Customer Persona logo

Customer Persona

Organization
inference-sh
customer-persona

Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. Use for: marketing strategy, product development, UX research, sales enablement, content strategy. Triggers: customer persona, buyer persona, user persona, target audience, ideal customer, customer profile, audience research, user research, icp, ideal customer profile, target market, customer avatar, audience persona

Overview

Publisherinference-sh
Repositoryskills
Skill namecustomer-persona
Stars
790
Forks
106
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by inference-sh on GitHub. Read the source before you install it.

Installation

Install the Customer Persona AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/inference-sh/skills/tree/main/guides/product/customer-persona
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/inference-sh/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/guides/product/customer-persona .claude/skills/customer-persona
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Customer Persona in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Customer Persona on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Customer Persona is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Install the belt CLI skill: npx skills add belt-sh/cli

Customer Persona

Create data-backed customer personas with research and visuals via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

bash
belt login

# Research your target market
belt app run tavily/search-assistant --input '{
  "query": "SaaS product manager demographics pain points 2024 survey"
}'

# Generate a persona avatar
belt app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a 35-year-old woman, product manager, friendly confident expression, modern office background, natural lighting, business casual attire, realistic portrait",
  "width": 1024,
  "height": 1024
}'

Persona Template

┌──────────────────────────────────────────────────────┐
│  [Avatar Photo]                                      │
│                                                      │
│  SARAH CHEN, 34                                      │
│  Product Manager at a Series B SaaS startup          │
│                                                      │
│  "I spend more time making reports than making       │
│   decisions."                                        │
│                                                      │
├──────────────────────────────────────────────────────┤
│  DEMOGRAPHICS          │  PSYCHOGRAPHICS             │
│  Age: 30-38            │  Values: efficiency, data   │
│  Income: $120-160K     │  Personality: analytical,   │
│  Education: BS/MBA     │    organized, collaborative │
│  Location: Urban US    │  Interests: productivity,   │
│  Role: Product/PM      │    leadership, AI tools     │
├──────────────────────────────────────────────────────┤
│  GOALS                 │  PAIN POINTS                │
│  • Ship features       │  • Too many meetings        │
│  faster                │  • Manual reporting (15     │
│  • Data-driven         │    hrs/week)                │
│  decisions             │  • Stakeholder alignment    │
│  • Team alignment      │    is slow                  │
│  • Career growth to    │  • Tool sprawl (8+ apps)   │
│    Director            │  • No single source of      │
│                        │    truth                    │
├──────────────────────────────────────────────────────┤
│  CHANNELS              │  BUYING TRIGGERS            │
│  • LinkedIn (daily)    │  • Peer recommendation      │
│  • Product Hunt        │  • Free trial experience    │
│  • Podcasts (commute)  │  • Integration with Jira    │
│  • Lenny's Newsletter  │  • Team plan pricing        │
│  • Twitter/X           │  • ROI calculator           │
└──────────────────────────────────────────────────────┘

Building a Persona Step-by-Step

Step 1: Research

Start with data, not assumptions.

bash
# Market demographics
belt app run tavily/search-assistant --input '{
  "query": "product manager salary demographics 2024 survey report"
}'

# Pain points and challenges
belt app run exa/search --input '{
  "query": "biggest challenges facing product managers SaaS companies"
}'

# Tool usage patterns
belt app run tavily/search-assistant --input '{
  "query": "most popular tools product managers use 2024 survey"
}'

# Content consumption habits
belt app run exa/answer --input '{
  "question": "Where do product managers get their industry news and professional development?"
}'

Step 2: Demographics

Use ranges, not exact values. Personas represent a segment, not one person.

FieldFormatExample
Age rangeX-Y30-38
Income range$X-$Y$120,000-$160,000
EducationCommon degreesBS Computer Science, MBA
LocationRegion/typeUrban US, major tech hubs
Job titleRole levelSenior PM, Product Lead
Company sizeRange50-500 employees
IndustrySectorB2B SaaS

Step 3: Psychographics

What they think, value, and believe.

CategoryQuestions to Answer
ValuesWhat matters most to them professionally?
AttitudesHow do they feel about their industry's direction?
MotivationsWhat drives them at work?
PersonalityAnalytical vs intuitive? Leader vs collaborator?
InterestsWhat do they read/watch/listen to professionally?
LifestyleWork-life balance preference? Remote/hybrid/office?

Step 4: Goals

What they're trying to achieve (both professional and personal).

