okhp3-linkedin-network-plan
Portable, identity-agnostic Agent Skill.
Public-package data boundary
This package and its fixtures contain no execution account, person, project,
campaign, topic, bias, opinion, or private URL. Use placeholders in public
examples and obtain all such context from the current run only.
Network growth is a sequencing problem. Pick the right people, in the right
order, at a pace the platform and the sender can sustain.
Scope
This package produces a segmented target audit, a wave plan, and a feedback
loop. Note text comes from okhp3-linkedin-connection-note. Replies come from
okhp3-linkedin-message. Sending is done by the sender by hand.
Process
- Establish the goal and constraints from the current run: the audience the
sender wants more of, the audience they want less of, account type, a wave
size they can sustain, a gap between waves, and any exclusions, such as
people they must not contact or categories to skip. Without a stated goal,
return
NEEDS INPUT.
- Build the working lists from supplied data: followed-but-unconnected
accounts, existing connections by segment, pending invitations, and past
exclusions. If a list can only be read from the live site, say so and use
the sender's pasted text or export. Do not scrape.
- Audit the current mix. Count connections by segment so the bias is visible
as numbers. State the gap between the current mix and the sender's goal.
- Segment the candidates into lanes tied to the goal. Tier each person: reach
tier (high-reach, mid, peer), relevance to the sender's real work, and
whether a specific hook exists. Prefer relevance with a real hook over raw
follower count. Remove duplicates, pending invitations, existing
connections, excluded categories, and anyone flagged by a restriction the
sender supplied.
- Order the waves. Put the highest-relevance, strongest-hook targets in the
earliest waves. Spread high-reach names across waves instead of stacking
them. Hold recruiters and cold-sales profiles for a separate, deliberate
decision. Reserve a small buffer of alternates for skips.
- Build the pacing plan: wave size, business-day gap, and a check before each
wave. The check reads acceptances and declines from the last wave and adjusts
lanes. A lane with a poor acceptance rate gets fewer slots or a revised hook
approach. Use
references/wave-feedback.md.
- Keep a record the sender can reuse: wave number, name or label, lane, status
(planned, sent, pending, accepted, skipped with reason), and send date. Mark
skips such as email-gated profiles with their reason. Do not guess contact
details.
- Hand the approved wave to the sender as a manual send checklist from
references/manual-send-checklist.md. The sender sends each invitation
themselves in their own session. This package does not drive the site with
a bot, script, or browser automation, because LinkedIn's terms prohibit
automated methods to send messages or add contacts.
- Return the audit, the wave plan, the feedback checkpoints, and the risks.
Do not send anything.
Output contract
Return Audit, Segments and tiers, Wave plan, Feedback checkpoints,
and Risks and limits. For an unknown account type or an unconfirmed weekly
limit, state the assumption and the way to verify it. Do not promise a result,
an acceptance rate, or a reach number.
Validation
Before return, verify the plan serves the stated goal, every excluded or
pending person is removed, waves are within the sender's stated size and pace,
a feedback check precedes each later wave, and nothing in the plan evades a
platform limit or automates sending without human approval.
Platform boundary
LinkedIn limits and can restrict invitation volume, and its terms prohibit
bots or other automated methods to add contacts or send messages. A suspected
automation tool can lead to a restricted account. Limits change and differ by
plan, so verify current figures instead of relying on remembered numbers.
Withdrawing invitations does not lift an invitation restriction. A plan that
looks efficient on paper can still harm the account if it ignores that.
Current platform reference
Public-neutrality gate
Keep this package portable for public distribution. Do not embed a person name,
account handle or URL, private identifier, employer or organization identity,
product or project name, campaign name, or user-specific subject in instructions,
examples, references, or evaluation fixtures. Resolve account, destination,
audience, subject, links, current facts, and visibility from execution-time
context. Use placeholders or supplied evidence; platform help links may remain.
About
This package is distributed as a portable, identity-agnostic Agent Skill.
It resolves account, destination, audience, subject, and source context at execution time.
MIT License -- free to use, fork, and adapt. A nod to the source is appreciated.
