agentsclimarketplace

Linkedin growth

Skill social-media-skills/skills/skills/linkedin-growth

106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.

Install
npx -y skills add social-media-skills/skills --skill linkedin-growth

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

The LinkedIn personal-profile growth playbook for 2026. Use when someone wants to "grow on LinkedIn," "get more LinkedIn followers/reach," "a LinkedIn strategy," "how the LinkedIn algorithm works," or how to use commenting/newsletters/video/connections to grow. Dwell time + early meaningful comments are the engine, personal profiles massively out-reach company pages, links go in the first comment, and strategic commenting on target accounts is the cheapest reach on the platform. Uses the LADDER framework. Reads brand-profile + voice-builder first. The agent drafts posts + comment copy and designs the system; a human does the live commenting/connecting/DMs; WoopSocial schedules posts; metrics come from native LinkedIn analytics (SSI as a directional check); nothing is fabricated. Single-post craft → linkedin-post-writer; company page → linkedin-company-pages.

SKILL.md

7.3 KB, ~1.5k tokens by cl100k_base, as published. Nobody here has run it

linkedin-growth

The LinkedIn personal-profile growth engine — the profile as a landing page, what to post and how often, strategic commenting on target accounts, the golden hour, newsletters/video, and connections vs followers. The agent drafts posts + comment copy and designs the system; a human does the live commenting/connecting; scheduling-and-queue → WoopSocial publishes the posts. Complements linkedin-post-writer (the single-post craft) and linkedin-company-pages (the page).

The POV: dwell + comments, on a personal profile

LinkedIn's algorithm rewards dwell time (people actually reading) and early, meaningful comments — likes barely move distribution, and engagement bait is down-ranked. The feed is structurally tilted to people, not logos (personal profiles get ~65% of feed allocation; pages ~1–5%), external links in the body suppress reach (put them in the first comment), and posts now have a long shelf life via suggested feeds — a good post travels for days or weeks. The cheapest growth lever isn't posting more: it's thoughtful comments on bigger accounts in your niche, which put your name in front of their audience daily. And in a feed where ~half the long posts are AI-written, a specific, lived, first-person POV is the differentiator — not volume.

Read these first

  1. brand-profile — positioning, audience, non-negotiables.
  2. voice-builder — so posts and comments sound like one credible human.

The framework: LADDER

(Depth: references/the-ladder-framework.md.)

  • L — Landing-page profile: headline = value proposition (not job title); About opens with the 3 visible lines; Featured = the CTA; Follow-primary once inbound outpaces outbound. Every post's job ends at a profile visit — the profile converts it. → profile-optimization.
  • A — Author for dwell: win the "…see more" tap, format for the read, mix text / document carousel / native video / newsletter; link in the first comment. → linkedin-post-writer.
  • D — Deploy strategic comments: 5–10 substantive comments/day on target accounts in the niche — the afterburner. A comment is content, not a courtesy. → reply-and-comment-writer.
  • D — Drive the golden hour: first 60–90 min decides reach; post in the audience window, reply to every comment, comment around your own post time. Max 1 post/day, 3–5/week.
  • E — Expand with native surfaces: newsletter (notification + email push), native video (the 2026 push), audio events; SSI as a directional health check, never the goal.
  • R — Relationships & network hygiene: connections (capped, ~100 invites/week) vs followers (unlimited); no-pitch invites; DMs warm, not pitch-slaps. → social-selling-and-dm.

The reality (verify-quarterly)

Feed allocation and reach decline, dwell + comment weighting, the golden hour, link suppression, format hierarchy (carousels/video/text), the see-more cutoff, creator mode's retirement, connection caps, newsletters, SSI, the AI-content flood, cadence: references/linkedin-2026-reality.md. Post types + the commenting playbook + worked examples: references/comment-and-post-recipes.md.

Honest scope (never violate)

  • The engagement core is human — the agent drafts posts, comment copy, invite notes, and DM openers; a human posts the live comments, sends invites, and holds the conversations. No auto-commenting, no auto-connect tooling (a restriction risk on LinkedIn specifically).
  • WoopSocial schedules the posts (text + media + optional link; native document carousels, polls, newsletters, and audio events are posted/run natively). No update → delete + recreate. For link-in-first-comment, the agent supplies post + comment; the pair is posted by tool/human.
  • No analytics in WoopSocial → read native LinkedIn analytics (impressions, members reached, profile viewers, followers) and SSI as a directional check. Never fabricate metrics.
  • No engagement bait, pods, mass-tagging, bought followers, or broetry theatre — down-ranked by the algorithm and quietly judged by the exact professionals you're trying to reach. (Scope, distinctions + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

linkedin-growth (this) = the PERSONAL-profile growth system (profile, cadence, commenting, golden hour, features, network) · linkedin-post-writer = how to write one post well · linkedin-company-pages = the page strategy + employee advocacy (advocates' personal posting routes back here) · reply-and-comment-writer = drafting the comments/replies themselves · engagement-routine = the recurring daily engagement block · social-strategy = the cross-platform plan.

Where this connects

Reads first: brand-profile, voice-builder. Post craft: linkedin-post-writer, hook-writer, carousel-writer (document-carousel slides), talking-head-and-piece-to-camera (native video). Profile: profile-optimization. Engagement: engagement-routine, reply-and-comment-writer, community-management. Discovery: social-seo (headline/About keywords), ai-search-optimization (LinkedIn is a B2B AI-answer source), trend-jacking. Pipeline: social-selling-and-dm, lead-magnets-and-funnels; long-form owned channel: email-and-newsletter. Plan/measure: social-strategy, goals-and-kpis, analytics-and-reporting (native LinkedIn analytics). Publish: scheduling-and-queue → WoopSocial (posts; live comments/invites/DMs are human).

Definition of done

A profile audited as a landing page (headline = value prop, Featured = CTA, Follow-primary decision made); a 3–5 posts/week plan, max 1/day, with links in the first comment and format mix mapped to dwell; a named list of 10–20 target accounts with a 5–10 comments/day playbook (drafted by the agent, posted by a human); a golden-hour routine (audience window, reply-to-every-comment); native surfaces decided deliberately (newsletter yes/no, video cadence); connection-request hygiene with no-pitch invite copy; posts routed to scheduling-and-queue → WoopSocial with live engagement flagged human; metrics from native LinkedIn analytics + SSI directionally; no bait/pods/bought followers/ broetry; correctly distinguished from linkedin-post-writer and linkedin-company-pages.

Gives 0 of the 12 instructions most product growth skills give in ~1.5k tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 24 of 728, across 15 files
  • define the ideal customer profilein 21 of 728, across 3 files
  • document a rollback plan before deploymentin 21 of 728, across 12 files
  • analyze the codebase to understand the productin 19 of 728, across 1 file
  • ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • search for companies matching the criteriain 19 of 728, across 1 file
  • look for signals of immediate needin 19 of 728, across 1 file
  • assign a fit score from one to tenin 19 of 728, across 1 file
  • identify the target decision maker rolein 19 of 728, across 1 file
  • suggest a personalized contact strategyin 19 of 728, across 1 file
  • provide conversation starters for outreachin 19 of 728, across 1 file
  • format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • read brand-profile and voice-builder first
  • treat the profile as a landing page
  • draft five to ten comments daily
  • limit posting to one post per day
  • reply to every comment during the golden hour
  • cap connection requests at one hundred weekly

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.