audience-builder
Skill3 starsChanged 5 months agoMITView on GitHub
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.
In this repository15 other files it gives its agents.
- angle-writerSkill
- brand-readerSkill
- budget-pacerSkill
- buyer-language-minerSkill
- catalog-commerceSkill
- competitor-ad-teardownSkill
- copy-formulasSkill
- creative-directorSkill
- daily-auditorSkill
- fatigue-detectorSkill
- lead-gen-builderSkill
- media-buyerSkill
- pain-to-promiseSkill
- performance-analystSkill
- pixel-conversionsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before launch, if you have a customer list worth seeding.
- Distinctive: line 13
When delivery lands in the wrong crowd ("my ad for young women went to older men"): usually an angle problem wearing a targeting costume.
- Distinctive: line 29
Never stack interests to feel in control.
- Distinctive: line 30
If an ad set was built on since-retired targeting options, flag it: those stopped delivering after January 15, 2026.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Audience Builder
Doctrine
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
- 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
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

