agentleFS
gooseworks-aigooseworks-ai/goose-skills/skills/marketing/research-audience-people-and-contacts/SKILL.md

research-audience-people-and-contacts

Skill1.3k starsChanged 23 days agoMITView on GitHub

For a list of companies, picks 1-3 current people per company in different buying roles, confirms each title with a dated source, finds a public contact route, labels email status honestly and flags regions with contact rules. Never contacts anyone. Use alone when you already have a vetted company list and the buyer titles; otherwise run research-audience.

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 1 mentionJun 2026: 0 mentionsJul 2026: 2 mentionsAug 2026: 1 mentionSep 2026: 0 mentionsOct 2026: 15 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the gooseworks-ai/goose-skills repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about gooseworks-ai/goose-skills

The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 20

Talked about on GitHub (20 times).

On GitHub · 20

15 more on GitHub

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:

    Rules: never label an address verified unless a checker said so.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

people-and-contacts

Reads: passing accounts; personas and title synonyms; ../research-audience/references/contacts-and-compliance.md; ../research-audience/references/data-sources.md.

Does:

  1. Free first, breadth before depth: for every kept account, get names and titles from the cheapest place first — the company's team, about and leadership pages, press releases, conference speaker pages, podcast guest pages, public profile headlines in web-search results ("<title>" "<company>"), the company's LinkedIn page's public people list. Paid profile reads only in the approved top-up, to confirm titles the free pass could not.
  2. Pick by company size and role (champion + economic buyer; category buyer for retail). Max 3 per account, different roles.
  3. Confirm current employer and title from a dated source (a dated search headline counts, labelled search-headline); if sources disagree, the newer wins; if unclear, drop. Chains → an account row with the vendor portal or buying-office route, plus 1–2 person rows (same account_id) for a category buyer confirmed by a dated source: LinkedIn route, email only if published or pattern-evidenced. Leave person rows out only when the retailer's vendor page says portal-only or not to contact buyers — note it in notes. Independent shops and small venues → one account-level row with the shop's published inbox (own-domain or published webmail) or IG/DM as the route; the owner's name only if a dated source gives it — an unnamed owner is not a reason to drop. Drop third-party recruiters and consultants (people who don't work for the account), fractional/advisor, interns, ex-, agency staff named for a client, competitor and own staff. When the account is a recruiting or staffing firm, its recruiters, sourcers and researchers are the users and champions — keep them.
  4. Contact route — when the connector has email find and check, follow ../research-audience/references/data-sources.md § When the contact routes exist (cheapest first, stop at the first found address the checker passes — one checker, a second only on unknown — never phones or personal modes). Otherwise: look for the exact work address on public pages (team page, press release, filing, speaker bio). Found → email_candidate with status published (<url>) (an address moves to email only after a checker passes it). Pattern-guess only when a published address at the same domain shows the pattern — cite it. A shop's own published webmail address counts as published. Otherwise record the best other route (LinkedIn, buying inbox, contact form, phone, IG for small shops).
  5. Set the person's location and region_flag; exclude Germany/Austria by default unless the human said otherwise; flag UK sole traders/partnerships UK-soletrader: consent needed (Companies House check) and give them a visit or a letter as the route (other_contact_route = visit/letter: <published shop address> (<url>)) (phone only after a TPS check, noted; never a cold IG DM), with email blank; a Canadian or AU/NZ pattern-guess is not sendable — give another route or drop; other countries flagged other:<country>.
  6. Suppression check: hash each person's keys the ledger's way (outcomes-ledger § Suppression without personal data) and drop any that match a suppressed key_hash — before any paid lookup on them.

Writes: people rows with title source and date, email (checker-passed only), email_candidate, email_status, email_source, other_contact_route, person_location, region_flag, persona_role.

Rules: never label an address verified unless a checker said so. Never use personal webmail or role addresses for people at companies with a named buyer (independent shops' published inboxes are the exception, as account rows), or anything behind a login.

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.