agentleFS
NadavShanun-designNadavShanun-design/opengtm/skills/linkedin-outreach/SKILL.md

linkedin-outreach

Skill4 starsChanged 29 days agoMITView on GitHub

Use when reaching prospects on LinkedIn - connection requests, DMs, engaging with their posts, and social selling. Covers the no-pitch-first rule, comment-before-connect, profile-based personalization, note vs no-note invites, respecting LinkedIn's invite limits and account safety, and a sane follow-up cadence. For overall cadence design see multichannel-sequences.

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cold-email.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ukunal91appSkill

    cold-email

    Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaigns, sales development emails, or SDR emails. Also use when the user mentions "cold outreach," "prospecting email," "outbound email," "email to leads," "reach out to prospects," "sales email," "follow-up email sequence," "nobody's replying to my emails," or "how do I write a cold email." Covers subject lines, opening lines, body copy, CTAs, personalization, and multi-touch follow-up sequences. For warm/lifecycle email sequences, see email-sequence. For sales collateral beyond emails, see sales-enablement.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Never run aggressive automation that mimics a bot - human-paced, business-hours, with natural gaps.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 7 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

LinkedIn outreach

Overview

LinkedIn is a relationship channel wearing a sales channel's clothes. The pitch-on-connect move that everyone hates converts terribly and gets accounts restricted. What works: show up as a relevant human first, earn the connection, then have a normal conversation.

No-pitch-first rule: the connection request is not the pitch. Its only job is to get accepted.

The sequence that works

  1. Engage before you connect. View the profile, then leave one genuine, specific comment on a recent post. You become a familiar name before you ask.
  2. Send the invite. A note barely moves acceptance either way - but a relevant note (about them, never a pitch) can roughly double your reply rate after they accept. Keep any note under ~300 characters. ("Enjoyed your post on X - keen to follow your work.")
  3. Wait for accept. Then still don't pitch. First DM is a human opener that references why you connected. Earn the reply.
  4. Then, one soft ask tied to a real reason. One ask, like email.
  5. Follow up 1-2 times max, spaced days apart, each adding value.

Personalize from the profile

Their LinkedIn is a gift: recent posts, role change, company news, shared groups, mutual connections, what they say matters. One true, specific reference beats any "I came across your profile." (See outreach-personalization.)

Respect the limits (account safety)

  • LinkedIn caps connection invites. LinkedIn itself publishes no number; the widely practitioner-observed ceiling is ~100 invites/week (rolling 7 days). Safe pace is ~10-25/day, and new accounts should ramp from ~5-10/day. Going over triggers a (typically one-week) restriction - and withdrawing pending invites does not lift it.
  • Warm up a new/automated account slowly - low activity first, ramp over weeks, mix real browsing and engagement with outreach.
  • Withdraw stale pending invites periodically (a high pending/ignored ratio hurts you).
  • Never run aggressive automation that mimics a bot - human-paced, business-hours, with natural gaps.

Social selling (the long game)

For high-value accounts, outreach and content compound: post useful things, comment in your buyers' threads, react genuinely. When you finally DM, you're not a stranger. The best LinkedIn pipeline often starts as engagement, not outreach.

Do / Don't

  • Do comment on a post before connecting, and keep the invite pitch-free.
  • Do stay under the weekly invite limit and pace like a human.
  • Don't pitch in the connection note or the first DM.
  • Don't auto-blast invites - it's the fastest way to a restricted account.

Common mistakes

  • Pitch-on-connect (instant ignore + "I don't know this person" flags).
  • Hitting the invite ceiling and getting the account throttled.
  • Copy-paste DMs with a visible {{firstName}} or no personal reference.
  • Treating LinkedIn like a second email inbox instead of a relationship channel.

Go live with Chronos (optional)

  • geo_linkedin_search - find prospects matching your ICP on LinkedIn.
  • geo_linkedin_get_prospect_profile / geo_linkedin_list_prospect_posts - pull the facts to personalize.
  • geo_linkedin_comment_on_post / geo_linkedin_react_to_post - engage before connecting.
  • geo_linkedin_send_connection_request - send paced, note-optional invites.
  • geo_automate_linkedin_dms / geo_send_paced_dm_batch - paced, human-timed DMs (never bursts).
  • geo_set_linkedin_autoenroll, geo_list_linkedin_dms, geo_stop_linkedin_followups - manage the flow.

Chronos paces LinkedIn actions to stay within safe limits on your connected seat.

Connect in ~30s → CONNECT-CHRONOS.md. Free, no card.

See also: multichannel-sequences, outreach-personalization, account-research.

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.