1---2name: okhp3-linkedin-network-plan3description: >4 Plan a LinkedIn network expansion: audit followed-but-unconnected accounts,5 segment and tier targets toward the sender's chosen audience, dedupe against6 pending and excluded lists, pace outreach in waves, and adjust from7 acceptance results. Use when the user wants to rebalance or grow a network on8 purpose. It returns a plan and a wave list only. Do not use for sending,9 note writing, or message writing.10license: MIT11metadata:12 source: https://skillmd.com/skills/okhp3/okhp3-linkedin-network-plan13 public_artifact: true14 author: Public Agent Skill Library15 version: "1.0.0"16 category: social-posting17 origin: portable-agent-skills18 in_scope: "Planning LinkedIn outreach waves from supplied account lists, segment goals, exclusions, and acceptance feedback."19 out_of_scope: "Sending invitations, drafting notes or messages, scraping, automating, or any plan that evades platform limits."20---2122# okhp3-linkedin-network-plan2324Portable, identity-agnostic Agent Skill.2526## Public-package data boundary2728This package and its fixtures contain no execution account, person, project,29campaign, topic, bias, opinion, or private URL. Use placeholders in public30examples and obtain all such context from the current run only.3132Network growth is a sequencing problem. Pick the right people, in the right33order, at a pace the platform and the sender can sustain.3435## Scope3637This package produces a segmented target audit, a wave plan, and a feedback38loop. Note text comes from `okhp3-linkedin-connection-note`. Replies come from39`okhp3-linkedin-message`. Sending is done by the sender by hand.4041## Process42431. Establish the goal and constraints from the current run: the audience the44 sender wants more of, the audience they want less of, account type, a wave45 size they can sustain, a gap between waves, and any exclusions, such as46 people they must not contact or categories to skip. Without a stated goal,47 return `NEEDS INPUT`.482. Build the working lists from supplied data: followed-but-unconnected49 accounts, existing connections by segment, pending invitations, and past50 exclusions. If a list can only be read from the live site, say so and use51 the sender's pasted text or export. Do not scrape.523. Audit the current mix. Count connections by segment so the bias is visible53 as numbers. State the gap between the current mix and the sender's goal.544. Segment the candidates into lanes tied to the goal. Tier each person: reach55 tier (high-reach, mid, peer), relevance to the sender's real work, and56 whether a specific hook exists. Prefer relevance with a real hook over raw57 follower count. Remove duplicates, pending invitations, existing58 connections, excluded categories, and anyone flagged by a restriction the59 sender supplied.605. Order the waves. Put the highest-relevance, strongest-hook targets in the61 earliest waves. Spread high-reach names across waves instead of stacking62 them. Hold recruiters and cold-sales profiles for a separate, deliberate63 decision. Reserve a small buffer of alternates for skips.646. Build the pacing plan: wave size, business-day gap, and a check before each65 wave. The check reads acceptances and declines from the last wave and adjusts66 lanes. A lane with a poor acceptance rate gets fewer slots or a revised hook67 approach. Use `references/wave-feedback.md`.687. Keep a record the sender can reuse: wave number, name or label, lane, status69 (planned, sent, pending, accepted, skipped with reason), and send date. Mark70 skips such as email-gated profiles with their reason. Do not guess contact71 details.728. Hand the approved wave to the sender as a manual send checklist from73 `references/manual-send-checklist.md`. The sender sends each invitation74 themselves in their own session. This package does not drive the site with75 a bot, script, or browser automation, because LinkedIn's terms prohibit76 automated methods to send messages or add contacts.779. Return the audit, the wave plan, the feedback checkpoints, and the risks.78 Do not send anything.7980## Output contract8182Return `Audit`, `Segments and tiers`, `Wave plan`, `Feedback checkpoints`,83and `Risks and limits`. For an unknown account type or an unconfirmed weekly84limit, state the assumption and the way to verify it. Do not promise a result,85an acceptance rate, or a reach number.8687## Validation8889Before return, verify the plan serves the stated goal, every excluded or90pending person is removed, waves are within the sender's stated size and pace,91a feedback check precedes each later wave, and nothing in the plan evades a92platform limit or automates sending without human approval.9394## Platform boundary9596LinkedIn limits and can restrict invitation volume, and its terms prohibit97bots or other automated methods to add contacts or send messages. A suspected98automation tool can lead to a restricted account. Limits change and differ by99plan, so verify current figures instead of relying on remembered numbers.100Withdrawing invitations does not lift an invitation restriction. A plan that101looks efficient on paper can still harm the account if it ignores that.102103## Current platform reference104105- [LinkedIn Help: prohibited software and extensions](https://www.linkedin.com/help/linkedin/answer/a1341387/prohibited-software-and-extensions?lang=en) (retrieved 2026-11-09) lists bots and automated methods that send messages or add contacts as violations of the User Agreement.106- [LinkedIn Help: invitation limit reached](https://www.linkedin.com/help/linkedin/answer/a550555) (retrieved 2026-11-09) states that all members are subject to invitation limits and that a restriction lasts about a week.107- [LinkedIn Help: excessive invitation requests](https://www.linkedin.com/help/linkedin/answer/a548476/excessive-invitation-requests-sent-on-linkedin?lang=en) (retrieved 2026-11-09) says excessive invitations with suspected automation can lead to suspension or restriction.108109## Public-neutrality gate110111Keep this package portable for public distribution. Do not embed a person name,112account handle or URL, private identifier, employer or organization identity,113product or project name, campaign name, or user-specific subject in instructions,114examples, references, or evaluation fixtures. Resolve account, destination,115audience, subject, links, current facts, and visibility from execution-time116context. Use placeholders or supplied evidence; platform help links may remain.117118## About119120This package is distributed as a portable, identity-agnostic Agent Skill.121It resolves account, destination, audience, subject, and source context at execution time.122MIT License -- free to use, fork, and adapt. A nod to the source is appreciated.