Social Analytics Report

---
name: social-analytics-report
description: Use when you need to turn supplied social performance data into a decision about what to keep, test, change, or stop. Trigger phrases include "report on this campaign", "what worked on social?", "analyse these post results", "make a weekly social report", and "what should we do next from these metrics?". Do not use this to invent data access, claim causation from a dashboard, or replace a campaign brief; use campaign-brief to define success before launch and launch-retrospective for the broader after-action review.
---

# Social Analytics Report

Make an honest operational report from the metrics the team actually has, with context, uncertainty, and a next decision.

## 1. Establish what the data can answer

Ask for the date range, channels, posts or campaigns, metric definitions, collection method, target or baseline, and any known changes in spend, audience, format, or distribution. If definitions differ across channels, do not silently compare the raw totals.

## 2. Check the data before interpreting it

Identify missing rows, partial reporting windows, duplicate posts, changed tracking, or metrics collected at different ages. Label the report's data boundary. Separate direct observations from hypotheses about why something happened.

## 3. Read outcomes against the intended job

Group results by the job each post or channel was assigned: awareness, education, discussion, qualified traffic, conversion assistance, or creator partnership learning. Compare like with like. Look for repeatable patterns in message, format, audience context, and distribution rather than choosing one winner by impressions.

## 4. Recommend the next smallest test

Return a decision table: observation, confidence, likely explanation, action, owner, and evidence needed next. State what not to conclude. Recommend a bounded test that preserves the campaign claim and measurement method so the next report can actually compare it.

## Hard rules

- Never claim causation from correlation or a single post.
- Do not compare unlike metrics, date windows, paid and organic activity, or posts at different maturity without saying so.
- Keep raw data, calculated rates, and interpretation distinguishable.
- Do not hide low-performing or incomplete data to make a narrative look cleaner.
- Never fabricate access to native analytics, ad accounts, or conversion systems.

## Failure modes

| Failure | Do this instead |
| --- | --- |
| A high-impression post is declared successful | Judge it against the job and downstream evidence it was intended to influence. |
| A report lists metrics but makes no decision | End with one keep, one test, one change, and their owners. |
| Platform totals are compared as if identical | Normalize the question or report each channel separately. |
| The team changes five things at once | Choose the smallest observable test and hold other conditions steady where possible. |

## Where it sits

Use campaign-brief and utm-campaign-plan before publishing so the report has a decision and attribution plan. Use this skill during a campaign for operating reviews. Use launch-retrospective after the reporting window to combine results, qualitative evidence, and process lessons.