Linkedin Engagement Handler logo

Linkedin Engagement Handler

Organization
swan-gtm
linkedin-engagement-handler

Use this skill when monitoring comments and reactions on a team member's LinkedIn posts. Comments get the full treatment — ICP + persona gating, CRM and account-memory logging, lead scoring, and a high-value path to connection requests and Slack alerts — while lone reactions are logged as a light touch unless the account is top-tier or a repeat engager. Repeat engagers escalate to high intent after an active-buyer check, with a personalized multi-channel draft queued for review.

Overview

Publisherswan-gtm
Repositorygtm-skills
Skill namelinkedin-engagement-handler
Stars
216
Forks
103
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by swan-gtm on GitHub. Read the source before you install it.

Installation

Install the Linkedin Engagement Handler AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/swan-gtm/gtm-skills/tree/main/skills/ariel-cohen/linkedin-engagement-handler
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/ariel-cohen/linkedin-engagement-handler .claude/skills/linkedin-engagement-handler
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkedin Engagement Handler in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Linkedin Engagement Handler on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Linkedin Engagement Handler is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Template placeholders

Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.

  • {{PROFILE_OWNER}} — Team member whose LinkedIn posts are monitored
  • {{INTERNAL_DOMAINS}} — Your company domain(s)
  • {{TEAM_MEMBERS}} — First names / known aliases of your team (engagement from them is ignored)
  • {{CRM}} — Your CRM (e.g. HubSpot)
  • {{ENGAGEMENT_CHANNEL}} — Slack channel for high-value engagement alerts
  • {{CRM_HYGIENE_SKILL}} — Sub-skill reference: how to create/update companies & contacts in your CRM
  • {{LEAD_SCORING_SKILL}} — Sub-skill reference: lead scoring & qualification methodology
  • {{ALERT_FORMAT_SKILL}} — Sub-skill reference: your alert formatting skill (optional — inline the format if you don't have one)
  • {{HIGH_ACV_TAG}} — Workspace tag marking high-ACV-potential accounts
  • {{SELF_SERVE_THRESHOLD}} — Company size below which accounts are self-serve (default: fewer than 30 employees)
  • {{ALERT_TIERS}} — Tiers that always alert on first touch (default: Gold, Diamond)

Signal type — read first

Check the event type in the webhook payload before processing:

  • New comment → full treatment (everything below).
  • New reaction (like) → light touch only: log to {{CRM}} + account memory, then stop. No connection request. No Slack alert. Exception: if the company is tagged {{ALERT_TIERS}}, or this is a repeated engagement (2+ interactions), apply the full treatment.

Comments and reactions are deliberately separate lanes: a comment is an opinion someone attached their name to; a lone like is awareness at best — volume is far higher and signal far lower.

Engagement Process

For Every ICP Lead/Agency Interaction

When someone from an ICP company or relevant agency comments on or likes {{PROFILE_OWNER}}'s post, AND they match a relevant persona:

Relevant personas (tune to your ICP's buying committee):

  • Sales Leader (CRO, SVP Sales, VP Sales, Head of Sales, Director of Sales)
  • Growth Lead (Head of Growth, Director of Growth, VP Growth, or senior marketing leader)
  • CEO (for companies in your core geographic/vertical segment)
  • Agency Owner (for agencies in your space)
  • GTM Engineer (GTM Engineer, Revenue Engineer, Marketing Engineer, Sales Engineer focused on GTM infrastructure)
  • RevOps Lead, Head of Demand Gen, CMO

Ignore engagement from:

  • CFOs, finance roles
  • CTOs, engineers, technical roles (unless they're also founders/CEOs or GTM-focused)
  • HR, operations, customer success
  • Individual contributors without buying responsibility (except the engineer-persona exception above)
  • Your own team ({{INTERNAL_DOMAINS}} domain, or known names: {{TEAM_MEMBERS}})
  • Universities, academic institutions, professors, researchers
  • Companies below {{SELF_SERVE_THRESHOLD}} (self-serve)

If the person is from an ICP company but NOT a relevant persona, ignore the engagement entirely.

Standard Processing (All ICP + Relevant Persona Engagers)
  1. Check relationship status — Are they a customer, active pipeline, or closed-lost? If yes, acknowledge but don't run the standard engagement flow.
  2. Mark awareness stage — Update the company record to your Aware stage if they're not already further along in the funnel. Never move a company backwards.
  3. Update {{CRM}} + account memory — Log the engagement (who, what they said, which post) and update the account record. Follow {{CRM_HYGIENE_SKILL}} for CRM writes.
  4. Run Lead Scoring — After processing (only when the person belongs to an identifiable company), run {{LEAD_SCORING_SKILL}}. LinkedIn engagement is the lowest-weight signal — include it in the signal stack but do not let it alone push an account above the second-lowest tier.
High-Value Path (High ACV + Decision Maker Only)

After standard processing, check if the engager's company has the {{HIGH_ACV_TAG}} tag AND the engager is a strong buyer persona (CRO, VP Sales, VP Marketing, CMO, CEO, Co-founder, RevOps Lead, Head of Demand Gen, Agency Owner, or equivalent GTM leadership).

