agentleFS
prosyo-aiprosyo-ai/gtm-skill/skills/post-engagement-outreach/SKILL.md

post-engagement-outreach

Skill13 starsChanged 25 days agoMITView on GitHub

Use this skill when people engage with LinkedIn posts (yours, your team's, a competitor's or an industry voice's) and you want to turn that engagement into conversations: \"reach out to people who liked our post\", \"warm outreach from post engagers\", \"turn commenters into leads\". Filters engagers to your ICP, ranks them by the strength of engagement, and writes a natural follow-up that continues the topic of the post instead of pitching.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Use this when a post has drawn reactions and comments from people who might be buyers.

    line 16
  2. Distinctive:

    MUST filter engagers against the ICP before writing.

    line 58
  3. Distinctive:

    MUST stay within daily LinkedIn activity limits.

    line 59
  4. Distinctive:

    NEVER pitch in the connection note.

    line 60
  5. Distinctive:

    NEVER say you saw someone react to a third party's post.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this when a post has drawn reactions and comments from people who might be buyers. Engagement shows interest in a topic; the follow-up continues that topic and lets the conversation find the business problem.

Inputs

  • The engagers: name, title, company, and how they engaged (reaction, comment, share).
  • The post: author, topic and the point it made.
  • The ICP.

The play

1. Filter hard

Typically 70-90% of engagers are outside any ICP: peers, vendors, recruiters, job seekers, friends. Keep only ICP fits. Remove competitors and current customers (route customers to the account owner instead).

2. Rank by engagement strength

EngagementStrength
Thoughtful comment adding a view or a questionStrongest
Share with their own commentaryStrong
Short comment ("Great post!")Medium
Reaction onlyWeak
Engaged with two or more posts on the topic in 30 daysBoost one level

3. Decide the source angle

  • Your own or your team's post: you can reference it directly; they engaged with you.
  • Someone else's post (an industry voice, a competitor): reference the topic, not the fact you saw their reaction. Keep it light.

4. Write the follow-up

Connection note: 1-2 sentences continuing the topic. After they accept: a question that bridges the topic to their situation. No pitch until they show the problem is real for them.

Connection note: "Your comment about ramp being a data problem stuck with me. Would be good to have you in my network."

After accepting: "Curious how you handle that at Lumen. Do new reps build their own lists, or does someone hand them accounts on day one?"

What good looks like

  • Under 25% of engagers make it through the filter. If 80% do, the filter is too loose.
  • Messages reference the idea in the post, not the act of liking it.
  • Commenters get a personal reference to what they actually said.
  • The common mistake is mass-messaging every reaction with "Thanks for liking my post! Want a demo?"

Rules

  • MUST filter engagers against the ICP before writing.
  • MUST stay within daily LinkedIn activity limits.
  • NEVER pitch in the connection note.
  • NEVER say you saw someone react to a third party's post.

Example prompts

  • "Here are 140 people who engaged with our founder's post on SDR ramp. Who should we reach out to and with what?"
  • "Write connection notes for the 12 commenters who fit our ICP."
  • "Turn engagers on this competitor's post into a warm outreach list."

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.