Social Performance Tracker

The problem this kills

Every Monday you become a human ETL pipeline. You log into Instagram, then LinkedIn, then TikTok, then Facebook, then X - export each one's analytics, and then spend an hour wrestling them into a single spreadsheet because every platform calls the same thing something different. One says "Reach," another says "Accounts reached," a third says "Impressions." One gives you "Engagements," another makes you add likes plus comments plus shares plus saves yourself. Then you compute engagement rate five slightly different ways, paste it into a deck, and hope nobody asks how you defined it.

The numbers aren't hard. The pain is doing the normalization reliably every single week, across five exports, without double-counting a post, and turning it into one clean scorecard that someone actually signed off on before it went to leadership.

What you'll build

A small private web app for your team that:

• Imports a native analytics export CSV per platform (post, date, reach, engagements, clicks).
• Uses a saved column mapping per platform so you tell it once that "Accounts reached" means reach, and it remembers - even when platforms rename their columns.
• Normalizes everything into one schema so a LinkedIn post and a TikTok post sit in the same table with the same fields.
• Computes a consistent engagement rate (the same formula for every channel) plus the week's top and bottom posts.
• Produces a weekly cross-channel scorecard: reach, engagement rate, leaders and laggards - per platform and combined.
• Requires your social manager to review and approve the normalized data and scorecard before it goes out - the tool drafts, the person approves.
• Emails the scorecard via Resend to stakeholders and exports a consolidated CSV so nobody has to log into five dashboards.

What's inside the Implementation Plan

The plan is a complete, paste-and-go runbook. It opens by interviewing you about your business - which platforms you run, the exact column names in each export, how you want engagement rate defined, what counts as a "week," and the messy edge cases - so the tool fits how you actually report, not a generic template. The agent reads a short spec back to you and waits for your thumbs-up before it builds anything.

From there it walks you, step by step, through standing up the database, the per-platform mapping screens, the normalization and engagement-rate math, the scorecard, the approval gate, the email, and the consolidated CSV export - each step ending in a ready-to-copy prompt you paste into your AI coding agent.

The governance it includes (this is the point)

This is not a throwaway script. Every build includes:

• Login so only your team can open the tool.
• Row-level security so each organization only ever sees its own social data.
• A full audit trail - who imported which export, who approved which scorecard, and exactly when.
• A hard human-in-the-loop approval gate - the normalized data and scorecard are drafts until a person reviews and approves them, and only then is the report published or emailed.
• Duplicate guards keyed on platform + post ID + week so the same post can never be counted twice.

Who it's for

Social media managers and marketing-ops people who manually compile weekly numbers from each platform and want one consistent, auditable scorecard - without logging into five dashboards or recomputing engagement rate by hand every Monday.

You've got this - paste the first prompt and let the agent interview you.