Kelpi

Audience Builder

Launch & TargetingWrites only with your approval (MCP)

Research targeting options honestly (interests, lookalikes, size estimates) and tell you when broad beats all of them. Use before a launch or when delivery seems stuck in the wrong crowd.

Install this skill

npx skills add kelpi-ai/meta-ads-skills --skill audience-builder

One command, into Claude Code, Cursor, Codex, and 60+ other agents (the open skills CLI). No account, no signup. Prefer to do it by hand?

View source on GitHub

Why this skill exists

Targeting is mostly the algorithm's job now: Meta removed exclusion options in 2025, retired interest categories in January 2026, and Andromeda aims by reading the ad. Audience work in 2026 is (a) first-party assets (customer lists, lookalikes) that give the system a seed, and (b) knowing when broad is simply better. An honest audience skill often ends with "go broad and fix the angle instead."

When to use it

  • Before launch, if you have a customer list worth seeding.
  • When delivery lands in the wrong crowd ("my ad for young women went to older men"): usually an angle problem wearing a targeting costume.
  • Needs a Meta Ads MCP (read for research, write only for creating audiences you approve).

Run it

Paste this into Claude, fill the brackets, and go. Needs a Meta Ads MCP connection.

The copy button bundles the guardrails and the output bar from below, so a plain Claude chat gets the whole skill, not just the ask.

Audience research for my offer: [ONE-LINE OFFER + WHO from my angles]

1. Search interests and behaviors related to my category. For each, give the estimated audience size.
2. If I have a customer list or purchasers: propose a custom audience plus a 1% lookalike, with estimated sizes. Draft only, do not create yet.
3. Then be honest with me: given my budget of [$X/day], would broad targeting likely beat these? Explain in two sentences using what my ad creative already signals about who it is for.
4. Wait for my pick before creating anything.

Guardrails

  • Research is read-only; audience creation happens only on explicit approval.
  • Never stack interests to feel in control. If the recommendation is broad, say broad.
  • If an ad set was built on since-retired targeting options, flag it: those stopped delivering after January 15, 2026.

Good output looks like

A short table of real options with sizes, one honest recommendation, and no audience created that you did not ask for by name.

Or let Kelpi run it

Kelpi builds and launches this for you: one simple campaign, a $20/day test, everything guard-railed and waiting for your yes before it spends. $99/mo flat, 7-day free trial, no card to start.

Related skills