LinkedIn Top-Post Analysis

The file

---
name: ai-driven-linkedin-analytics-top-performing-post-analysis
description: >-
  Your top-performing LinkedIn posts ranked from your analytics data, with the themes that drive engagement. Adapted from Daniel Disney.
  Task type: Analyze. Built for Sales.
  Use when the request sounds like "LinkedIn Top-Post Analysis".
  Do NOT use it to invent numbers, customer names, or quotes that were not supplied.
license: MIT
metadata:
  author: The Revenue AI Report
  suite: Outbound and Prospecting
  version: "1.0"
  source: https://www.therevenueaireport.com/prompts/ai-driven-linkedin-analytics-top-performing-post-analysis
---

# LinkedIn Top-Post Analysis

Your top-performing LinkedIn posts ranked from your analytics data, with the themes that drive engagement. Adapted from Daniel Disney.

One job only: your top-performing LinkedIn posts ranked from your analytics data, with the themes that drive engagement. Anything outside that job belongs in another file in the Outbound and Prospecting 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
- prompt

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 analyzing LinkedIn analytics data to identify the top performing posts. Here are the steps to follow:

1. First, prompt the user to provide the LinkedIn analytics data by outputting:
<prompt>Please provide the LinkedIn analytics data you would like me to analyze:</prompt>

2. Once the user has provided the data, store it in the {$LINKEDIN_ANALYTICS} variable.

3. To identify the top performing posts based on impressions:
- Look at the "Impressions" column in the data
- Sort the rows in descending order by the "Impressions" values
- The post(s) with the highest "Impressions" value are the top performers based on impressions

4. To identify the top performing posts based on likes:
- Look at the "Likes" column 
- Sort the rows in descending order by the "Likes" values
- The post(s) with the highest "Likes" value are the top performers based on likes

5. To identify the top performing posts based on comments:
- Look at the "Comments" column
- Sort the rows in descending order by the "Comments" values 
- The post(s) with the highest "Comments" value are the top performers based on comments

6. Provide the top performing posts in the following order:
<Top Posts>
Impressions:
List the post title(s) and impressions value(s) of the top post(s) by impressions

Likes: 
List the post title(s) and likes value(s) of the top post(s) by likes 

Comments:
List the post title(s) and comments value(s) of the top post(s) by comments
</Top Posts>

Make sure to analyze the provided {$LINKEDIN_ANALYTICS} data thoroughly. 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-driven-linkedin-analytics-top-performing-post-analysis
- Suite: https://www.therevenueaireport.com/agent-skills/suites/outbound-and-prospecting
- Publication: The Revenue AI Report, https://www.therevenueaireport.com