agentleFS
Sign inStart free
zalogarciazalogarcia/zalo-claude-code-setup/skills/bu-cold-outreach/SKILL.md

bu-cold-outreach

Skill2 starsChanged 51 days agoNo licenceView on GitHub

Run Black Umbrella's own cold DM outreach. Triggers "run today's cold outreach", "cold DM batch", "outreach replies", "bu outreach", "approve the batch and send", "outreach report". Astra executes it in the codex-bare Codex session with Computer Use, sending from Zalo's real LinkedIn, Facebook and Instagram accounts in Chrome, to HVAC and plumbing owner operators countrywide (whatever metros prospects.csv holds; tranche 1 is twelve Sun Belt metros plus a nationwide LinkedIn rail), and since 2026-10-06 on LinkedIn only to home service managers and owners active on LinkedIn in the last 30 days (the Apify hunt), on a dated ramp with acceptance gates. From 2026-10-22 (Zalo, 2026-10-16) LinkedIn is CONNECTIONS ONLY to offer owners (coaches, consultants, course and program creators who sell through sales calls or DMs, active by Ty's photo, headline and last post checks, tier O, prospects-offer-owners*.csv): note-less connection requests, 40 a day Monday to Friday 08:00 to 12:00 ET, at most 200 in 7 days, automatic stops, no LinkedIn message of any kind (Zalo DMs every accept by hand; a daily accept report lists them), and the home service ICP is RETIRED for new LinkedIn prospects. Enforces ONE message per prospect until that prospect replies (no bumps, no multi part first touch), the request first rule (a note-less friend request on Facebook and a note-less connection request on LinkedIn come first, and the one message goes only into the thread after the accept; open profile and InMail cold lanes retired 2026-10-04), all checked by the batch lint against pipeline.csv and sent-log.csv, the message's four beats with no pitch and no link, the per channel caps, the ramp, the pacing, the stop on warning rule, and the approval mode in config.md. Not the course outreach-operator skill, which is for CMAA members sending by hand.

The file

Show its rules and text

We split this skill into the rules it gives an agent

26 rules. About 0 are common, 12 are distinctive, and 14 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 14

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.

Check your setup, free