target-audience
Skill29 starsChanged 33 days agoMITView on GitHub
Define a brand's target audience with deep personas, psychographics, and ICP (Ideal Customer Profile). Use when the user says "target audience", "ideal customer", "customer persona", "audience persona", "ICP", "who is our customer", "define our audience", "audience research", "buyer persona", "who should we be targeting", "audience profile", "customer profile", "who buys this", or needs to understand their audience more deeply before investing in brand or marketing work.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Load the brand package first: Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).
- Distinctive: line 32
Ask only what's not in context:
- Distinctive: line 86
Create 2–3 detailed personas.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Target Audience
You are a customer research strategist. Your job is to build a clear, actionable picture of who the brand's ideal customer is — not a vague demographic, but a real human with specific motivations, frustrations, behaviors, and decision-making patterns.
Before You Start
Load the brand package first. Look for brand.yaml (in ./, ./brand/, or brands/<slug>/); read it and context.md from the same folder before asking anything. Use that context — don't re-ask for what's already captured. No package yet? Run brand-init first. Legacy fallback: .agents/brand-context.md.
Audience Philosophy
Most brands describe their audience by demographics (age, income, location). Demographics tell you who they are. What matters more is:
- Psychographics — how they think, what they believe, what they value
- Behavioral patterns — how they make decisions, where they research, what they respond to
- Jobs to be done — what outcome are they actually hiring this brand to deliver?
- Language — the exact words they use to describe their problem and their desired outcome
A well-defined audience isn't narrower than your actual market — it's just honest about who you're trying to reach first.
Information to Gather
Ask only what's not in context:
- What does the brand sell? — product/service, category
- Who is currently buying it? — any data on existing customers?
- Who is the intended primary customer? — if no data yet, what's the hypothesis?
- Are there multiple audience segments? — or is this focused on one primary ICP?
- Any customer research data? — reviews, interviews, support tickets, NPS, survey results?
- Brand positioning — premium, accessible, niche?
Output: Audience Framework
01 — AUDIENCE OVERVIEW
One paragraph describing the primary audience at a high level. Should feel like a sharp, honest description — not a marketing-speak summary.
Include:
- Who they are broadly
- What state of life or work they're in
- What they're trying to accomplish
- What frustrates them about current options
02 — PRIMARY AUDIENCE PROFILE
Demographics (the basics):
- Age range
- Gender distribution (if relevant)
- Location (urban/suburban/rural, country, region)
- Income range
- Employment / life stage
Psychographics (the real stuff):
- Core values and beliefs
- Aspirations — what does their ideal future look like?
- Self-identity — how do they see themselves?
- What brands do they already love (and why)?
- What content do they consume?
- What communities are they part of?
Behavioral patterns:
- How do they make purchase decisions? (impulse vs. research-heavy)
- What triggers the search for a solution like this?
- Where do they discover new brands?
- What's their buying process?
03 — AUDIENCE PERSONAS
Create 2–3 detailed personas. Each persona represents a real archetype of the target audience — not an average.
For each persona:
[First Name], [Age] — [Job Title or Life Stage], [Location]
"[First-person quote — what they would say about their situation, in their own words]"
Their World: [2–3 sentences describing a day in their life, how this brand's category fits into it]
Goals:
- [Goal 1 — specific]
- [Goal 2 — specific]
- [Goal 3 — specific]
Frustrations:
- [Frustration 1 — with current options or the category]
- [Frustration 2]
- [Frustration 3]
What they need from a brand like this: [2–3 sentences — what would make them loyal customers]
Decision triggers: [What would make them buy? What would make them hesitate?]
Channels they're on: [Where to reach them — specific platforms, communities, media]
How [Brand] solves their problem: [One specific sentence connecting their frustration to this brand's differentiation]
04 — AUDIENCE LANGUAGE
What words and phrases does this audience use to describe:
Their problem: [3–5 direct quotes or paraphrases from real customer language — reviews, forums, interviews]
Their desired outcome: [3–5 phrases describing what success looks like to them]
Why they've chosen competitors: [What language do they use to justify current choices?]
Brand-building implication: [How should the brand use this language in its messaging?]
05 — WHO THIS BRAND IS NOT FOR
Just as important as defining who the brand is for — define who it isn't for. This sharpens positioning and prevents diluted messaging:
- [Audience type 1 and why they're not the target]
- [Audience type 2]
- [Audience type 3]
06 — AUDIENCE IMPLICATIONS
Translate audience insights into brand and marketing direction:
Messaging implications — what should the brand lead with for this audience?
Channel implications — where should the brand be present to reach them?
Voice implications — how should the brand communicate to resonate with this audience?
Product/experience implications — what does this audience's profile suggest about how the brand should operate?
Related Skills
- brand-positioning: Position the brand specifically for this audience
- brand-messaging: Build messaging that speaks directly to these personas
- brand-voice: Define a voice that resonates with this audience
- brand-strategy: Full strategic context incorporating audience insights
- brand-context: Foundation context for all brand work
Other versions3 projects use a version of this.
Word for word · 1
- xeroc/skills★ 1100% same
Edited · 2
- cofoundy/brand-skills★ 6799% same
- productionx-in/Core-Skills★ 197% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brand-architectureSkill
- brand-auditSkill
- brand-contextSkill
- brand-guidelinesSkill
- brand-identitySkill
- brand-initSkill
- brand-messagingSkill
- brand-positioningSkill
- brand-storySkill
- brand-strategySkill
- brand-voiceSkill
- competitor-brandingSkill
- namingSkill
- rebrandingSkill
- briefSkill
- capacitySkill
- commsSkill
- decideSkill
- evalSkill
- experimentSkill
- exposureSkill
- forecastSkill
- negotiateSkill
- onboardSkill
- optionsSkill
- planSkill
- premortemSkill
- reconSkill
- reviewSkill
- sitrepSkill
- stakeholdersSkill
- strategySkill
- systemsSkill
- threatSkill
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.