Professional:
- Ship features faster with fewer meetings
- Make data-driven decisions (not gut feelings)
- Get promoted to Director of Product within 2 years
- Build a more autonomous product team

Personal:
- Leave work by 6pm more often
- Be seen as a strategic leader, not a ticket manager
- Stay current with industry trends without information overload

Step 5: Pain Points

Quantify whenever possible. Vague pain = vague persona.

❌ "Has trouble with reporting"
✅ "Spends 15 hours per week creating manual reports for 4 different stakeholders"

❌ "Too many tools"
✅ "Uses 8 different tools daily (Jira, Slack, Notion, Figma, Analytics, Sheets, Docs, Email) with no unified view"

❌ "Meetings are a problem"
✅ "Averages 6 hours of meetings per day, leaving only 2 hours for deep work"

Step 6: Jobs-to-be-Done (JTBD)

Three types of jobs:

Job TypeDescriptionExample
FunctionalThe task they need to accomplish"Prioritize the product backlog based on customer impact data"
EmotionalHow they want to feel"Feel confident presenting to the exec team"
SocialHow they want to be perceived"Be seen as the person who makes data-driven decisions"

Step 7: Buying Process

StageBehavior
AwarenessReads blog posts, sees peer recommendations on LinkedIn
ConsiderationCompares 3-4 tools, reads G2/Capterra reviews, asks in Slack communities
DecisionRequests demo, needs IT/security approval, evaluates team pricing
InfluencersEngineering lead, VP of Product, CFO (for budget)
Objections"Will my team actually adopt it?", "Does it integrate with Jira?"
Trigger eventNew quarter with aggressive goals, new VP demanding better reporting

Step 8: Generate Avatar

bash
# Match demographics: age, gender, ethnicity, professional context
belt app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot photograph of a 34-year-old Asian American woman, product manager, warm confident smile, modern tech office background, natural lighting, wearing smart casual blouse, realistic portrait photography, sharp focus",
  "width": 1024,
  "height": 1024
}'

Avatar tips:

  • Match the age range, ethnicity representation, and professional context
  • Use "professional headshot photograph" for realistic results
  • Friendly, approachable expression (not stock-photo-stiff)
  • Background suggests their work environment
  • Business casual or industry-appropriate attire

The Anti-Persona

Equally important: who is NOT your customer.

ANTI-PERSONA: "Enterprise Earl"
- CTO at a 5,000+ person enterprise
- Needs SOC 2, HIPAA, on-premise deployment
- 18-month procurement cycles
- Wants white-glove onboarding and dedicated CSM
- WHY NOT: Our product is self-serve SaaS for SMB/mid-market.
  Enterprise needs would require 2+ years of product investment.

Anti-personas prevent wasted effort on customers you can't serve.

Multiple Personas

Most products have 2-4 personas. More than 4 = too many to serve well.

PriorityPersonaRole
PrimaryThe main user and buyerWho you optimize for
SecondaryInfluences the buying decisionWho you need to convince
TertiaryUses the product occasionallyWho you support, not target

Validation

Personas based on assumptions are fiction. Validate with:

MethodWhat You Learn
Customer interviews (5-10)Real language, real pain points
Support ticket analysisActual problems, not assumed ones
Analytics dataActual behavior, not reported behavior
Survey (50+ responses)Quantified patterns across segments
Sales call recordingsObjections, buying triggers, language

Common Mistakes

MistakeProblemFix
Based on assumptionsFiction, not researchStart with data
Too many personas (6+)Can't serve everyone wellMax 3-4
Vague pain pointsNot actionableQuantify everything
Demographics onlyMisses motivations and behaviorAdd psychographics, JTBD
Never updatedBecomes outdatedReview quarterly
No anti-personaWasted effort on wrong customersDefine who you're NOT for
Single persona for allDifferent users have different needsPrimary/secondary/tertiary

Related Skills

bash
npx skills add inference-sh/skills@web-search
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: belt app list

Frequently asked questions

What does the Customer Persona AI skill do?

Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. Use for: marketing strategy, product development, UX research, sales enablement, content strategy. Triggers: customer persona, buyer persona, user persona, target audience, ideal customer, customer profile, audience research, user research, icp, ideal customer profile, target market, customer avatar, audience persona

Why use Customer Persona on TypingMind?

Because you install it once and use it with any model. Customer Persona is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Customer Persona in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/inference-sh/skills/tree/main/guides/product/customer-persona. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Customer Persona?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Customer Persona?

As many as you like. As long as a model supports skills, you can use Customer Persona with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Customer Persona AI skill free?

It is published on GitHub by inference-sh. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