":
        wb = Workbook()
        ws = wb.active
        ws.title = "Enriched list"
        ws.append([c.replace("_", " ").capitalize() for c in COLS])
        for r in recs:
            ws.append([r[c] for c in COLS])
        ws.freeze_panes = "B2"
        wb.save(outp)
    else:
        _write_csv(outp, COLS, [[r[c] for c in COLS] for r in recs])
    return outp


def main(argv=None):
    ap = argparse.ArgumentParser(description="Enrich a list of email addresses: triage, then merge.")
    sub = ap.add_subparsers(dest="cmd", required=True)
    t = sub.add_parser("triage")
    t.add_argument("--input", required=True, help=".csv with an 'email' column, or one address per line")
    t.add_argument("--out-dir", default="work")
    t.add_argument("--exclude-domain", action="append", default=[],
                   help="a domain never looked up, e.g. your own organisation's (repeatable)")
    m = sub.add_parser("merge")
    m.add_argument("--dir", default="work")
    m.add_argument("--people", help="person-enrich output (default DIR/people.xlsx)")
    m.add_argument("--companies", help="company-enrich output (default DIR/companies.xlsx)")
    m.add_argument("--output", required=True)
    args = ap.parse_args(argv)
    if args.cmd == "triage":
        r = triage(args.input, args.out_dir, args.exclude_domain)
        print(f"{r['addresses']} unique addresses: " +
              ", ".join(f"{k} {v}" for k, v in sorted(r["counts"].items())))
        print(f"companies.csv: {r['company_lookups']} company lookups (one per domain)")
        print(f"people.csv:    {r['person_lookups']} person lookups - run only if names/titles are needed")
        print("Webmail, invalid and excluded addresses are not looked up. Agree the lookup count "
              "(1 credit per match) before running enrich.py.")
    else:
        recs = merge(args.dir, args.people, args.companies)
        outp = write(recs, args.output)
        counts = {}
        for r in recs:
            k = r["outcome"].split(" (")[0]
            counts[k] = counts.get(k, 0) + 1
        print(f"Wrote {outp}: " + ", ".join(f"{k} {v}" for k, v in sorted(counts.items())))


if __name__ == "__main__":
    main()
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall