LinkedIn Engagement Follow-up

Identify useful conversations in a post’s comments and draft replies that address what people actually said.

v0.2.0

View example draft · How to use

Example draft

Replies for a discussion about personal agents

Public comments under a Stripe post about personal agents and AI cost measurement.

A question about measuring value

I'd separate cost per attempted task from cost per accepted outcome, and include human review and rework in the latter. For a reviewed contract, what would your team count as an accepted outcome?

A question about approval boundaries

Where would you put the approval boundary for a personal agent: before it chooses a tool, or before the tool changes an external system? What evidence would you want the user to see at that point?

Original English reply drafts. The examples ask questions and propose a measurement approach; no message was sent and no commenter is presented as a buyer.

What you get

  • Evidence-based fit list and useful follow-up drafts

Good fit

  • Responding thoughtfully to public questions
  • Separating relevant discussion from praise and promotion

Not for

  • Automatic messages, connection requests or monitoring
  • Treating job titles, reactions or comments as confirmed buying intent

How to use

Supplied material works without API calls. Live data uses your SandBase connection and current API pricing; eligible calls share the daily free quota.

Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.

Download Skill v0.2.0

Ask your Agent

Use linkedin-engagement-followup. Start from the account, link, topic or material I provide, and use SandBase where needed to complete the requested task. Deliver: Evidence-based fit list and useful follow-up drafts

  1. Read the post, comments and necessary individual role context

  2. Apply the task rules to observed evidence

  3. Check and deliver the native result with limits

FAQ

How do I use this Skill?

Download and unpack the whole Skill folder, including references, into your Agent’s supported Skill directory. You can also ask the Agent to read its SKILL.md and follow the instructions. Run it locally with your own material.

Will it send the replies?

No. It prepares a review and drafts. You choose whether and where to use them.