---
name: ai-powered-linkedin-engagement-tracker
description: >-
  A list of the people who liked or commented on your LinkedIn posts, pulled from your analytics, so reps can follow up with engaged prospects. Adapted from Daniel Disney.
  Task type: Organize. Built for Sales.
  Use when the request sounds like "LinkedIn Engagement Tracker".
  Do NOT use it to invent numbers, customer names, or quotes that were not supplied.
license: MIT
metadata:
  author: The Revenue AI Report
  suite: Marketing and Demand
  version: "1.0"
  source: https://www.therevenueaireport.com/prompts/ai-powered-linkedin-engagement-tracker
---

# LinkedIn Engagement Tracker

A list of the people who liked or commented on your LinkedIn posts, pulled from your analytics, so reps can follow up with engaged prospects. Adapted from Daniel Disney.

One job only: a list of the people who liked or commented on your LinkedIn posts, pulled from your analytics, so reps can follow up with engaged prospects. Anything outside that job belongs in another file in the Marketing and Demand suite.

## When to use this skill

- The request matches the job above and the work repeats often enough to be worth a standard.
- You have, or can ask for, the inputs listed below.
- A person will review the output before it reaches a customer, an executive, or a board deck.

## When not to use it

- The answer needs a number, a benchmark, or a quote nobody supplied. Ask for it instead of producing one.
- The task is a different job in the same suite. Open that file rather than stretching this one.
- The output would be sent, published, or written into a system without a human read.

## Inputs to collect first

- linkedin analytics data
- output

Ask for anything missing before running. Do not fill a gap with a plausible guess.

## Process

1. Confirm the job, the audience, and the decision the output feeds.
2. Collect the inputs above. Name anything still missing out loud.
3. Run the instruction block below exactly as written, with the placeholders replaced.
4. Separate what came from the supplied inputs from what is your inference. Label the inference.
5. Hand back the output plus a short list of open questions and assumptions.

## Instruction block

Run this text with the placeholders filled in.

```text
You will be working with LinkedIn analytics data to extract the names of people who have liked or commented on posts. Here are the steps to follow:

1. The data you will be working with is provided in the {$LINKEDIN_ANALYTICS_DATA} variable. This contains information about various LinkedIn posts, including details on likes and comments.

2. First, parse the data to identify the relevant sections containing information about likes and comments for each post. This may involve splitting the data into chunks by post, and then further splitting each post chunk to extract the likes and comments sections.

3. Within the likes and comments sections, look for patterns that indicate a person's name, such as strings with a capitalized first letter followed by a space and capitalized second letter (e.g. "John Doe"). You may need to account for variations like middle initials or suffixes.

4. As you identify names in the likes and comments, store them in a list or other data structure, being careful to avoid duplicates.

5. Once you have extracted all the names, format them into an output string like this:

<output>
Names of people who liked or commented:
[Name 1]
[Name 2]
[Name 3]
...
</output>

Make sure to replace [Name 1], [Name 2], etc. with the actual names you extracted, each on a new line.

If there are no names found in the data, simply output:
<output>No names found in the provided data.</output>

Let me know if you need any clarification on these instructions!
```

## Decision rules

- Supplied evidence beats inference. If the two disagree, say so and keep the evidence.
- Unknown is a valid answer. Write "unknown" rather than estimating.
- Keep one recommendation per output. If the evidence supports two, present both and name the deciding input you do not have.
- Match the reading level of a working operator. Short sentences. Explain any term the reader may not use daily.

## Quality checks

- Every number, name, date, and quote traces to an input the user supplied.
- No vendor claim is repeated as fact without naming the source.
- Assumptions are listed separately from findings.
- The output answers the original request and nothing else.
- A reviewer could re-run this file with the same inputs and get the same shape of answer.

## Guardrails

- Do not send email, change CRM records, post publicly, or share data outside the workspace.
- Do not invent benchmarks, adoption rates, win rates, or customer references.
- Flag anything that needs a human decision instead of deciding it.

## Source

- Prompt page: https://www.therevenueaireport.com/prompts/ai-powered-linkedin-engagement-tracker
- Suite: https://www.therevenueaireport.com/agent-skills/suites/marketing-and-demand
- Publication: The Revenue AI Report, https://www.therevenueaireport.com