mcpField
P
performance-analyst

performance-analyst

github.com/kelpi-aiMarketing & growth557 installsUpdated 17w ago
Repository

About performance-analyst

A marketing skill for evaluating Meta ad performance through business outcomes rather than platform metrics alone. It produces a concise weekly readout with evidence-based decisions and explicit caveats about attribution and sample size.

Key features

  1. 0130-day ad performance review
  2. 02Spend rollups by angle
  3. 03Best and worst spend allocations
  4. 04Attribution and sample-size caveats
  5. 05Supported decision summary

Use cases

  1. 01Reviewing Meta ads each week
  2. 02Deciding whether to scale, stop, or rebuild
  3. 03Separating platform attribution from store or CRM results

MCP support

Uses a Meta Ads MCP with read access to analyze ad performance.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kelpi-ai/meta-ads-skills --skill performance-analyst

After installing, type/performance-analystin Claude Code to confirm it loaded.

Bundled filesskill.meta.json

Details

From the project README

Performance Analyst

Doctrine

Platform dashboards are a signal, not the truth: Meta grades its own homework, attribution flatters, and "great ROAS" can hide zero incremental revenue. The analyst's job is to say what the data supports, say what it does not, and refuse to fill gaps with optimism. Vanity metrics (reach, impressions, clicks) answer "did people see it"; the business question is "did the loop close": what did a customer cost, what did they pay you back, how fast.

When to use

  • Weekly, same day, 15 minutes.
  • Before any big decision: scale, kill, or rebuild.
  • Needs a Meta Ads MCP, read access.

Run it

Weekly read, READ-ONLY:

1. Last 30 days by ad, sorted by spend: spend, results, cost per result, CTR, CPM, frequency. Roll it up by ANGLE, not just by ad.
2. My three best and three worst spend allocations, in plain sentences ("$X went to Y and bought Z").
3. Then the honest caveats, every time:
   - which numbers depend on Meta's attribution (and would look different in my store/CRM data),
   - where the sample is too small to conclude anything,
   - what I would need to track to know the truth (blended cost per customer: total spend / total new customers, from MY records, not Meta's).
4. End with the at-most-3 decisions this data actually supports, and the decisions it does NOT support yet.

Guardrails

  • Never present platform ROAS as business truth. Pair it with the blended number or mark it unverified.
  • "The sample is too small" is a finding, not a failure. Say it whenever it is true.
  • Roll up by angle: individual ad noise hides the message-level pattern that actually matters.

Good output looks like

A page a busy owner reads in two minutes: what the money did, what we actually know vs what Meta claims, and 1-3 supported decisions.

Comments

Markdown supported