agentleFS
automatewithudayautomatewithuday/GTM-Public-Traded-AI-Accounts/.claude/skills/people/SKILL.md

people

Skill0 starsChanged 4 months agoMITView on GitHub

Find decision-makers (name, title, LinkedIn, public email) for qualified accounts via Parallel research. Use after /score qualifies companies, or when asked for contacts at an account.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. pantalytics/odoo-mcp-pro★ 92same name
    2. flowing-abyss/obsidian-vault-skills★ 9same name
    3. calebnewtonusc/Chewbacca★ 8same name
    4. ajsai47/aic-agi★ 0same name
    5. yourbeckett/beckett-for-claude★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Run (capped by config people.max_companies_per_run, default 10):

    line 14
  2. Very specific:

    If one account's task fails or times out, the batch continues without it and the company keeps its qualified status.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 5 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

/people — decision-maker search for qualified accounts

Preview which companies/roles would be searched (no spend):

uv run python -m pipeline people --dry-run

Run (capped by config people.max_companies_per_run, default 10):

uv run python -m pipeline people --limit 5
# or a single account:
uv run python -m pipeline people --ticker XYZ

How targeting works: each qualified company's latest service_fit picks target roles — from config/personas.yaml's services mapping when the active pack has one (e.g. lead-gen fit → CMO/CRO/VP Marketing; custom agents → CTO/CIO), else the legacy flat people.roles_by_service list — plus always_include_roles (CEO — micro-caps often buy top-down). One Parallel task per company researches names, exact titles, LinkedIn URLs, and publicly listed emails only (source URL + confidence stored; no guessing, no pattern-inventing).

Personas also carry pains/language per role (not just target titles) — /outreach attaches the matched persona's pains and language to each contact's message packet for personalization, so a contact's role_bucket (even a legacy value like "CEO" already in the DB) or title is enough to pull role-specific copy material later.

Run mechanics:

  • Run multi-account batches in the background and report from the final stats + DB — tasks are created up front and polled together, so a 10-account batch ≈ one task's duration (~2–4 min).
  • If one account's task fails or times out, the batch continues without it and the company keeps its qualified status; retry just that account with --ticker X.

After running:

  • Table per company: name, title, role bucket, LinkedIn, email (or —), confidence.
  • Companies move to contacts_found.
  • Flag companies where key roles came back empty (tiny micro-caps often have no CMO — the CEO is the buyer).
  • Suggest uv run python -m pipeline export for a CSV of qualified accounts + contacts.

Next stage: /outreach drafts per-contact message sequences from angles (v2). Still no sending or CRM push.

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.