If BOTH conditions are met:

  1. Queue a LinkedIn connection request from {{PROFILE_OWNER}}'s account for approval. Connection requests carry no note by design (better acceptance rates). Skip if already connected. (⚠️ Policy decision — see the checklist. The original deployment auto-sent these with no approval for this narrow high-ACV + decision-maker path; switch to auto-send only as a conscious opt-in.)
  2. Post to {{ENGAGEMENT_CHANNEL}} with:
    • Who engaged (name, title, company)
    • What they said (comment text)
    • Which post they commented on
    • ACV tier and why they qualify for the high-value path
    • A link to the engager's LinkedIn profile

If either condition is NOT met (not high ACV, or not a decision maker) — stop after standard processing. No connection request, no Slack post. The engagement is logged and scored silently.

Repeated Engagement (2+ Interactions)

When the same ICP lead engages 2 or more times across {{PROFILE_OWNER}}'s posts:

Active buyer check (run before any escalation): verify the engager is currently active in a buying role at the ICP company:

  • Is the ICP company their primary, active role? If they have stepped back (currently running a separate startup, recently founded a new company, or no longer day-to-day there), treat them as a non-buyer and stop — do not surface, do not sequence, do not create a task.
  • If their primary/active company is itself not an ICP fit (a 2-person startup, a personal venture studio, or self-serve territory), stop. Do not escalate on their nominal association with the larger company.
  • Partner-potential exception: a GTM operator, agency owner, or advisor who might refer clients to you gets flagged to your partnerships owner instead of routed as a buyer.

If the active buyer check passes:

  1. Move to high intent — Update their stage to MQL (high intent signal)
  2. Build a multi-channel sequence — Create a personalized multi-channel campaign, queued for review (never sent automatically):
    • Open with a question tied to your product's core problem space
    • Personalize based on their engagement history and what they do
    • Use both LinkedIn and email if available
    • Reference their repeated engagement naturally
  3. Post to {{ENGAGEMENT_CHANNEL}} flagging this as high-intent (2+ interactions), include the full engagement history, and recommend immediate follow-up. This notification fires regardless of ACV tier — repeated engagement is always worth surfacing.
  4. Load {{ALERT_FORMAT_SKILL}} for the alert format (or inline your format here).

First-touch alert-tier rule: Even on a first interaction, if the engager's company is tagged {{ALERT_TIERS}}, immediately post to {{ENGAGEMENT_CHANNEL}} with a high-priority flag. Do not wait for a second interaction.

Lead Magnet Posts

Some posts may offer a lead magnet (e.g., "Comment X to get Y"). When this happens:

  1. Current lead magnet: There is no active lead magnet at this time. Do NOT share any URLs or documents. Treat commenters on lead magnet posts with the standard processing flow.
  2. Future lead magnets — {{PROFILE_OWNER}} updates this section before each new lead magnet post with the post topic and corresponding URL. The skill only ever shares the URL written here — never an inferred or remembered one.

Key Principles

  • Track ALL comments and reactions (likes) from ICP companies and agencies
  • High-value path (connection request + Slack) only fires for high ACV + decision maker — don't burn {{PROFILE_OWNER}}'s connection budget on low-value targets
  • Repeated engagement always gets surfaced, regardless of ACV tier
  • Always personalize based on what they said
  • If outreach is needed, build the campaign — don't just recommend reaching out
  • Keep initial outreach warm and helpful, not salesy
  • LinkedIn engagement is the lowest-weight signal — capped at the second-lowest tier unless stacked with other signals

What good looks like

A great run processes only engagers who clear both gates — ICP company and buying persona — and the high-value path fires precisely: high-ACV tag plus decision maker, nothing else. Repeat engagers get a personalized multi-channel draft queued for review with their full engagement history attached, and every alert includes what the person actually said.

Lone reactions stay in their light-touch lane, and repeat engagers who have stepped back from the ICP company get caught by the active-buyer check instead of escalated.

Mediocre looks like: full-treatment alerts fired on a lone like, connection requests burned on individual contributors, engagement alone driving Gold or Diamond tiers, alerts without the comment text, or sequences going out without review.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Linkedin Engagement Handler AI skill do?

Use this skill when monitoring comments and reactions on a team member's LinkedIn posts. Comments get the full treatment — ICP + persona gating, CRM and account-memory logging, lead scoring, and a high-value path to connection requests and Slack alerts — while lone reactions are logged as a light touch unless the account is top-tier or a repeat engager. Repeat engagers escalate to high intent after an active-buyer check, with a personalized multi-channel draft queued for review.

Why use Linkedin Engagement Handler on TypingMind?

Because you install it once and use it with any model. Linkedin Engagement Handler is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Linkedin Engagement Handler in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan-gtm/gtm-skills/tree/main/skills/ariel-cohen/linkedin-engagement-handler. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Linkedin Engagement Handler?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Linkedin Engagement Handler?

As many as you like. As long as a model supports skills, you can use Linkedin Engagement Handler with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Linkedin Engagement Handler AI skill free?

Yes. It is published on GitHub by swan-gtm under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